- Current Issue
- Online First
- Adopt
- Most Downloaded Archive
-
Deng Zhi, Wang Zhengyong, He Xiaohai, Teng Qizhi, He Haibo
2024,47(18):1-8, DOI:
Abstract:
In the field of oil and gas development, the sealing performance test of oil casing after installation is particularly important.Torque sequence data is an important basis for judging the sealing performance of the oil casing, which can be used to judge whether the buckle is qualified. In order to identify and classify the sealing performance of the oil casing by using the information of the buckled torque sequence data, a new network model was built which named PSE-TCN network based on the TCN model integrated with position encoding and self-attention mechanisms. By comparing the accuracy of results under different strategies, the learning process of the model was demonstrated. The effectiveness of this method was validated by comparing it with other network models. Experimental results show that torque sequence recognition accuracy was significantly improved by the PSE-TCN network compared with other classical network models and several improved TCN models. The recognition accuracy of this model achieved 93.41% on the self-made UCR_whorl dataset.
-
Yu Xiangdong, Yu Wenfeng, Ke Ruiting, Chen Hongyu, Tao Jianfeng
2024,47(18):9-14, DOI:
Abstract:
To enhance the stability of angle measurement methods based on single-vision techniques, which are susceptible to random disturbances from environmental or systemic sources, we propose a dual-viewpoint visual angle measurement method based on complex-valued neural networks. Feature extraction is conducted manually, followed by an assessment of the features’ relevance and monotonicity with respect to angles to facilitate feature selection. To address the significant numerical discrepancy between the 0° and 360° labels, which impacts training outcomes, angles are represented using Euler′s formula. This representation facilitates the construction of a complex-valued neural network with both complex inputs and outputs for angle computation. Experimental results demonstrate a significant improvement in measurement accuracy; the proposed method reduces the mean error by 0.322° and the root mean square error by 0.64° compared to methods based on deep neural networks using a single viewpoint, maintaining high performance across various environmental test sets. By leveraging the robustness against environmental disturbances provided by dual viewpoints and the strong fitting capabilities of complex-valued neural networks for angle labels, this model enhances the accuracy and stability of radial visual angle measurements while adhering to the constraints and stability of mathematical models.
-
Wu Jiangping, Liu Ruochen, Sun Jianzhong, Zuo Hongfu, Zhang Lanchun
2024,47(18):15-22, DOI:
Abstract:
Aiming at the problem of easy interference of electrostatic signal and low fault recognition rate when the new electrostatic monitoring technology is applied to rolling bearing fault diagnosis, a method of electrostatic signal recognition of rolling bearing fault based on the combination of Bayesian optimization SVM is proposed. First of all, through the electrostatic simulation test platform constructed, the electrostatic signals of different wear states high speed are collected, and the feature sets of different working conditions are selected according to the time domain feature parameters; and then the hyper-parameters of the minimum error of SVM are selected using Bayesian optimization to achieve the effect of completing the diagnostic model training, and the diagnostic accuracy of the models is evaluated with the results of the confusion matrix after training. The research results show that this method has certain recognition ability for bearings with different fault characteristics under electrostatic monitoring, and the Bayesian optimization algorithm can effectively improve the recognition efficiency, and its average recognition accuracy can reach 98.82%.
-
2024,47(18):23-30, DOI:
Abstract:
In the classification and recognition of motor imagery EEG features for limb movements, there exists a problem of low action recognition accuracy when fusing features from different domains. To address this issue, this study designs an EEG-symmetric positive definite network model for motor feature classification, tailored to the complex cross-domain relationships of motor imagery EEG features in multi-channel data collection. This model effectively extracts and integrates features from different domains, achieving accurate classification of limb features and action recognition based on EEG signals. Experimental results demonstrate that on the BCI Competition IV 2a dataset, which contains motor imagery data of four types of limb movements, the proposed classification model achieves an action recognition accuracy of 0.85 and a Kappa coefficient of 0.80, indicating high precision.
-
Liu Weihua, Yang Xiaona, Wu Qidong, Xie Jing, Chen Ziying, Li Honglian
2024,47(18):31-37, DOI:
Abstract:
The application formula and process of tobacco fragrance are the core technology of the tobacco industry. In China, each tobacco industry has chosen the construction of fragrance categories as the next round of strategic choices. Its differentiation is a technical key point for the competition among various cigarette brands. This paper proposes a machine vision method combining dual light source illumination to solve the problem of poor quality judgment by manual judgement in the processing of tobacco fragrance configuration and preparation, and designs and manufactures an appearance quality qualification detection device for tobacco fragrance based on this. Using white light and red light as the main test light sources and green light as auxiliary detection light source, a dual light source coaxial forward illumination environment is set up; by fixing the optical plate for lighting and image acquisition module as a whole and combining the slide table with the stepping motor to rotate and stop at designated points, the machine vision method is used to eliminate reflections and automatically analyze color model parameters and detect the appearance quality qualification of the tobacco fragrance. The results show that the relative standard deviation of the parallel test of single tube sample image is less than 0.9968%, and the relative standard deviation of the parallel test of the same batch sample is less than 0.021 7%. The experimental results show that the precision and repeatability of the instrument are good, and can provide support for further promoting the intelligent management of the tobacco fragrance configuration detection industry.
-
Jin Zilong, Qian Liang, Zhao Chen, Cui Xiaosong, Pan Chengsheng
2024,47(18):38-46, DOI:
Abstract:
In intelligent networks, multiple service flows have different transmission requirements in terms of delay and bandwidth, and the burstiness of self-similar traffic exacerbates delay and packet loss rate. To address this problem, an improved WFQ scheduling algorithm based on traffic prediction (LPR-WFQ) is proposed. This algorithm uses the TLGP strategy to classify traffic based on the mean and variance of traffic. Based on the Bayesian estimation idea, it predicts future traffic levels by calculating conditional transition probabilities. The weights are dynamically adjusted based on the prediction results and the mean arrival rate, thereby reducing delay and packet loss, improving service quality, and optimizing the calculation method of virtual finish time. Simulation results show that compared with other scheduling algorithms, this algorithm improves the delay, delay jitter, throughput and packet loss by 6.01%, 9.66%, 5.37% and 38.57% respectively, indicating that the algorithm can meet the performance requirements of differentiated services.
-
2024,47(18):47-53, DOI:
Abstract:
Aiming at the multi-point path planning problem of mobile robots, a path planning algorithm combining ant colony algorithm and bat algorithm is proposed in this paper. The ant colony algorithm is used to establish the shortest path network between nodes. The pointing angle and turning angle are introduced as heuristic information in the traditional ant colony algorithm to reduce the paths′ turning times and turning angles. The reward and punishment mechanism is used to optimize the pheromone updating mode and improve the convergence speed of the algorithm. The objective function of multi-point path planning is based on the shortest path network. When solving the optimal node access order, the structure of the bat algorithm is improved, the hierarchical search method and a new local optimization mechanism are introduced, and the bat algorithm′s solving accuracy, speed, and stability are improved. The simulation results demonstrate that the proposed algorithm effectively addresses the issue of multi-point path planning. In comparison to existing algorithms, it exhibits lower computational complexity, higher search efficiency, smoother overall paths, and shorter lengths.
-
Wang Xihong, Lei Bin, Li Yuanyuan, Zhang Li, Li Decang
2024,47(18):54-62, DOI:
Abstract:
To address problem that the ORB-SLAM2 algorithm is prone to mismatching and cannot build a dense map during feature matching, the GMS algorithm is introduced to improve the mismatching problem in the ORB-SLAM2 algorithm and add a dense map thread. First, an image pyramid is established, and a grid division is performed on each layer of the image pyramid to extract feature points. A four-tree strategy is introduced for feature point selection in each grid, resulting in a uniform distribution of feature points. Second, the GMS algorithm is introduced in the feature matching stage to eliminate false matches. Finally, the dense point cloud map is built based on the pose estimation and key frames. Through the experimental verification on TUM data set, the results show that the matching number of the improved algorithm is 7.82% higher than that of the original ORB-SLAM2 algorithm, and the matching time is reduced by 8.53%. The improved algorithm is applied to the automatic navigation and obstacle avoidance of mobile robot, which can improve the reliability and operation efficiency of the system.
-
Liao Liefa, Zhan Yumin, Liu Yingbao
2024,47(18):63-70, DOI:
Abstract:
It is essential to accurately predict the state of health (SOH) of lithium-ion batteries. Aiming at challenges such as differences in degradation mechanisms at different stages of a single battery cycle and incomplete data acquisition in practical utilization scenarios, a lithium-ion battery SOH estimation method based on Involution-Vision Transformer (IViT) is proposed. Features that can effectively characterize the degradation information of lithium-ion batteries are automatically extracted from the voltage-time profile, weights are adaptively assigned at different positions using the Involution module, and Vision Transformer is used to learn the high-level feature representations at different stages and capture the global dependencies. The experimental results show that the prediction error of IVIT is around 0.5%, and the error is only around 2% when the overall data is missing 50%, proving the effectiveness and stability of the proposed method.
-
Zhou Yaluo, Zhang Jie, Jin Chengnan, Liu Wenguang, Zhang Ruicheng
2024,47(18):71-79, DOI:
Abstract:
In the surface measurement of metal workpieces based on line structured light, this paper proposes a laser stripe centerline extraction algorithm based on improved principal component analysis to address issues such as strong reflection and laser stripe breakage on the surface of metal workpieces. Firstly, for the irregular reflection of metal workpiece surface, the optical fringe region of image was extracted based on maximal variance between clusters (OTSU); Secondly, in response to the problems of high convolution operations, low efficiency, and poor real-time performance of the Steger algorithm, an improved Steger algorithm based on principal component analysis (PCA) was proposed. The covariance matrix of the gradient vector was constructed using PCA to estimate the normal direction of the stripe, and the second-order Taylor expansion was used in this direction to obtain accurate sub-pixel coordinates of the stripe center. The experimental results show that the algorithm proposed in this paper can effectively extract laser stripe areas under severe reflection conditions on the surface of metal workpieces. At the same time, the standard deviation of the extracted laser stripe centerline is reduced by about 0.25 pixels compared to the grayscale centroid method, and the speed is increased by nearly 13 times compared to the Steger algorithm. It can quickly and accurately extract the laser stripe centerline, meeting the real time detection requirements of structured light 3D vision.
-
2024,47(18):80-88, DOI:
Abstract:
Aiming at the problems of poor structural consistency and insufficient texture details in the inpainting results of existing image inpainting algorithms, an image inpainting algorithm based on multi-feature fusion was proposed under the framework of generative adversarial network (GAN). Firstly, the dual encoder-decoder structure is used to extract the texture and structure feature information, and the fast Fourier convolution residual block is introduced to effectively capture the global context features. Then, the information exchange between structure and texture features was completed through the attention feature fusion (AFF) module to improve the global consistency of the image. The dense connected feature aggregation (DCFA) module was used to extract rich semantic features at multiple scales to further improve the consistency and accuracy of the inpainted image, so as to present more detailed content. Experimental results show that, compared with the optimal comparison method, the proposed algorithm improves PSNR and SSIM by 1.18% and 0.70% respectively, and reduces FID by 3.99% on the Celeba-HQ dataset when the proportion of damaged regions is 40%~50%. On the Paris Street View dataset, PSNR and SSIM are increased by 1.17% and 0.50%, respectively, and FID is reduced by 2.29%. Experimentally, it is proved that the suggested algorithm can effectively repair large broken images, and the repaired images have a more sensible structure and richer texture details.
-
Zheng Huijie, Lyu Qingfeng, Zhu Zhixing, Yi Xiang, Min Chaobo
2024,47(18):89-99, DOI:
Abstract:
In order to further improve the compatibility of machine vision systems and enrich the types of video formats processed by encoding and decoding systems, a multi interface video encoding and decoding system based on FPGA was designed. By using the asynchronous DDR read-write principle to build the codec selection module and complete the conversion operation of different video formats, the final system supports the decoding of PAL, HDMI and Cameralink videos as well as the encoding functions of HDMI, Cameralink and LVDS videos. Meanwhile, by comparing the transmission characteristics of different video interfaces, the seamless conversion between the above video interface standards is realized. The system can not only be used as an independent video codec system, but also can be connected to ARM processor through LVDS interface, thus expanding its application scenarios. Experimental results show that the system can accurately decode PAL video with a resolution of 720×576, Cameralink video with a resolution of 640×512 and HDMI video with a resolution of 1 080p, and then output it through HDMI, Cameralink and LVDS video interfaces respectively. In addition, the consumption of all kinds of resources in the system does not exceed 50%, which ensures the efficient operation of the system.
-
Dang Ruiyang, Wu Kerui, Zhang Huixin, Zhang Hua, Yan Wenxuan
2024,47(18):100-107, DOI:
Abstract:
To address the frequent disassembly required for program updates in storage systems within the industrial testing field, as well as the unique need for data storage without a host computer, a smart online upgrade storage system design based on FPGA is proposed. This system utilizes FPGA as the main controller and employs a combination of Gigabit Ethernet and FLASH. Update instructions and configuration files are transmitted via Gigabit Ethernet to the program memory, where they are partitioned, erased, and written to SPI Flash, enabling online upgrades of the FPGA program. Additionally, the optocoupler instruction parsing module enables the system to operate independently of a host computer, performing intelligent data storage autonomously. Furthermore, the system integrates a reliable feedback design using a custom DR_UDP protocol, optimizing the communication efficiency and stability of the Gigabit Ethernet port. Functional verification analysis confirms that the system operates stably, flexibly, and reliably, with a Gigabit Ethernet transmission rate reaching 700 Mb/s, and no data loss detected. This system can be widely applied in various scenarios where disassembly is inconvenient.
-
Tan Huisheng, Yang Wei, Yan Shuqi
2024,47(18):108-119, DOI:
Abstract:
Spatio-temporal graph convolutional network (STGCN) enhances the accuracy of traffic speed prediction by capturing the spatial dependencies and temporal dependencies in traffic data through graph convolution and time convolution. However, the hardware implementation of traffic speed prediction using STGCN faces challenges such as high computational demands that do not meet the real-time requirements of practical applications and high resource consumption leading to increased costs. To optimize the traffic speed prediction STGCN model, a method for optimizing the FPGA implementation structure combination of traffic speed prediction STGCN is proposed. Initially, the model is optimized through lightweight pruning and precise selection of prediction data bit-width to reduce computational complexity and resource consumption, verified by Python simulation for feasibility. Subsequently, an optimization strategy using pipeline, parallel computing, and alternating data stream storage is introduced to enhance system computational speed. Finally, the traffic speed prediction STGCN is implemented and tested on FPGA using Verilog programming. Experiments with the PeMSD7(M) dataset show that the FPGA implementation reduces the time for single data traffic speed prediction to 355.5 μs, maximum processing speed increases of 25.9×, 6.7× and 3.5× compared to CPU, GPU platform and FPGA design option 1 comparisons, respectively, proving that the proposed method significantly improves processing speed while maintaining prediction accuracy.
-
Zhao Xuesong, Fu Min, Liu Xuefeng
2024,47(18):120-129, DOI:
Abstract:
Deep learning has become one of the important tools for hyperspectral image classification due to its modular design and powerful feature extraction capability. However, effectively extracting deeper features and simultaneously improving the analysis of spatial and spectral joint features remains an urgent challenge. In response to these issues, a deep feature extraction residual network is proposed in this paper, composed of two key components: a multi-level transfer fusion residual network and a spatial-spectral multi-resolution fusion attention residual network. The multi-level transfer fusion residual network effectively promotes interaction between feature information to obtain deeper-level features. Subsequently, the spatial-spectral multi-resolution fusion attention residual network ensures comprehensive extraction of spatial-spectral joint features and multi-resolution features from hyperspectral data. To validate its effectiveness, the performance of the proposed method was evaluated on three hyperspectral datasets, Indian Pines, Pavia University, and Salinas Valley, achieving classification accuracies of 98.10%, 99.81%, and 99.94% respectively. Experimental results demonstrate that, compared to other methods, this network exhibits better generalization capability and classification performance.
-
Wang Min, Xu Yongqi, Cao Xiaomeng, Cao Ran, Ou Xiang
2024,47(18):130-137, DOI:
Abstract:
In order to realize unmanned production in factories, textiles need to be sorted efficiently. The manual classification method for traditional textile production plants has the problem of low efficiency and difficulty in meeting the needs of large-scale production. Artificial intelligence and computer vision advanced technology were applied to textile material classification, and a textile material classification algorithm based on DSCI-YOLOv8 was proposed. On the basis of the original classification network of the YOLOv8 model, the coordinate information attention module is added to enhance the model′s ability to extract the features of textile materials at different scales, improve the accuracy of network classification, and reduce some of the calculations and parameters required for calculation. Secondly, the distributed offset convolution is added to the C2f network module, which improves the network structure of the classification neural part, so that the memory usage is reduced and the computation speed is improved. Experimental results show that the accuracy of the improved model is increased by 2.09 percentage points and 13.5% increase in image processing per second compared with the YOLOv8 model. While greatly reducing the calculation cost, it effectively improves the accuracy and speed of textile material classification. It can meet the testing needs of the textile industry for product category classification and quality.
-
2024,47(18):138-144, DOI:
Abstract:
To address the problems of low accuracy, easy false detection and missed detection in the existing insulator self-explosion defect detection methods under complex backgrounds and foggy environments, an improved YOLOv8 insulator self-explosion defect detection algorithm is proposed. First, the SPD-Conv module for low resolution image and small target detection is introduced into the backbone network to fully extract the feature information of insulator defect target. Secondly, BiFPN is integrated with the SimAM attention mechanism to build the BiFPN_SimAM module, replacing the concat connection of PANet to achieve multi-scale feature fusion and enhance the overall performance of the network. The experimental results show that the precision and mAP@0.5 of the improved algorithm for insulator self-explosion defect detection reach 95% and 93.1%, respectively, which are increased by 1.8% and 1.5% compared with the original YOLOv8 algorithm, and it also has a good detection effect on insulator self-explosion defect detection under complex background and foggy environment.
-
Xu Jinda, Chen Cifa, Zhang Shang
2024,47(18):145-154, DOI:
Abstract:
To address the high proportion of small target objects in waterborne debris detection, the interference caused by multiple factors such as water surface fluctuations and shoreline reflections, and the high demands on device performance due to the large number of parameters and computational load of detection models, we propose a lightweight, high-precision, real-time detection model, LS-YOLO. First, this algorithm uses the HS-FPN pyramid network design to construct the Neck network structure of YOLOv8. The constructed network structure sacrifices a small part of the accuracy and significantly reduces the number of parameters and computational complexity of the model. Secondly, HS-FPN is improved by introducing the CAA context-anchored attention mechanism to capture remote contextual information to improve detection accuracy. Then, by replacing the loss function with Wise-IoUv3, which features a dynamic focusing mechanism, the detection performance is significantly improved, increasing the robustness of the model. Finally, LAMP pruning technology is used to prune the model to reduce the number of parameters and calculations of the model. The experiment shows that the improved LS-YOLO has a 0.9% increase in mAP50 compared to the baseline model, a 3.2% increase in recall, a reduction in parameters to 19.83% of the baseline model, a reduction in computational cost to 44.44%, and a reduction in model size to 22.22%. The optimized detection algorithm not only significantly improves detection performance and feature extraction accuracy, but also facilitates deployment on resource-constrained hardware platforms.
-
2024,47(18):155-163, DOI:
Abstract:
Addressing the issue of subpar performance in identifying shallow water marine life in underwater environments using existing methods, we propose an improved method based on the RT-DETR benchmark model. Initially, the reparameterization network RepViT is utilized as the backbone of the model, enhancing its feature extraction capabilities. Subsequently, a reparameterized parallel dilated convolution (RepPDC) is constructed and incorporated into the neck network, enabling the model to effectively capture long-range contextual information, thereby improving the model′s recognition accuracy. Lastly, a bidirectional feature fusion module (CAFM) is constructed based on the attention mechanism, enhancing the model′s ability to focus on key information in underwater environments. Experimental results demonstrate that the improved method significantly boosts the mAP50 to 87.5%, mAP75 to 70.9%, and mAP50:95 to 64.9%, with fewer parameters, making it a promising candidate for practical applications in the identification of shallow water marine life.
-
Li Miaomiao, Hua Caijian, Xie Tao, Xue Qingxia
2024,47(18):164-171, DOI:
Abstract:
To address the challenges in food image recognition caused by small inter-class differences, large intra-class variations, and complex structures, this paper proposes a food image recognition method that integrates multi-scale features and an attention mechanism. First, the ConvNeXt model, which has stronger feature extraction capabilities, is used as the backbone network to better capture the detailed features of food images. Next, an improved ASPP module is introduced to expand the receptive field and utilize multi-scale information, enhancing the model′s ability to capture features at different scales. Finally, an attention mechanism is added after each convolutional block to improve feature representation and the ability to capture contextual information. Experimental results show that the proposed method achieves accuracies of 91.56% and 87.22% on the extended Vireo Food172 dataset and the ETH Food101 dataset, respectively, which represents an improvement of 2.05% and 1.66% over the original model, thus verifying the effectiveness of the proposed method.
-
Xu Qianxiang, Zeng Yong, Lu Qian, Nan Yulong
2024,47(18):172-181, DOI:
Abstract:
To address the challenges of small defect targets, multi-scale issues, and high reflectivity on the surface of the inner car door handle, we first tackle the problem of defect features being obscured during image acquisition due to surface curvature and mirror reflection by using a bowl-shaped light source and reducing the angle of the image acquisition surface. Then, recognizing the limitations of traditional RT-DETR models, such as poor detection accuracy and slow speed, we propose an improved RT-DETR object detection method. This method builds upon the RT-DETR framework, utilizing parallel dilated convolutions and the CA attention mechanism combined with convolutional re-parameterization in the backbone network to increase the receptive field and establish long-distance semantic information while improving the network inference speed. Additionally, extra detection layers are added to improve the network′s feature extraction capability for small object detection. In the multi-scale feature fusion stage, we use an improved BIFPN structure to enhance the model′s information interaction capability. Finally, ablation experiments show that, compared to traditional RT-DETR-based detection methods, our proposed improved RT-DETR method increases the mean Average Precision by 6.5%, achieves a detection speed 1.6 times that of the traditional model, and reduces the model′s parameter count to only 76.5% of the original network, validating the effectiveness of our proposed method.
-
Xia Yunchao, Li Kun, Zhu Linfu
2024,47(18):182-192, DOI:
Abstract:
The railway signal system is an important technical means to ensure the safe and efficient operation of railway transportation. As a key equipment of the railway signal system, the completeness testing of the system itself is essential for the computer interlocking system. The interlocking human-machine interface is an important component of the interlocking system. Through the operation of the operators, control commands can be sent to the signal equipment, and on-site equipment status information can be received and displayed. Testing the interlocking human-machine interface according to standard specifications is an important technical means to ensure the normal operation of the interlocking system and ensure the safety of railway operations. At present, the testing of interlocking human-machine interfaces mostly relies on manual labor, which has problems such as low testing efficiency and untraceable testing processes. This article proposes a template matching scheme suitable for real-time graphical interface detection based on the normalized squared difference algorithm; analyze the local features of the interlocking human-machine interface image and propose a non-invasive and distortion free image pixel feature recognition method; modeling and abstracting manual operation steps into computer recognizable language; propose 13 custom keywords to simulate interlocking human-machine interface operations; automatically capturing and analyzing image, text, and speech information, accurately calculating the RGB primary color model values of the image, determining the compliance of test results with specifications, and improving the accuracy and consistency of detection results. After verification and comparison, the proposed interlocking human-machine interface detection method has achieved full process automation testing, visualized all operation processes, and traceable test results and intermediate links, greatly improving testing efficiency and the credibility of test results.
Volume 47, 2024 Issue 18
Research&Design
Theory and Algorithms
Application of Programmable Device
Information Technology & Image Processing
-
Study on Adaptive White Balance Scheme Based on Histogram
Abstract:
Aiming at the problems such as the limited application scenarios commonly existing in the automatic white balance algorithm (Auto White Balance, AWB), and taking into account factors such as real-time hardware processing, an adaptive automatic white balance algorithm is proposed and implemented in hardware using a Field Programmable Gate Array (FPGA). Firstly, the histograms of different color channels of the color image are statistically analyzed. Then, the similarity of histogram patterns among channels is determined by utilizing the histograms of different color channels, and based on this, an adaptive histogram adjustment algorithm is employed for white balance correction of different color images. Experimental results demonstrate that this algorithm exhibits superior adaptability and yields favorable processing effects for images rich in colors and those containing large area color blocks. Both subjective and objective evaluations have improved compared to single algorithms, and it is capable of real-time processing of images with a resolution of 1280*720@30fps on embedded devices, presenting excellent prospects for engineering applications.
- 1
-
Research on defect detection of drainage pipeline network based on improved YOLOv8
Abstract:
Addressing the issues of urban drainage pipeline defects being susceptible to background interference, the variability of characteristic scales, and the low detection accuracy and high false positive rate of existing detection models, this paper presents an improved defect detection algorithm based on YOLOv8. Initially, the DSK module is designed and embedded within the C2f module of the backbone network to expand the receptive field and improve the ability to extract multi-scale defect features. Subsequently, the Slim-neck network structure is introduced to refine the neck network, effectively utilizing and fusing defect feature information, which also contributes to the lightweightification of the model. Finally, the FocalEIOU loss function is adopted to enhance the detection performance for smaller defect targets and the convergence speed of the model. Experimental results on a pipeline defect dataset indicate that the proposed improved algorithm achieves a mean Average Precision (mAP) of 67.5% at a detection rate of 70.4 frames per second. Compared to the original YOLOv8 algorithm, the mAP value and detection speed are respectively increased by 3.8% and 1.7 frames per second, demonstrating superior detection performance. For the purpose of practical application, this paper has developed a system software capable of real-time detection of pipeline defects based on an improved algorithm. Through actual project detection, the enhanced algorithm proposed in this paper has been validated to meet the requirements of high precision and real-time detection for the task of urban drainage pipeline defect inspection.
- 1
-
Integrated navigation method based on adaptive anti-noise Kalman filter
Abstract:
With the rapid development of autonomous driving, the demand for high-precision real-time vehicle navigation and positioning technology is becoming increasingly urgent. In the commonly used GNSS/INS integrated navigation, adaptive Kalman filtering is a standard state prediction method. However, in complex dynamic environments, it has limitations in dealing with multipath noise from GNSS and real-time variations in process noise. To address this issue, this paper proposes an adaptive anti-noise Kalman filtering algorithm to suppress measurement noise from GNSS and dynamic process noise. The algorithm first preprocesses the original GNSS measurement data using variational mode decomposition and wavelet denoising to improve the input accuracy for data fusion. Secondly, during the data fusion process, a dynamic noise scaling factor that changes in real time with the vehicle environment is introduced. Through these two denoising steps, the overall interference of noise uncertainty on navigation accuracy is effecti
- 1
-
Research on ship berthing distance perception based on UAV vision
Abstract:
In order to solve the problem of limited field of view during ship berthing and achieve the visualization of berthing distance, a berthing distance perception method based on UAV vision is proposed. First, the UAV is used to collect the berthing video of the ship, and the EMA mechanism is added on the basis of the YOLOv8 segmentation model to achieve the fine segmentation of the ship edges. Next, the berth line is extracted by the regional growth algorithm and the Hough line detection. Finally, the closest distance calculation model is used to convert ships and berths into three-dimensional world coordinate system, and the closest distance between ships and berths is searched. The experimental results show that the accuracy of the algorithm after adding the EMA attention mechanism can reach 92.3% of the segmentation accuracy, and the error of the closest distance between the ship and the berth is less than 0.1m. This method can not only monitor the environment around the berthing ship, but also achieve the visualization of the distance between the ship and the berth, which has a good application prospect in berthing operation.
- 1
-
Research on parameter design of radiation biological effect Nanodosimeter
Abstract:
Nanodosimetry simulates the biological effects of radiation by measuring physical quantities, such as ions that are ionized by initial particles. The microchannel ionized ion counting nanodosimeter can measure ionized ions by utilizing an internal electric field to drive them into the microchannel, where they induce an electron avalanche under high voltage. This paper studies the parameter design of a nanodosimeter utilizing microchannel ionized ion counting, based on finite element analysis and the Monte Carlo method. COMSOL finite element analysis and Garfield++ Monte Carlo software are utilized to calculate and simulate the static electric field, the dynamic transport of ionized ions, and the formation of electron avalanches in microchannels. The characteristics of the internal electric field funnel effect were systematically studied under various anode and cathode electric field configurations. Additionally, the impact of these configurations on the dynamic transport and collection efficiency of ionized ions was analyzed. The dependence of electron avalanche on design parameters, such as electric field configuration and microchannel diameter, is examined, and the results are discussed and summarized. The analysis results indicate that selecting an anode voltage of (5~15) V, a cathode voltage of (-1500~ -2000) V, and a microchannel diameter of (0.5~0.75) mm can achieve good measurement performance. The research findings presented in this article will provide a crucial theoretical foundation for a deeper understanding of the internal mechanisms and parameter design optimization of nanodosimeters.
- 1
-
GNSS/UWB/IMU integrated indoor and outdoor seamless positioning method with robustness estimation
Abstract:
In order to solve the problems of low positioning accuracy and poor continuity in the single navigation source positioning system in indoor and outdoor seamless positioning, a GNSS/UWB/IMU integrated indoor and outdoor seamless navigation and posi-tioning algorithm based on robust estimation was proposed. In the face of complex indoor and outdoor scene switching, the robustness estimation algorithm is used to evaluate the confidence level of the two observation signals collected by GNSS and UWB and fuse them, and the fused data is used as the new observation value, and the extended Kalman filter algorithm is used to fuse the new observation value with the data of the inertial system to achieve fusion positioning. In order to evaluate the navi-gation and positioning accuracy of the algorithm in the presence of interference and noise, the inertial navigation positioning module, the satellite positioning module and the ultra-wideband tag were integrated together and field tests were carried out. Experiments show that the root mean square error of the proposed fusion positioning method is 6.40cm in the east direction and 6.73cm in the north direction, and the maximum error is not more than 28.55cm.
- 1
-
Non constant modulus APCMA signal recognition method based on signal-to-noise ratio estimation
Abstract:
This paper proposes a recognition algorithm based on signal-to-noise ratio estimation for the identification of non constant modulus signals in asymmetric paired carrier multiple access (APCMA) in satellite communication signals. Firstly, the algorithm performs power spectrum estimation on the received signal to calculate the observed signal-to-noise ratio; Secondly, by calculating the effective signal-to-noise ratio through high-order moment calculation and combining it with constellation moment algorithm, the problem of large errors in the effective signal-to-noise ratio of non constant modulus signals in high-order moment calculation has been solved; Finally, based on the characteristic that the observed signal-to-noise ratio of the mixed signal is higher than the effective signal-to-noise ratio, a feature parameter M was designed to achieve the recognition of non constant modulus APCMA signals. The experimental results show that the proposed algorithm achieves a recognition rate of nearly 100% for non constant modulus APCMA signals when the signal-to-noise ratio of weak signals is greater than 0dB.
- 1
-
Fabric Seam Detection Algorithms Based on Improved YOLOv8
Abstract:
Fabric seams detection in industrial setting is becoming increasingly important in textile applications. However, seam detection faces challenges such as small target size, few available features, and complex environmental factors, which make it difficult to ensure stable and real-time detection results. A fabric seam detection algorithm YOLOv8-DVB based on improved YOLOv8 is proposed to address this series of problems. The C2f module is optimized based on the characteristics of Deformable Convolutional Networks v4, a C2f-DCN module with multi-size feature sampling is proposed to strengthen the network"s extraction of feature information of different sizes. In the neck, the BiFPN structure is used as a feature fusion approach, which allows features of different scales to be more fully fused at multiple levels by introducing top-down and bottom-up bidirectional pathways. Additionally, a more efficient VoV-GSCSP module is introduced to lightweight the feature fusion network, which helps the neck network to reduce the computational load and parameter count. Finally, a dedicated small target detection layer is designed to optimize the feature extraction of small targets. YOLOv8-DVB is compared with the original model as well as YOLOv5, YOLOv7, and Faster R-CNN through experiments to verify the detection accuracy and detection precision. The experimental results show that the method obtains 84.7% detection accuracy on the self-constructed dataset, which is higher than the original model and other network models, and is able to quickly and effectively accurately detect the target categories and locations in complex industrial environments.
- 1
-
Model predictive control of PMSM based on SMA optimization
Abstract:
To address the issues of slow dynamic response and large current ripple in traditional control of permanent magnet synchronous motors, an improved model predictive control algorithm is proposed based on a novel dual-power sliding mode integral speed controller optimized by the slime mold algorithm. First, the velocity loop adopts a new double power convergence law sliding mode velocity controller to control the motor more accurately. The stability of this method is validated using the Lyapunov function. Second, the slime mold optimization algorithm is applied to optimize the parameters of the dq-axis PI controller, enabling rapid determination of the optimal PI parameters. At the same time, current model predictive control is employed to reduce current ripple. Finally, from a microscopic perspective, a 3D phase diagram of dq-axis current and motor speed (n) is drawn to further verify the effectiveness of the controller. Simulation results show that compared with the traditional PI-MPC, SMC-MPC and NSMC methods, the proposed method NSMC-MPC has significant advantages in dynamic response speed, speed stability and anti-interference ability, which can significantly reduce the overshooting and current pulsation, and improve the dynamic performance and load adaptability.
- 1
-
A lightweight contraband detection algorithm focusing on edge and multi-scale Features
Abstract:
To address challenges such as complex backgrounds, varying scales, and the difficulty of detecting small objects in X-ray security images, we propose a lightweight contraband detection algorithm named LEM-YOLO, which focuses on enhancing edge and multi-scale features. First, a Lightweight Edge Feature Enhancement module (LEFE) is designed to construct the EFE_C2f, enhancing the model"s capability to extract edge features. Next, we develop an Efficient Multi-level Feature Fusion Pyramid Network (EM-FPN) that utilizes Dynamic Upsampling (Dysample) and the Hierarchical Scale Feature Pyramid Network (HS-FPN) to enhance multi-scale feature fusion and reduce computational redundancy. Additionally, a Dynamic Feature Encoding module (DFE) is employed to preserve global information for small-sized objects. Finally, Shape-IoU is used as the bounding box regression loss function, focusing on the shape and scale of the bounding boxes to improve object localization accuracy. Experimental results on the publicly available SIXray dataset show that LEM-YOLO achieves a mean Average Precision (mAP) of 94.63%, which is a 2.56% improvement over the original algorithm. Furthermore, the model size is reduced by 50.67%, making it better suited for contraband detection scenarios compared to similar algorithms.
- 1
-
Study on Bilinear Self-Attention mechanism for CAN bus intrusion detection method
Abstract:
The CAN bus is widely used in industrial data acquisition, Internet of Vehicles, and other fields, making its security intrusion detection very important.To comprehensively enhance the performance of the detection method, a bilinear self-attention mechanism for CAN bus intrusion detection is proposed. Firstly, based on the idea of stacked integration, DNN, CNN, and LSTM models are used to extract and generate deep learning layer feature data;Then, bilinear layers are used to generate self-attention mechanism and FNet feature data separately, which are then fused with deep learning layer feature data through a residual connection layer, and intrusion detection prediction is performed through a fully connected layer, demonstrating high accuracy, detection rate, and good generalization characteristics.Experiments on the Car_Hacking public dataset show that the accuracy, precision, recall, F1 score, and AUC values are 0.951, 0.996, 0.997, 0.960, and 0.984, respectively, and as the number of training epochs increases, the accuracy and loss value error remain within 5% and 10%, respectively, indicating that this method outperforms other comparison methods.Application to IoT experimental devices evaluation shows that this method achieves a detection rate of 99.23% for abnormal attack identification, which has significant promotion value for enhancing the security performance of monitoring and control systems.
- 1
-
Novel 8th order SIW bandpass filter based on coupling matrix
Abstract:
To address the issues of large size and integration difficulty in traditional Ku-band bandpass filters, this paper proposes a novel 8th-order SIW bandpass filter utilizing LTCC technology. The filter features an effective coupling topology, with eight SIW cavities interconnected through electromagnetic hybrid coupling, achieving wide bandwidth and high out-of-band rejection. To reduce overall volume, the eight SIW cavities are divided into two layers, with four cavities on each layer. By designing a coupling matrix and adjusting the coupling coefficients between the cavities, the filter"s volume is significantly reduced. Coplanar waveguide coupling is employed at the microstrip and SIW junctions, introducing two transmission zeros in the out-of-band region to suppress spurious passbands and further enhance out-of-band performance. Experimental results show that the filter has a bandwidth of approximately 13.3-17.2 GHz, a relative bandwidth (FBW) of 26%, an in-band insertion loss of less than -2.2 dB, and out-of-band rejection greater than -20 dB in the 18-20 GHz range.
- 1
-
Adaptive perception object detection network based on aerial photography
Abstract:
Due to the diverse height and angle of drone shots, the images often have complex backgrounds and mainly feature small targets. As a result, the performance of detection algorithms for these images is often poor. To address this issue, this paper presents a vehicle detection method for aerial images using an adaptive perception network. The goal is to improve the detection of small targets by focusing on two aspects: enhancing the saliency of vehicle features and improving the preservation of feature information. First, an adaptive perception feature extraction module is proposed to extract a more efficient feature representation. This module captures long-range dependencies and stronger geometric feature representations to adaptively model the shape of objects. Second, a dual-branch spatial perception downsampling module is introduced to mitigate information loss caused by down-sampling and continuous pooling. This module combines feature maps of different channels to maximize the retention of small target feature information. Next, the feature fusion network incorporates shallow feature maps with rich spatial information and adds detection heads to enhance the detection capability of small targets. Finally, a new dynamic regression loss function, DEloU, is designed. This function includes a penalty term to measure the correlation between the aspect ratio of the ground truth box and the detection box, further improving the prediction accuracy of the network. Experimental results on the Visdrone dataset show that the proposed method achieves an average precision (mAP) of 69.9% and an inference speed of 99.26FPS, indicating a good balance between speed and accuracy. Moreover, the proposed method has achieved the best detection accuracy on the UCAS-AOD dataset and has strong generalization ability.
- 1
-
Study on acceleration control strategy in resonant acoustic mixer
Abstract:
Given the control accuracy problem of the resonant acoustic mixer's acceleration, a radial basis function neural network (RBFNN) PID optimized by an improved sparrow search algorithm (ISSA) method is proposed to control acceleration. Firstly, the acceleration model is identified through the step response curve. Secondly, the sparrow search algorithm is enhanced by introducing a Tent chaos initializing population and a linear dynamic inertial weight method for updating the discoverer's position. Thirdly, ISSA is then applied to optimize the parameters of the RBFNN. Finally, the optimized RBFNN-PID is employed for the simulation test of acceleration and compared with other traditional algorithms. The simulation results show that the convergence speed and optimization ability of the developed ISSA are superior to other algorithms. It is found that the RBFNN-PID acceleration control optimized by ISSA can effectively suppress system overshoot and improve system control speed, accuracy, and stability. Experimental results show that, compared with the comparison algorithms, the RBFNN-PID acceleration control system optimized by ISSA demonstrates superior control performance and adaptive capability, providing a great practical value for the acceleration control of the resonant acoustic mixer.
- 1
-
Weakly supervised shadow-object instance detection with bidirectional learning
Abstract:
Current shadow-object instance detection methods rely on fully supervised training with mask labels. However, mask labeling is both complex and costly. Utilizing only bounding box labels for training can reduce annotation challenges and costs, but this weak supervision may decrease the accuracy of instance mask predictions. To address this issue, weakly supervised methods were first utilized for shadow-object instance detection. A weakly supervised shadow-object instance detection approach with bidirectional learning network is proposed. Firstly, a teacher-student bidirectional learning structure was designed, utilizing the predicted results of the teacher network as pseudo mask labels for the supervised training of the student network. The accuracy of weakly supervised detection was enhanced by updating the parameters of the teacher network using the exponential moving average method. Secondly, the prediction mask is precisely positioned using projection loss, and a color affinity index is introduced to represent the color prior information of the image. By integrating this with the cross-entropy loss function, a color affinity loss function is designed to enhance the network's overall detection performance. To verify the effectiveness of the proposed method and enhance the network's robustness, a shadow-object instance detection dataset was constructed. The predictive capability of the network was validated using both this dataset and the public dataset SOBA, with average precision values of 53.3 and 51.5, respectively.
- 1
-
IZOA-Transformer-BiGRU short-term wind power prediction based on decomposition technique
Abstract:
Accurate wind power prediction is crucial for ensuring the stable operation of power grids and improving the efficiency of wind resource utilization. To address the non-stationary and intermittent characteristics of wind power data, this paper proposes a combined IZOA-Transformer-BiGRU prediction model based on data decomposition techniques to enhance the accuracy and reliability of short-term wind power forecasting. First, the energy difference method is employed to determine the number of sub-modalities for variational mode decomposition, which decomposes the original wind power with strong random fluctuations into a series of relatively stable sub-sequences, enabling better more effective extraction of temporal features. Next, the Transformer-BiGRU model is constructed, incorporating a multi-head attention mechanism to process interactions between multiple features in parallel, while the BiGRU component captures temporal dependencies within the sequence, thus enhancing prediction performance. To further improve the model’s forecasting accuracy, an improved zebra optimization algorithm, integrating singer chaotic mapping, lens refraction-based learning, and the simplex method, is developed to optimize four key hyperparameters of the Transformer-BiGRU model: the number of hidden layer neurons, initial learning rate, regularization coefficient, and the number of attention heads. Finally, the IZOA-Transformer-BiGRU model predicts the subsequences derived from VMD, and the final prediction is reconstructed through aggregation. Experimental results show that, compared to the standalone BiGRU model, the proposed model improves the coefficient of determination by 5.10% and reduces the mean absolute error, root mean square error, and mean absolute percentage error by 56.17%, 54.58%, and 54.55%, respectively. demonstrating its high prediction accuracy.
- 1
-
Small target detection algorithm for traffic signs in complex scenes
Abstract:
In the application of traffic sign recognition, most of the targets to be detected are small targets, which are prone to problems such as missed detection and false detection. In order to solve these problems, an improved traffic sign recognition algorithm, FKDS-YOLOv8s, was designed based on the YOLOv8s algorithm. FasterBlock is used to reconstruct the C2f module to form a new lightweight module C2f-Faster, which not only improves the feature extraction ability of the model, but also reduces the computational overhead. Based on the SENet and ResNeXt models, a new detection head Detect_SR was designed to enable the model to effectively focus on the key features of small targets. DySample, a lightweight and efficient dynamic upsampler, significantly reduces GPU memory consumption. By increasing the output level of upsampling and prediction, the model can capture rich position information, which effectively solves the problem of insufficient information when the YOLOv8s model processes small targets. The Shape-
- 1
-
Surface defect detection algorithm of transmission line insulators based on YOLOv8
Abstract:
Aiming at the problems of complex image background and poor recognition of small defect targets in the current insulator surface defect recognition, a transmission line insulator surface defect recognition algorithm based on YOLOv8 is proposed. Firstly, the CAF module is introduced in the backbone network to enhance the model's analysis of complex image scenes and enhance the ability to extract global and local features; secondly, the GD mechanism is added to the neck network of the model to reduce the loss of information in the feature fusion process and improve the small target detection ability; finally, the ATFL classification loss function is used to weaken the interference of complex background on small target detection, and the PIOU bounding box loss function is introduced to improve the recognition accuracy and accelerate the model convergence speed. Experimental results show that the mAP50 of the algorithm reaches 94.1%, the precision rate reaches 92.5%, and the recall rate reaches 91.3%, which are 3.1%, 0.7%, and 3.9% higher than the baseline model, respectively, and the comprehensive performance is better than the recent YOLOv9s, YOLOv10s and other representative algorithms.
- 1
-
Research on Four-level Charging Control Strategy Based on Improved MPPT Algorithm
Abstract:
Aiming at the problem of unstable and random power input in the traditional three-stage charging method of battery, this study proposes a photovoltaic energy storage charging control strategy based on the maximum power point tracking ( VSS-POM-MPPT ) algorithm of variable step perturbation observation method based on perturbation observation method ( POM ) and the four-stage charging algorithm. By building a photovoltaic model, the tracking speed of maximum power point tracking ( MPPT ) of VSS-POM and POM is compared. At the same time, the voltage stabilization accuracy and current stabilization accuracy are used as the performance evaluation indexes of photovoltaic cells for battery charging. The controller program design based on VSS-POM-MPPT algorithm is completed, and the charging experiment of photovoltaic cell to battery is carried out. The experimental results show that the time of VSS-POM-MPPT is 0.008 s less than that of POM-MPPT when tracking the maximum power point, and the speed is increased by 24.3 %. The battery charging data recorded in the experiment is consistent with the charging algorithm designed in this study. The voltage stabilization accuracy and current stabilization accuracy are ± 0.4 % and ± 0.8 %, respectively, which meet the power industry standards of ± ( 0.5 % -1 % ) and ± ( 1 % -2 % ).
- 1
-
Design of flexible OAM array antenna in terahertz band
Abstract:
Aiming at the problems of the current OAM antenna, such as fewer modes, and difficulty to conform, this paper designs a terahertz-frequency array antenna using graphene and MXene. By adjusting the feed phase difference, the antenna can generate OAM vortex waves with integer mode of 0~3 and fractional mode of 0.5, 1.5 and 2.5. The use of graphene material allows the antenna to be reconfigurable within a frequency range of 1.1~1.9THz while maintaining a bandwidth of 0.3THz. To overcome the impact of bending on the antenna, compensation methods, including phase and frequency compensation, are proposed to maintain the vortex wave form and working frequency.
- 1
-
Xue Xianbin, Tan Beihai, Yu Rong, Zhong Wuchang
2024,47(6):1-7, DOI:
Abstract:
Urban intersections are accident-prone sections. For intelligent networked vehicles, it is very important to carry out risk detection and collision warning during driving to ensure the safety of driving. This paper proposes a traffic risk field model considering traffic signal constraints for urban intersections with traffic lights, and designs a three-level collision warning method based on this model. Firstly, a functional scenario is constructed according to the potential conflict risk points of urban intersections, and the vehicle risk field model is carried out considering the constraint effect of traffic signal. In order to solve the problem of collision warning, a three-level conflict area is proposed to be divided by the index, and the collision risk of the main vehicle is measured according to the position of the potential energy field around the main vehicle by calculating the corresponding field strength around the main vehicle. The experimental results show that the designed model can accurately warn the interfering vehicles entering the potential energy field of the main vehicle, the warning success rate can reach 100%, and the false alarm rate is only 3.4%, which proves the reliability and effectiveness of the proposed method.
-
Wei Jinwen, Tan Longming, Guo Zhijun, Tan Jingyuan, Hou Yanchen
2024,47(6):8-13, DOI:
Abstract:
To address the issue of low accuracy in indoor static target positioning with existing single-antenna ultra-high frequency RFID technology, this paper proposes a new RFID localization method based on an antenna boresight signal propagation model. The method first determines the height position of the target through vertical antenna scanning; secondly, it adjusts the antenna height to match that of the target and then performs stepwise rotational scanning to identify the target′s azimuth angle; furthermore, it utilizes a Sparrow Search Algorithm optimized back propagation neural network to establish a path loss model for ranging purposes; finally, it integrates the height, azimuth angle, and distance data to complete the target positioning. Experimental results show that in indoor environment testing, the proposed method has an average positioning error of 7.2 cm, which meets the positioning requirements for items in general indoor scenarios.
-
Zhang Huimin, Li Feng, Huang Weijia, Peng Shanshan
2024,47(6):86-93, DOI:
Abstract:
A lightweight improved model CAM-YOLOX is designed based on YOLOX to address the issues of false alarms of land targets and missed detections of shore targets encountered in ship target detection in large scene Synthetic Aperture Radar(SAR)images in near-shore scenes. Firstly, embed Coordinate Attention Mechanism in the backbone to enhance ship feature extraction and maintain high detection performance; Secondly, add a shallow branch to the Feature Pyramid Network structure to enhance the ability to extract small target features; Finally, in the feature fusion network, Shuffle unit was used to replace CBS and stacked Bottleneck structures in CSPLayer, achieving model compression. Experiments are carried out on the LS-SSDD-v1.0 remote sensing dataset. The experimental results show that compared with the original algorithm, the improved algorithm in this paper has the precision increased by 5.51%, the recall increased by 3.68%, and the number of model parameters decreased by 16.33% in the near-shore scene ship detection. The proposed algorithm can effectively suppress false alarms on land and reduce the missed detection rate of ships on shore without increasing the number of model parameters.
-
Zhang Fubao, Wu Ting, Zhao Chunfeng, Wei Xianliang, Liu Susu
2024,47(6):100-108, DOI:
Abstract:
In real-time detection of saw chain defects based on machine vision, factors like oil contamination and dust impact image brightness and quality, leading to a decrease in the feature extraction capability of the object detection network. In this paper, an automated saw chain defect detection method that combines low-light enhancement and the YOLOv3 algorithm is proposed to ensure the accuracy of saw chain defect detection in complex environments. In the system, the RRDNet network is used to adaptively enhance the brightness of the saw chain image and restore the detailed features in the dark areas of the image. The improved YOLOv3 algorithm is used for defect detection. FPN structure is added with a feature output layer, the a priori bounding box parameters are re-clustered using the K-means clustering algorithm, and the GIoU loss function is introduced to improve the object defect detection accuracy. Experimental results demonstrate that this approach significantly improve image illumination and recover image details. The mAP value of the improved YOLOv3 algorithm is 92.88%, which is a 14% improvement over the original YOLOv3. The overall leakage rate of the system eventually reduces to 3.2%, and the over-detection rate also reduces to 9.1%. The method proposed in this paper enables online detection of saw chain defects in low-light scenarios and exhibits high detection accuracy for various defects.
-
Fang Xin, Shen Lan, Li Fei, Lyu Fangxing
2024,47(6):20-27, DOI:
Abstract:
The high-frequency measurement data of underground vibration signals can record more specific details about the dynamic response of drilling tools, which is helpful for analyzing and diagnosing abnormal vibrations underground. However, the high-frequency measurement generates a large amount of measurement data, resulting in significant storage pressure for underground vibration measurement equipment. The proposed method uses compressed sensing technology to selectively collect and store sparse underground vibration data and then recover high-frequency measurement results through a signal reconstruction algorithm. In the process of realizing this method, an innovative method of constructing a layered Fourier dictionary against spectrum leakage is proposed, and an improved OMP signal reconstruction algorithm based on layered tracking is researched and realized, which greatly reduces the time required for signal recovery. Simulation and experimental test results demonstrate the method′s effectiveness, achieving a system compression ratio of 18.9 and a reconstruction error of 52.1 dB. The proposed method may greatly reduce the data storage pressure of the measuring equipment in the underground, and provides a new way to obtain high-frequency measurement data of underground vibration.
-
Wang Huiquan, Wei Zhipeng, Ma Xin, Xing Haiying
2024,47(6):14-19, DOI:
Abstract:
To solve the problem of low control accuracy of the tidal volume emergency ventilation for lower air pressure at high altitudes, we propose a dual-loop PID tidal volume control system, which utilizes a pressure-compensated PID controller to adjust fan speed, supplemented by an integral-separate PID controller in order to achieve precise control of airflow velocity.Compared with single-loop PID control, the rapid response and no overshooting are observed in the performance tests of the dual-loop control system at an altitude of 4 370 m and atmospheric pressure of 59 kPa, in addition, the output error of the average airflow velocity decrease to 3.19% (the maximum error is 4.1%), which is superior to that of current clinical equipment. Our work offers an effective solution for high-altitude emergency ventilator tidal volume control, and contributes important insights to the development of ventilation control technology in special environments.
-
Zhan Huiqiang, Zhang Qi, Mei Jianing, Sun Xiaoyu, Lin Mu, Yao Shunyu
2024,47(6):123-130, DOI:
Abstract:
Aiming at the force test in low-speed pressurized wind tunnel, the original data source of aerodynamic characteristic curve is analyzed. With the balance signal, flow field state and model attitude as the main objects, combined with the test control process, the abnormal detection methods and strategies of the test data are studied from the dimensions of single point data vector, single test data matrix and multi-test data set in the same period, and an expert system for abnormal data detection is designed and developed based on this core knowledge base. The system inference engine automatically detects online during the test, and realizes the pre-detection and pre-diagnosis of the original data through data identification, rule reasoning, logical reasoning and knowledge iteration. The experimental application results show that the expert system is highly sensitive to the detection of abnormal types such as abnormal bridge pressure, linear segment jump point and zero point detection, which guides the direction of abnormal data analysis and improves the efficiency of problem data investigation.
-
Zhang Bian, Tian Ruyun, Han Weiru, Peng Yuxin
2024,47(6):109-115, DOI:
Abstract:
In order to solve the problems that the traditional SPD life alarm characterization method can not clearly correspond to the real life state of SPD, and the remaining life model characterized by a single degradation related parameter has poor predictability, a multi-parameter SPD life remote monitoring system based on STM32 is designed. With STM32 as the main controller, the important parameters such as surge current, leakage current, surface temperature and tripping status of SPD are collected in real time, and the status information is uploaded to the One net cloud platform through the BC20 wireless communication module. The One net cloud platform displays and stores the multi-parameter data of SPD in real time, and provides data management and analysis. The SVM classification model is used to judge whether SPD is damaged and the BO-LSTM prediction model is used to predict the remaining life of SPD. Based on the positioning function of BC20, the real-time geographic location of SPD can be viewed on the host computer. The results show that the root mean square error and average absolute error of the BO-LSTM prediction model are 0.001 3 and 0.001 8, and the system can monitor the SPD status in real time, effectively predict the remaining life value of SPD, and give early warning in time.
-
Ma Zhewei, Zhou Fuqiang, Wang Shaohong
2024,47(6):94-99, DOI:
Abstract:
A feature point extraction algorithm based on adaptive threshold and an improved quadtree homogenization strategy are proposed to address the issue of low positioning accuracy or low matching logarithms of the SLAM system caused by the ORB-SLAM2 algorithm extracting fewer feature points in dark environments or environments with fewer textures, resulting in system crashes. Firstly, based on the brightness of the image, FAST (Features from Accelerated Seed Test) feature points are extracted using adaptive thresholds. Then, an improved quadtree homogenization strategy is used to eliminate and compensate the feature points of the image, completing feature point selection. The experimental results show that the improved feature point extraction algorithm increases the number of matching pairs by 17.6% and SLAM trajectory accuracy by 49.8% compared to the original algorithm in dark and textured environments, effectively improving the robustness and accuracy of the SLAM system.
-
Zhou Jianxin, Zhang Lihong, Sun Tenghao
2024,47(6):79-85, DOI:
Abstract:
Aiming at the problems that the standard honey badger algorithm (HBA) is easy to fall into local optimum, low search accuracy and slow convergence speed, a honey badger algorithm based on elite differential mutation (EDVHBA) is proposed. The elite solution searched by the two optimization strategies in the standard HBA is combined with differential mutation to generate a new elite solution. The use of three elite solutions to guide the next iteration of the population can increase the diversity of the algorithm solution and prevent the algorithm from falling into premature convergence. At the same time, the nonlinear density factor is improved and a new position update strategy is introduced to improve the convergence speed and optimization accuracy of the algorithm. In order to verify the performance of the algorithm, simulation experiments are carried out on eight classical test functions. The results show that compared with other swarm intelligence algorithms and improved HBA, EDVHBA can find the optimal value 0 in the unimodal function, and converge to the ideal optimal value in the multimodal function after about 50 iterations, which verifies that EDVHBA has better optimization performance.
-
Ma Dongyin, Wang Xinping, Li Weidong
2024,47(6):58-63, DOI:
Abstract:
Aiming at the Automatic Train Operation of high-speed train,an algorithm based on BAS-PSO optimized auto disturbance rejection control (ADRC) is used to design speed tracking controller.The ADRC is designed based on the train dynamics model,ITAE is used as the objective function,and the parameters are tuned by BAS-PSO.CRH380A train parameters are selected, The tracking effect of BAS-PSO, PSO and improved shark optimized ADRC algorithm on the target speed curve of the train is compared by MATLAB simulation,The tracking error of the train target speed curve based on the BAS-PSO optimized ADRC algorithm is kept in the range of ±0.4 km/h,which is closer to the target speed curve than the other two algorithms.The results show that the ADRC based on BAS-PSO optimization has the advantages of small tracking error and strong anti-interference ability.
-
Li Ya, Wang Weigang, Zhang Yuan, Liu Ruipeng
2024,47(6):64-70, DOI:
Abstract:
A task offloading strategy based on Vehicle Edge Computing (VEC) is designed to meet the requirements of complex vehicular tasks in terms of latency, energy consumption, and computational performance, while reducing network resource competition and consumption. The goal is to minimize the long-term cost balancing between task processing latency and energy consumption. The task offloading problem in vehicular networks is modeled as a Markov Decision Process (MDP). An improved algorithm, named LN-TD3, is proposed building upon the traditional Twin Delayed Deep Deterministic Policy Gradient (TD3). This improvement incorporates Long Short-Term Memory (LSTM) networks to approximate the policy and value functions. The system state is normalized to accelerate network convergence and enhance training stability. Simulation results demonstrate that LN-TD3 outperforms both fully local computation and fully offloaded computation by more than two times. In terms of convergence speed, LN-TD3 exhibits approximately a 20% improvement compared to DDPG and TD3.
-
Shi Shujie, Zhao Fengqiang, Wang Bo, Yang Chenhao, Zhou Shuai
2024,47(6):116-122, DOI:
Abstract:
Rolling bearings play an important role in rotating machinery. If a fault occurs, it can cause equipment shutdown, and in severe cases, endanger the safety of on-site personnel. Therefore, it is necessary to diagnose the fault. In response to the difficulty in extracting fault features of rolling bearings and the low accuracy of traditional classification methods, this paper proposes a fault diagnosis method based on Set Empirical Mode Decomposition (EEMD) energy entropy and Golden Jackal Optimization Algorithm (GJO) optimized Kernel Extreme Learning Machine (KELM), achieving the goal of extracting fault features of rolling bearings and correctly classifying them. Through experimental data validation, this method can extract the fault information features hidden in the original signal of rolling bearings, with a diagnostic accuracy of up to 98.47%.
-
Feng Zhibo, Zhu Yanming, Liu Wenzhong, Zhang Junjie, Li Yingchun
2024,47(6):34-40, DOI:
Abstract:
The data bits and spread spectrum codes of the spaceborne spread-spectrum transponder are asynchronous. Due to the influence of transmission system noise and Doppler frequency shift, it can cause attenuation of peak values related to receiving and transmitting spread spectrum codes, leading to a decrease in capture performance. Traditional capture techniques often have problems such as high algorithm complexity, slow capture speed, and difficulty adapting to the requirements of large frequency offsets of hundreds of kilohertz. This article proposes a spread spectrum sequence search method that truncates the spread spectrum sequence into two segments for correlation operations, and combines the signal squared sum FFT loop for a large frequency offset locking, effectively suppressing the attenuation of correlation peaks and improving pseudocode capture performance. MATLAB simulation and FPGA board level testing show that the proposed spread spectrum signal capture scheme can resist Doppler frequency shifts of up to ±300 kHz, with an average capture time of about 95 ms. In addition, the FPGA implementation of this algorithm saves about 47% of LUT, 43% of Register, and more than half of DSP and BRAM resources compared to traditional structures, making it of great application value in resource limited real-time communication systems.
-
Cheng Dongxu, Wang Ruizhen, Zhou Junyang, Zhang Kai, Zhang Pengfei
2024,47(6):137-142, DOI:
Abstract:
For the tobacco industry, there is currently no detection device and method for detecting the heating temperature and temperature uniformity of heated cigarette smoking sets. In order to solve the temperature measurement needs of micro rod-shaped heating sheets in a narrow space, this article developed a cigarette heating rod thermometer, and designed a new structure suitable for temperature measurement of cigarette heating rods. In order to verify the accuracy and reliability of the measurement results of the cigarette heating rod thermometer, uncertainty analysis of the thermometer was performed. The analysis results are based on the "GB/T 13283-2008 Accuracy Level of Detection Instruments and Display Instruments for Industrial Process Measurement and Control" standard. The measurement range is 100 ℃~400 ℃, meeting the requirements of level 0.1. The final experiment verified that the heating temperature field of different cigarettes can be effectively measured.
-
Chen Haoan, Li Hui, Huang Rui, Fu Pingbo, Zhang Jian
2024,47(6):182-189, DOI:
Abstract:
Facing the challenges of regulating unmanned aerial vehicles (UAV), and based on an YOLOv5-Lite improved model, this paper incorporates an exponential moving sample weight function that dynamically allocates loss function weights to the model during the training iteration. Through model computations, we achieve real-time UAV tracking using a two-degree-of-freedom servo platform. Furthermore, video capture, model calculations, and servo control are all performed locally on a Raspberry Pi 4B.The optimized model maintains the original model's parameter count while achieving a mAP@.5:.95 score of 70.2%, representing a 1.5% improvement over the baseline model. Real-time inference on the Raspberry Pi yields an average speed of 2.1 frames per second (FPS), demonstrating increased processing efficiency. Simultaneously, the Raspberry Pi controls a servo platform via the I2C protocol to track UAV targets, ensuring real-time dynamic monitoring of UAVs. This optimization enhances system reliability and offers superior practical value.
-
Zhou Guoliang, Zhang Daohui, Guo Xiaoping
2024,47(6):190-196, DOI:
Abstract:
The gesture recognition method based on surface electromyography and pattern recognition has a broad application prospect in the field of rehabilitation hand. In this paper, a hand gesture recognition method based on surface electromyography (sEMG) is proposed to predict 52 hand movements. In order to solve the problem that surface EMG signals are easily disturbed and improve the classification effect of surface EMG signals, TiCNN-DRSN network is proposed, whose main function is to better identify the noise and reduce the time for filtering the noise. Ti is a TiCNN network, in which convolutional kernel Dropout and minimal batch training are used to introduce training interference to the convolutional neural network and increase the generalization of the model; DRSN is a deep residual shrinkage network, which can effectively eliminate redundant signals in sEMG signals and reduce signal noise interference. TiCNN-DRSN has achieved high anti-noise and adaptive performance without any noise reduction pretreatment. The recognition rate of this model on Ninapro database reaches 97.43% 0.8%.
-
2024,47(6):28-33, DOI:
Abstract:
With the increasing demand for satellite network, vehicle-connected network, industrial network and other service simulation, this paper proposes a multi-session delay damage simulation method based on delay range strategy to build flexible software network damage simulation, aiming at the problems of small number of analog links, low flexibility and high resource occupation of traditional dedicated channel damage instruments. In this method, the delay damage of each session flow is identified and controlled independently, and the multi-queue merging architecture based on time delay strategy is adopted to reduce the resource consumption. The experimental results show that compared with the traditional dedicated device and simulation software NetEm, the proposed method supports the independent delay configuration of million-level links, increases the number of session streams from ten to one million, and reduces the memory consumption by at least 85% under each bandwidth, which meets the requirements of large scale and accuracy, and greatly reduces the system cost.
-
Peng Duo, Luo Bei, Chen Jiangxu
2024,47(6):50-57, DOI:
Abstract:
Aiming at the non-range-ranging location problem of multi-storey WSN structures, a three-dimensional indoor multi-storey structure location algorithm IAODV-HOP algorithm based on improved Tianying is proposed in the field of large-scale indoor multi-storey structure location for some large commercial supermarkets, hospitals, teaching buildings and so on. Firstly, the nodes are divided into three types of communication radius to refine the number of hops, and the average hop distance of the nodes is modified by using the minimum mean square error and the weight factor. Secondly, the IAO algorithm is used to optimize the coordinates of unknown nodes, and the population is initialized by the best point set strategy, which solves the problem that the quality and diversity of the population are difficult to guarantee due to the random distribution of the initial population in the Tianying algorithm. In addition, the golden sine search strategy is added to the local search to improve the position update mode of the population, and enhance the local search ability of the algorithm. Through simulation experiments, compared with traditional 3D-DV-Hop, PSO-3DDV-Hop, N3-3DDV-Hop and N3-ACO-3DDV-Hop, the normalized average positioning error of the proposed algorithm IAODV-HOP is reduced by 70.33%, 62.67%, 64% and 53.67%, respectively. It has better performance, better stability and higher positioning accuracy.
-
Yang Yi, Aimen Malik, Yuan Ruifu, Wang Keping
2024,47(6):41-49, DOI:
Abstract:
Hydraulic support pillar pressure prediction has been a pivotal basis for decision-making in the mining process. It has been one of the fundamental pieces of information for ensuring the stability of the surrounding rock. However, although the pressure of hydraulic support pillars followed certain patterns, it couldn’t be predicted using simple mathematical models. Additionally, during the mining process, issues such as the support detaching the roof, roof fragmentation, and sensor detection errors introduced a significant amount of random noise, turning the pressure data into a non-stationary time series. This significantly complicated the pressure prediction. Based on the Transformer model, this paper proposed a differencing non-stationary Transformer model, which introduced differencing normalization and de-normalization operations in the Transformer′s Encoder and Decoder, respectively, to enhance the stationarity of the series. At the same time, a de-stationary attention mechanism was deployed within the Transformer to calculate the correlations between sequence elements, which thereby enhanced the model′s predictive capabilities. Comparative experiments on a real coal mine support pillar dataset showed that the differencing non-stationary Transformer model proposed in this paper achieved a prediction performance of 0.674, which was significantly better than LSTM, Transformer, and non stationary Transformer models.
