Abstract:Exploring the optimal axial position of the relay coil of the three-coil magnetic coupling resonant wireless power transmission system is very important to optimize the transmission performance of the system. To this end, the transmission characteristics of the three-coil MCR-WPT system are deeply studied, the maximum power and maximum efficiency transmission conditions of the system are obtained by applying the circuit mutual inductance coupling theory combined with the coaxial coil mutual inductance calculation method. Based on the above optimal transmission conditions, the electromagnetic simulation of the influence of the axial offset of the relay coil on the transmission characteristics of the system in a wide load range is carried out. The simulation results show that the optimal axial position of the relay coil transmission power and transmission efficiency is related to the load, and both shift to the receiving coil side with the increase of the load. When the internal resistance of the power supply is equal to the load, the system can obtain the maximum transmission power when the relay coil is located in the middle of the coupling mechanism, and the system can obtain the maximum transmission efficiency when it is close to one side of the transmitting coil. Finally, a three-coil MCR-WPT system experimental platform is built, and the experiment verifies the correctness of the theory and simulation.

Abstract:To solve the problem that the evaporation duct data is easily disturbed by noise in compressed sensing and traditional reconstruction methods have poor performance in denoising, an adaptive regularized matching pursuit denoising method is proposed and it based on the similarity threshold. This method can gradually expand the candidate set by using the adaptive idea when the signal sparsity is difficult to be known. At the same time, some atoms are removed by setting the similarity threshold, and the support set atoms are screened by the regularization process, so that the reconstruction of noise components is better constrained and the reconstruction accuracy of signal is improved. Theoretical analysis and experiments show that the proposed method has better reconstruction performance than the existing similar reconstruction methods and has better denoising performance than the wavelet denoising method. The proposed method can obtain higher reconstruction SNR under the same conditions, and can effectively realize the denoising and reconstruction of the evaporation duct data.

Abstract:The state of health (SOH) estimation of lithiumion batteries at a low sampling frequency has great significance in engineering applications. The concepts of regional voltage (ΔV) and regional sampling points (RSP) are introduced, and an evaluation method of lithium-ion battery SOH under the framework of probability density function (PDF) is proposed. A battery SOH evaluation model based on RSP was established based on the laboratory cycle ageing data of lithium-iron phosphate (LFP) batteries. The RSP method and the traditional PDF method were compared, and the effects of the RSP-SOH models under different sampling frequencies and regional voltages were investigated. The results show that the RSP-SOH model has a linear positive correlation with SOH, and the effect of RSP-SOH model is better than that of the traditional PDF method under both charging and discharging conditions. The evaluation effect of the RSP-SOH model can be improved by increasing the region voltage appropriately when the sampling frequency is low. The battery RSP-SOH model is robust to the sampling frequency under the charging condition, and the R2 of the model is greater than 0.98 under the low sampling frequency of one sampling point every five minutes. On this basis, the SOH of 220 LFP batteries in an energy storage power station is relatively evaluated by using the regional sampling point method. When nine batteries with smaller RSP are replaced, the power handling capacity of the energy storage station will increase by 20.9%.

Abstract:Aiming at the prediction of industrial process quality with noise interference and delay, in this paper,we propose a method of stacking noise reduction auto-encoder embedded with attention mechanism and bidirectional long short-term memory network. Firstly, the AE model is constructed in an unsupervised manner, and the industrial data is reconstructed with Gaussian noise processing to achieve denoising and de-redundancy. Secondly, embed the attention mechanism to reconstruct the weight allocation of process variables to achieve deep feature extraction. Finally, the BLSTM network is used to learn and reconstruct the time series trend characteristics of the data to overcome the delay between the data, and fully explore the potential relationship between the process variables and the quality variables, and finally achieve accurate prediction. Through the simulation experiments of single-mass variable prediction of debutane process and multivariate mass prediction of sulfur recovery process, it is verified that the proposed method has a more accurate prediction effect than other methods such as BP, LSTM, BLSTM and DAE-BLSTM.

Abstract:Aiming at the phenomenon of low coverage and uneven nodes in three-dimensional wireless sensor networks with random deployment, taking the coverage as the fitness function, a coverage optimization algorithm for three-dimensional wireless sensor networks based on EGWOEO algorithm is proposed. Firstly, tent chaotic map is used to initialize the population to increase the diversity of the population. Secondly, reverse learning strategy is used to increase the global search ability. Thirdly, the hyperbolic tangent Gaussian strategy is integrated to strengthen the optimization ability of the algorithm. Then, a nonlinear convergence factor of sine and cosine function is proposed to balance the global and local search. Finally, the population position update equation is improved to speed up the convergence speed and accuracy of the algorithm. The improved EGWOEO algorithm is applied to 3D WSN coverage optimization, the simulation results show that compared with GWO, PSOGWO and LGWO algorithms, the average increment of 3D WSN coverage of EGWOEO algorithm is 11.023%, 10.662% and 12.401% respectively, which improves the uneven distribution of nodes and improves the utilization of nodes.

Abstract:Aiming at the problem that the ultrawideband signal is easily interfered by the harsh downhole environment, which leads to the large error of the existing downhole personnel location method, an improved algorithm based on the combination of SDS-TWR optimization method and robust Kalman filter is proposed. In this method, two ranging values from the positioning tag to the adjacent base station can be measured in a positioning period, which are then used as two observation values of robust Kalman filter to improve the positioning accuracy and stability of the algorithm and suppress the random NLOS delay error of roadway. Simulation results show that under the same conditions, the proposed algorithm reduces the error by 35% compared with S-TDOA and 31% compared with asynchronous timing method, and the error fluctuation is small. Meanwhile, the NLOS delay error of roadway is suppressed, and the positioning accuracy of downhole personnel is effectively improved.

Abstract:Among the various traffic accidents, the proportion of traffic accidents caused by the reduction of visibility caused by bad weather such as smog is increasing year by year, so the detection of visibility in bad weather has become an urgent problem to be solved. According to the different ways of extracting features, this paper not only divides the visibility detection methods into visual inspection methods, instrument and equipment detection methods and image algorithm detection methods, but also summarizes the development process of visibility detection methods. On the basis of analyzing and comparing the visibility detection methods based on deep learning, it is proposed that the introduction of the latest deep learning algorithm into visibility detection is the focus of follow-up research. Finally, the shortcomings and limitations of existing visibility detection methods are summarized, and the direction of further research in the future is pointed out.

Abstract:Aiming at the deficiency of current multi-mode multi-objective optimization algorithm in obtaining the integrity and convergence of Pareto solution set, a decision space self-organizing multi-mode multi-objective whale optimization algorithm (MMO_SOM_WOA) is proposed. First, whale optimization algorithm is used to solve multi-modal multi-objective problems for the first time, and the ability to find the integrity of Pareto solution set is improved through the randomness of whale optimization algorithm itself. Secondly, the self-organizing mapping network is combined with whale optimization algorithm to establish a good neighborhood for whale optimization algorithm at the beginning of iteration. Finally, the elite reverse learning strategy is used to initialize the population and non dominated sorting mechanism to obtain uniform and complete solutions. Through simulation comparison with the current five classical algorithms on multi-modal multi-objective optimization problems, the results show that MMO_SOM_WOA algorithm takes into account both the diversity of Pareto solution set and the integrity of Pareto solution. The convergence speed and convergence accuracy are improved and have high performance, effectively solving multi-modal and multi-objective optimization problems.

Abstract:Gas meters are widely used and need to be regularly and compulsorily replaced, and the first inspection items are complicated and workload is large, and the existing gas meter metering inspection line has low efficiency and no synergy in discrete testing. In this paper, we study the first inspection scheduling technology based on the gas meter metering inspection line, starting from the composition of the gas meter metering inspection line and the requirements of the first inspection items, and investigate the gas meter inspection scheduling modeling based on flexible job-shop scheduling problem, discrete particle swarm optimization based scheduling solution method to find the optimal task scheduling sequence. The experimental results of scheduling optimization for a batch of gas meters to be inspected show that the scheduling technique in this paper can reduce the total testing time by 33.3% and improve the inspection efficiency and equipment utilization.

Abstract:When single-phase grounding fault occurs in power system transmission and distribution lines, it is difficult to extract fault feature information due to electromagnetic environment interference of electrical equipment, complex fault zero sequence current components and other reasons. Variational modal decomposition parameters are determined artificially, resulting in poor decomposition effect of zero sequence current, slow entropy operation and poor robustness, and low accuracy of subsequent line selection, a new zero-sequence current fault feature extraction method for single-phase grounding fault based on NGO-VMD-DE is proposed. Firstly, the adaptive decomposition of the zero-sequence current signal is realized through the northern goshawk optimization algorithm (NGO) optimization variational modal decomposition (VMD), and the selection criteria of the intrinsic mode functions component of the adaptive correlation coefficient are established. The effective IMF component is selected, and then the selected IMF component is reconstructed. Finally, the dispersion entropy (DE) of the reconstructed signal is calculated to extract the zero-sequence current fault characteristics of single-phase grounding fault, the proposed fault feature extraction method can more accurately and effectively characterize the zero-sequence current fault information of single-phase grounding fault lines by building a model for simulation experiments and comparing it with other characteristic entropy.

Abstract:In order to improve the accuracy of radius measurement of round hole parts, an improved Zernike moment sub-pixel measurement method of round hole parts is proposed. First of all, the traditional Canny operator is improved, and the image input, denoising, gradient amplitude calculation and threshold selection are optimized to realize the rough location of the pixel-level edge coordinates of the circular hole center. Secondly, the edge pixel of the target region where the round hole is located is extracted, the new edge judgment condition is put forward on the basis of Ghosal algorithm and the best gray step threshold of Zernike moment is calculated by iterative method to judge and obtain the sub-pixel edge point, and the error is analyzed from the point of view of gray edge model. Finally, the high precision detection and measurement of the center coordinate and radius of the round hole are realized by using the least square principle. The simulation results show that the relative error of the center coordinate of the improved algorithm is in the range of 0.02 pixels and the relative error accuracy of the radius is in the range of 0.05 pixels. Through the actual measurement of several different parts, the experimental results show that, compared with the manual measurement value, the relative error of the improved algorithm and the original algorithm is lower, the actual value obtained is closer to the manual measurement value, and the measurement accuracy is obviously higher than that of the traditional Zernike moment algorithm. The measurement accuracy can meet the accuracy requirements of the production process of industrial parts.

Abstract:Aiming at the problem of outliers in the process of data collection, a data cleaning method based on improved GMM algorithm is proposed. Firstly, edge computing is introduced to solve the problem of excessive load. Secondly, in order to avoid falling into the local optimal solution when calculating the parameters of EM algorithm, the disadvantages of falling into the local optimal solution are improved by optimizing the parameters of GMM algorithm. The experimental results show that the improved GMM algorithm outperforms the GMM-EM algorithm in terms of recall and F value under a certain amount of data. It can be seen that the improved algorithm can improve the cleaning effect of abnormal data to a certain extent and ensure the reliability of data.

Abstract:In order to reduce the electromagnetic interference caused by the introduction of the 5G base station antenna into the substation to the sensitive equipment in the station, and to optimize the 5G signal at each monitoring device in the station, a method for 5G base station antenna placement in the substation based on the multi-objective particle swarm algorithm is proposed, namely. The radio frequency field strength at the sensitive equipment of the substation cannot exceed the specified electromagnetic compatibility immunity limit as the constraint condition, and the Pareto optimal solution of the signal received by the monitoring equipment in the station is used as the objective function. Find the most suitable base station antenna layout. Taking the 500 kV Guandu substation as an example, according to its actual internal space layout, four antenna layout installation schemes are obtained by using the algorithm in this paper, which can make the radio frequency field strength at all sensitive equipment in the station lower than the 10 V/m immunity limit, and at the same time. It can also increase the average signal of each monitoring equipment in the station by 3.77, 6.37, 4.34 and 4.58 dB respectively, and the variance of the monitoring equipment signal is reduced by 15.07%, 12.64%, 14.62% and 14.78% respectively. It can improve the signal strength at the monitoring equipment to a certain extent, and can also reduce the dispersion of the signals at the monitoring equipment in the station, so that the signal coverage at the monitoring equipment is more stable, which can be used for the actual project. 5G base station antenna layout in substations provide some reference.

Abstract:Aiming at the problems of phase error and reduced reconstruction accuracy caused by grating deformation caused by strong surface reflection in the process of structured light 3D reconstruction, a reconstruction method based on local grating completion is proposed. Firstly, the reflection factors that cause the missing phenomenon of the 3D reconstructed point cloud model, such as the material properties of the measured object and the angle of specular reflection, are analyzed. Secondly, before the phase unwrapping, the local grating complement method is introduced to complete the missing part of the grating in the reflective area, and the phase unwrapping accuracy is improved based on the phase shift method and the complementary Gray code reconstruction method. Finally, by building a monocular structured light 3D reconstruction system, the 3D reconstruction of the reflective rectangular aluminum alloy plate with a flatness error within 0.5 mm is carried out. Experiments show that the improved method proposed in this paper can effectively complement the reconstruction loss caused by the reflection on the surface of the object, and its phase decoding information is more complete. Compared with the traditional method, the reconstruction rate is increased by 25%, and the flatness error rate is reduced by 28.2%.

Abstract:Aiming at the problems of low efficiency and poor precision of visual track recognition in traditional UAV inspection, an algorithm for track detection based on LSD constrained cluster fitting and Kalman filter is proposed. Firstly, IPM algorithm was used to correct the Angle distortion caused by the lens Angle, and the track contour was detected by LSD algorithm. Under the constraint of track spacing, LSD results were clustered and the track lines were obtained by least square fitting. Then, a mathematical model is established according to the geometric characteristics of the orbit and the dynamics characteristics of UAV, and the track coordinate information is estimated by Kalman filter to ensure the stability and robustness of the algorithm. The trajectory images of multiple scenes collected by UAV are used as test samples, and the detection algorithm is compared with other algorithms. The experimental results show that the track recognition algorithm in this paper is better than other algorithms, and its track accuracy recognition rate reaches 92.49%, and the recognition rate reaches 23 frame/s, which meets the stability and real-time requirements of track detection.

Abstract:In view of the current metal surface defects classification, data is scarce and tagging process is cumbersome and expensive. This paper introduces the few-shot learning into the metal surface defect classification, proposes a few-shot learning network model with more informative detail descriptor to represent image features: Through adding spartial attention mechanism to screen local information and introducing the fusion measurement to class metric. Experiment results show that our model has better metric effect on MiniImageNet.We gains 6.34%, 5.78% and 1.25% improvements over RelationNet, CovaMNet and DN4 algorithms on the 5-way 5-shot task.The average accuracy of 5-way 5-shot on NEU-DET was improved by 2.87%, 3.34%, and 2.5% respectively.

Abstract:At present, the cable maintenance of power companies is completed manually. Manual maintenance not only has heavy workload and low efficiency, but also has serious secure issue. With the rapid development of machine vision and the wide application of robot technology in all walks of life, it has become an inevitable trend to apply these techniques to the automatic cable maintenance. This paper presents a method of binocular cable recognition and location based on the YOLACT model. Firstly, it uses the improved YOLACT network to recognize and segment dense cables in complex environments, then optimizes and extracts the edge of the cable segmentation image, and finally uses the obtained cable edge features to match the targets in the binocular image, so as to realize the recognition and location of cables in complex environments. Compared with the traditional YOLACT model, the correlation calculation method of cable candidate frame proposed in this paper can well solve the problems of missed detection and false detection when identifying dense cables, and improve the accuracy of cable identification.

Abstract:In order to accurately grade the nuclei of renal clear cell carcinoma in whole slide images and improve the treatment and prognosis of renal cancer, an International Society of Urological Pathology nuclear grading method based on CSFNet for ccRCC pathological images was proposed. In CSFNet, the semantic information of different stages was fused through multi-scale channel information splicing, thereby extracting more shallow features without losing depth information and subsequently achieving better classification performance. The renal histological sections of 90 patients were collected in the experiment. Afterwards, the WSI images were divided into training set and test set in a ratio of 4∶1 after being cut and enhanced. The CSFNet convolutional neural network model was then optimized iteratively on the training set and verified on the test set. The experimental results showed that the proposed CSFNet model achieved a macro-AUC of 0.975 8, a micro-AUC of 0.979 4, an accuracy of 88%, a precision of 88.36%, a recall of 86.67% and a F1-score of 87.32% for classifying ISUP Ⅰ, ISUP Ⅱ, ISUP Ⅲ and normal. Furthermore, our model was superior to other traditional classification network models, which proved that the proposed ISUP nuclear grading model for ccRCC had satisfied diagnostic effectiveness and potential clinical application value.

Abstract:For wind tunnel test characteristic such as vibration sensor and measurement system, the system introduces a calibration frequency range across the high frequency of low frequency can meet the demand of wind vibration characteristics and testing of the calibration device, the power of the moving parts, solve the optimal design, the air gap magnetic circuit optimization design, precision guide design, power amplifier design of gas film, shaking table control of key technical problems such as low frequency distortion, The evaluation results of device performance test and calibration uncertainty are far higher than the relevant technical requirements, which effectively improves the measurement support ability of wind tunnel vibration measurement.

Abstract:In order to optimize the extraction of pearl color features and improve the accuracy of pearl color detection, a shadow detection algorithm based on K-means clustering and local gradients is proposed. The results show that the algorithm can accurately detect the shadow of pearls in pearl images and eliminate the interference of shadows on the extraction of color features. In the Lab color space, a color feature extraction based on the area of pearl echo gallery effect is proposed, GA-SVM is used as the pearl color identification method, and a secondary color detection strategy is proposed to determine the pearl color category through two color detections. The comparison experimental results show that the accuracy rate of pearl body color detection is 100%, and the accuracy rate of pearl color detection is 98.7878%.

Abstract:There are many small targets in infrared images of substations with complex environment, resulting in low accuracy of existing detection algorithms. Therefore, this paper proposes an infrared image detection method for substation equipment based on improved Centernet. Firstly, taking Centernet as basic model, the FPN structure is introduced into the upsampling network to fully use the feature information of small targets, so as to solve the problem that small targets are difficult to be accurately detected; Then, in order to improve the detection robustness of the network in complex environment, an attention mechanism is embedded in the backbone network resnet50 to increase the attention of network to core targets; Finally, the training strategy of center point offset loss and width and height loss is replaced by CIOU loss to accelerate network convergence and improve training effect. The experimental results show that the method in this paper can have better detection effect in both small targets detection and complex environment detection, and the detection accuracy is improved by 3.1%, reaching 92.7%, which is more accurate than existing methods such as Faster R-CNN, and has certain reference value in infrared image detection of substation equipment.

Abstract:Current methods have limitations in detecting the uneven brightness and low contrast micro defects on the surface of the lithium battery electrode. To solve this problem, a algorithm based on the fusion of wavelet enhancement and the Canny operator was proposed. Firstly, the K-nearest mean filter algorithm was introduced to suppress the image background noise. Afterward, wavelet transform was implemented to separate the low-frequency and high-frequency components of the image. Subsequently, linear adjustment was adopted to process the low-frequency components, while the multi-scale detail enhancement method was used to process the high-frequency. Then PSO-OTSU adaptive algorithm was used to obtain the best threshold of the enhanced images. Finally, the Hough test was performed to connect the edge points. Through test defects such as leakage of metal, bright spots, scratches, holes each 700 images, the accuracy of quantitative analysis and comparison of 3 kinds of algorithm，experimental results show that compared with other algorithms, this algorithm had a detection accuracy of 97.85% and better performance in retaining the details of the defect edge, detecting low-contrast and micro defects, and extracting the defect contour.

Abstract:Aiming at the problems of low accuracy and poor effect of UAV intelligent power inspection caused by the complex background and dense small targets of power equipment, an improved target detection algorithm of YOLOv5. Firstly, a detection layer is added to the original model to re-obtain the anchor frame so as to better learn the multi-level features of dense small targets and improve the ability of the model to deal with complex power scenarios. Secondly, the feature fusion module PANet structure of the model is improved, and the features of different scales are fused by jumping connection to enhance the dissemination and reuse of information. Finally, combined with the collaborative attention module, the backbone network is designed to focus on the target characteristics and enhance the visibility of dense target areas in complex backgrounds. The experimental results show that the average accuracy of the proposed algorithm (IoU=0.5) reaches 97.1%, which is 5.6% higher than the original network detection performance, and effectively improves the false detection and missed detection of small targets in complex background.

Abstract:Road damage detection is an important basic link in the process of road maintenance. Traditional road damage detection methods have the defects of high detection cost and low efficiency. In order to accurately and quickly detect road damage, an improved road damage detection model YOLO-C-α based on YOLOv5 is proposed. By introducing the attention mechanism CBAM module, the feature extraction and feature fusion capabilities of the detection model are improved, and the problem of missed detection of small targets with road damage is improved; the α-IoU loss function is introduced to replace the CIOU loss function of the original network to reduce the regression loss of the prediction frame, to improve the positioning accuracy of the prediction box. Based on the RDD2020 road damage detection data set, a comparative experiment was carried out. The results showed that the average accuracy of the YOLO-C-α model reached 60.3%, which was 1.4% higher than the average accuracy of the original model. Its F1 value was 60.2, compared with the original model. It is improved by 1%, and has high detection performance for pavement damage under different weather conditions. The detection speed of each image in the experimental environment is 6.3 ms, and the model size is 40.6 Mb. The results show that the improved algorithm based on YOLOv5m has strong anti-interference ability and can more accurately detect road damage targets under various weather conditions, which can provide a reference for real-time road damage detection and intelligent road maintenance.

Abstract:To address the problem of low accuracy of tire laser scattergram recognition, this paper proposes a new classification network for tire laser scattergram (CA-ResNet50). Firstly, ResNet50-based residual network is selected to change the residual block structure in the traditional ResNet50 network model to maximize the role of batch normalization. Then, a lightweight convolutional attention module is introduced to enhance the feature extraction ability of the network model for tire defects. Next, LeakyRelu activation function is used instead of the Relu activation function to solve the neuronal deactivation problems.Finally, the training data set is extended to overcome the problems of insufficient data volume and overfitting of the network model in training. The CA-ResNet50 proposed in this paper is compared with the current commonly used classification network models on the same dataset, and the experimental results prove that the testing accuracy of the proposed network model in this paper is higher than other networks for tire laser scatter maps, and the recognition accuracy can reach 99.7%.

Abstract:In recent years, with the continuous development of resilient PNT and integrated PNT, the elastic fusion mechanism of multi-source sensors has attracted wide attention. Aiming at the problem that the measurement accuracy and reliability of visual sensors in multi-source integrated navigation are greatly affected by the environment, and the degree of influence on the accuracy is difficult to be evaluated independently. The evaluation factors of the pose calculation quality of monocular visual odometry were analyzed to reflect the measurement quality of visual sensors in multi-source sensor fusion system. A precision attenuation factor Visual-DOP based on the influence of the configuration of the reaction space point on the pose recovery accuracy of the camera was proposed. Further, the pose calculation quality evaluation algorithm of monocular visual odometry was designed, and it was verified on the visual odometry authoritative data set KITTI. The connection between each evaluation factor and the positioning accuracy was decoupled by the method of control variables. The results indicate that the pose calculation quality evaluation factors can correctly reflect the influence of visual measurement quality on the navigation accuracy of monocular visual odometer.

Abstract:The traditional CamShift only uses the color histogram of the target as the feature, so it may lead to inaccurate tracking or losing the target in the case of similar background, occlusion, high-speed motion and so on. In view of the above shortcomings, an improved CamShift tracking algorithm based on SIFT and perceptual hash is proposed. Firstly, transforming the image from RGB color space to HSV color space, then extracting the hue and saturation histograms and the edge gradient histogram of the image and combine the histograms to obtain the fusion histogram of the target. Secondly, using the fusion histogram of the target to obtain the optimal candidate target under the framework of CamShift algorithm. If the Bhattacharyya distance between the candidate target and the target template is larger than the threshold, using the improved perceptual hash algorithm to search the optimal candidate target. Then in the next frame search, using the SIFT algorithm to extract the feature points of the high information entropy part of both the target and video sequence, then matching the feature points to obtain the initial search window. If the SIFT algorithm fails to match, using the search box which is predicted by the Kalman filter as the initial search window to search the target. The algorithm is compared with other common tracking algorithms on OTB-100 dataset. The experimental results show that the algorithm can track the target accurately and the success rate reaches 90.1%. Then applying the algorithm to the task of face tracking and compared with other face tracking algorithms. The experimental results show that the algorithm has good performance and high accuracy, and the tracking success rate reaches 93.5%.

Abstract:Aiming at the shortcomings of common wind turbine blade fatigue loading methods, a new fatigue loading method based on motor-drum-traction rope drive is proposed, and single-axis and dual-axis loading control strategies are designed. Firstly, the dynamic analysis of the fatigue loading system based on the traction rope is carried out, and the feasibility of the half-wave simple harmonic periodic excitation force is illustrated. Secondly, the uniaxial loading control with dynamic update of the excitation force amplitude and excitation frequency is designed. Finally, the co-simulation analysis of Adams and MATLAB is used to verify the rationality of the dual-axis loading control strategy, which provides a basis for future research on the fatigue loading system based on traction rope.