面向工业环境气体泄漏检测的多模态融合模型*
作者单位:

1.昆明理工大学;2.中国铜业有限公司;3.昆明信息港传媒有限责任公司

中图分类号:

TP274

基金项目:

云南省重大科技专项计划项目(No. 202202AD080006)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [24]
  • | | | |
  • 文章评论
    摘要:

    目前工业气体泄漏检测的方法主要使用单一模态的数据,忽略了不同模态数据之间的互补性。由于单一模态数据刻画复杂环境能力的局限性,影响了检测的准确性和鲁棒性?针对上述问题,本文提出了一种融合工业多模态数据的气体泄漏检测模型 (MFT)?为了充分挖掘不同模态数据之间的信息,依据不同数据的特性,引入了两种特征编码器,有效地提取各模态数据的特征;此外,为了充分融合多模态数据,采用了基于多头注意力机制的融合策略,有效融合不同模态数据之间的潜在表示?实验结果表明,本文所提出的方法可以充分利用各模态的之间的互补信息,并在公开的 MultimodalGasData 数据集上取得了 98.05% 准确率,提高气体泄漏检测的准确性和鲁棒性?

    Abstract:

    Industrial gas leak detection remains a critical challenge, with existing methods predominantly relying on single-modality data. This reliance neglects the complementary nature of different modalities and limits the ability to accurately and robustly detect leaks in complex environments. To address these limitations, this study proposes a novel gas leak detection model, the Multimodal Fusion Transformer (MFT), which integrates data from multiple industrial modalities. The MFT model employs two distinct feature encoders to effectively extract features from each modality, tailored to their unique characteristics. To fully leverage the potential of multimodal data, a multi-head attention mechanism is utilized to fuse the latent representations of different modalities. This approach ensures that the complementary information from each modality is effectively combined. Experimental results demonstrate that the proposed method significantly improves the accuracy and robustness of gas leak detection. The MFT model achieves an impressive 98.05% accuracy on the publicly available MultimodalGasData dataset, highlighting its efficacy in utilizing the complementary information across various modalities. This advancement marks a substantial step forward in enhancing the reliability and performance of industrial gas leak detection systems.

    参考文献
    [1] BOAZ L, KAIJAGE S, SINDE R. An overview of pipeline leak detection and location systems [C]. Proceedings of the 2nd Pan African International Conference on Science, Computing and Telecommunications (PACT 2014) IEEE, 2014: 133-137.
    [2] JIN H, ZHANG L, LIANG W, et al. Integrated leakage detection and localization model for gas pipelines based on the acoustic wave method [J]. Journal of Loss Prevention in the Process Industries, 2014, 27: 74-88.
    [3] 张永娟, 纪春华, 葛楠, 等. 基于数据融合的流量式泄漏检测温度补偿方法研究 [J]. 液压与气动, 2010, (10): 52-55.
    [4] DOSHMANZIARI R, KHALOOZADEH H, NIKOOFARD A. Gas pipeline leakage detection based on sensor fusion under model-based fault detection framework [J]. Journal of Petroleum Science and Engineering, 2020, 184: 106581.
    [5] ABDULSHAHEED A, MUSTAPHA F, GHAVAMIAN A. A pressure-based method for monitoring leaks in a pipe distribution system: A Review [J]. Renewable and Sustainable Energy Reviews, 2017, 69: 902-911.
    [6] KOPBAYEV A, KHAN F, YANG M, et al. Gas leakage detection using spatial and temporal neural network model [J]. Process Safety and Environmental Protection, 2022, 160: 968-975.
    [7] 杨嘉嘉, 路晶. 基于物联网的智能化工厂可燃气体监测系统 [J]. 物联网技术, 2023, 13(03): 3-5.
    [8] SALAMEH H A B, DHAINAT M F, BENKHELIFA E. An end-to-end early warning system based on wireless sensor network for gas leakage detection in industrial facilities [J]. IEEE Systems Journal, 2020, 15(4): 5135-5143.
    [9] ELMENREICH W. A review on system architectures for sensor fusion applications [C]. IFIP International Workshop on Software Technologies for Embedded and Ubiquitous Systems. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007: 547-559.
    [10] 李泉成, 曹江涛, 姬晓飞. 光流增强的红外成像气体泄漏检测方法 [J]. 电子测量与仪器学报, 2023, 37(03): 50-56.
    [11] 彭敏, 马宁, 王少军, 等. 基于可见光图像的工业过程气体泄漏检测研究 [J]. 电子测量与仪器学报, 2019, 33(06): 1-8.
    [12] 唐璟, 罗秀丽, 刘绍华, 等. 石油和天然气红外成像检漏 [J]. 激光与红外, 2016, 46(01): 62-66.
    [13] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]. Advances in neural information processing systems, 2017: 5998-6008.
    [14] 唐永旺, 刘会景, 靳彦青, 等. 基于Transformer的时序多模态融合特征的异常网络流量检测方法 [J]. 信息工程大学学报, 2023, 24(04): 468-474.
    [15] ZHANG Y, XIE F, CHEN J. TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis [J]. Computers in Biology and Medicine, 2023, 157: 106712.
    [16] LIU Z, LIN Y, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows [C]. Proceedings of the IEEE/CVF international conference on computer vision, 2021: 10012-10022.
    [17] LIU H, DAI Z, SO D, et al. Pay attention to mlps [C]. Advances in neural information processing systems, 2021, 34: 9204-9215.
    [18] LOSHCHILOV I, HUTTER F. Decoupled weight decay regularization [J]. arxiv preprint arxiv:1711.05101, 2017.
    [19] NARKHEDE P, WALAMBE R, CHANDEL P, et al. MultimodalGasData: Multimodal dataset for gas detection and classification [J]. Data, 2022, 7(8): 112.
    [20] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
    [21] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016: 770-778.
    [22] HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications [J]. arxiv preprint arxiv:1704.04861, 2017.
    [23] ELMAN J L. Finding structure in time [J]. Cognitive science, 1990, 14(2): 179-211.
    [24] HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural computation, 1997, 9(8): 1735-1780.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文
分享
文章指标
  • 点击次数:4
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-07-27
  • 最后修改日期:2024-12-31
  • 录用日期:2025-01-07
文章二维码