Volume 32 Issue 5
Sep.  2023
Turn off MathJax
Article Contents
ZHANG Changfan, HUANG Congcong, HE Jing, “Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 941-954, 2023, doi: 10.23919/cje.2022.00.162
Citation: ZHANG Changfan, HUANG Congcong, HE Jing, “Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 941-954, 2023, doi: 10.23919/cje.2022.00.162

Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network

doi: 10.23919/cje.2022.00.162
Funds:  This work was supported by the National Natural Science Foundation of China (52172403, 62173137), the Hunan Provincial Natural Science Foundation of China (2021JJ50001), and the Project of Hunan Provincial Department of Education (19A137, 18A267)
More Information
  • Author Bio:

    Changfan ZHANG received the M.S. degree in Southwest Jiaotong University in 1989 and Ph.D. degree from Hunan University in 2001, respectively. Now he is a Professor at Hunan University of Technology. His main research interests include nonlinear control and application. (Email: zcf@hut.edu.cn)

    Congcong HUANG received the B.E. degree in Hunan University of Technology in 2019. Now she is an M.S. candidate at Hunan University of Technology. Her main research interests include Intelligent detection and control. (Email: 1393117258@qq.com)

    Jing HE (corresponding author) received the M.S. degree in Central South University of Forestry and Technology in 2002 and Ph.D. degree from National University of Defense Technology in 2009, respectively. Now she is a Professor at Hunan University of Technology. Her main research interests include electro-mechanical system fault diagnosis.(Email: hejing@hut.edu.cn)

  • Received Date: 2022-06-06
  • Accepted Date: 2022-08-10
  • Available Online: 2022-10-20
  • Publish Date: 2023-09-05
  • Surface defect recognition of train wheelset is crucial for the safe operation of the train wheel system. However, due to the diversity and complexity of such defects, it is difficult for existing algorithms to make rapid and accurate recognitions. To solve this problem, an improved spiking neural network (SNN) based defect recognition method for train wheelset tread is proposed. Specifically, a hybrid convolutional encoding module is first designed to conduct image-to-spike conversion and to create multi-scale sparse representations of the features. Second, a residual spiking convolutional neural network is implemented to extract spiking features optimally, and a multi-scale structure is adopted to enhance the SNN’s ability to handle details. A channel attention module is then incorporated to re-calibrate the weights of four-dimensional spiking feature maps. Finally, effective spiking features are obtained according to the recognition decisions which are made. The experimental results showed that the proposed method improved the accuracy of defect recognition. The recognition time of a single image is only 0.0195 s on average. The overall performance of the proposed method is noticeably superior to current mainstream algorithms.
  • loading
  • [1]
    Y. Cao, Y. K. Sun, G. Xie, et al., “Fault diagnosis of train plug door based on a hybrid criterion for IMFs selection and fractional wavelet package energy entropy,” IEEE Transactions on Vehicular Technology, vol.68, no.8, pp.7544–7551, 2019. doi: 10.1109/TVT.2019.2925903
    L. Jing and K. Liu, “Review on wheel-rail dynamic responses caused by wheel tread defects,” Journal of Traffic and Transportation Engineering, vol.21, no.1, pp.285–315, 2021. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2021.01.014
    J. He, H. Y. Yu, C. F. Zhang, et al., “Damage detection of train wheelset tread using Canny-YOLOv3,” Journal of Electronic Measurement and Instrumentation, vol.33, no.12, pp.25–30, 2019. (in Chinese) doi: 10.13382/j.jemi.B1902543
    Y. Cao, Y. K. Sun, G. Xie, et al., “A sound-based fault diagnosis method for railway point machines based on two-stage feature selection strategy and ensemble classifier,” IEEE Transactions on Intelligent Transportation Systems, vol.23, no.8, pp.12074–12083, 2022. doi: 10.1109/TITS.2021.3109632
    Y. K. Sun, Y. Cao, and P. Li, “Fault diagnosis for train plug door using weighted fractional wavelet packet decomposition energy entropy,” Accident Analysis & Prevention, vol.166, article no.106549, 2022. doi: 10.1016/j.aap.2021.106549
    E. L. Liu, C. G. Liu, X. J. Jiang, et al., “Cluster analysis of wheel tread defects based on gray-gradient cooccurrence matrix,” Journal of Optoelectronics Laser, vol.33, no.1, pp.53–60, 2022. (in Chinese) doi: 10.16136/j.joel.2022.01.0291
    U. Batool, M. I. Shapiai, M. Tahir, et al., “A systematic review of deep learning for silicon wafer defect recognition,” IEEE Access, vol.9, pp.116572–116593, 2021. doi: 10.1109/ACCESS.2021.3106171
    A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,,” Advances in neural information processing systems, vol.25, no.2, pp.1097–1105, 2012. doi: 10.1145/3065386
    S. B. Li, J. Yang, Z. Wang, et al., “Review of development and application of defect detection technology,” Acta Automatica Sinica, vol.46, no.11, pp.2319–2336, 2020. (in Chinese) doi: 10.16383/j.aas.c180538
    P. M. Bhatt, R. K. Malhan, P. Rajendran, et al., “Image-based surface defect detection using deep learning: a review,” Journal of Computing and Information Science in Engineering, vol.21, no.4, article no.040801, 2021. doi: 10.1115/1.4049535
    X. Tao, W. Hou, and D. Xu, “A survey of surface defect detection methods based on deep learning,” Acta Automatica Sinica, vol.47, no.5, pp.1017–1034, 2021. (in Chinese) doi: 10.16383/j.aas.c190811
    C. F. Hu and Y. X. Wang, “An efficient convolutional neural network model based on object-level attention mechanism for casting defect detection on radiography images,” IEEE Transactions on Industrial Electronics, vol.67, no.12, pp.10922–10930, 2020. doi: 10.1109/TIE.2019.2962437
    Z. Huang, J. J. Wu, and F. Xie, “Automatic recognition of surface defects for hot-rolled steel strip based on deep attention residual convolutional neural network,” Materials Letters, vol.293, article no.129707, 2021. doi: 10.1016/J.MATLET.2021.129707
    Z. Y. Chen, H. Zhao, Y. S. Lyu, et al., “Recognition method of coating surface defects based on the improved MobileNetV2 network,” Journal of Harbin Engineering University, vol.43, no.4, pp.572–579, 2022. (in Chinese) doi: 10.11990/jheu.202103061
    I. Konovalenko, P. Maruschak, J. Brezinová, et al., “Steel surface defect classification using deep residual neural network,” Metals, vol.10, no.6, article no.846, 2020. doi: 10.3390/met10060846
    R. Miao, Z. T. Shan, Q. Y. Zhou, et al., “Real-time defect identification of narrow overlap welds and application based on convolutional neural networks,” Journal of Manufacturing Systems, vol.62, pp.800–810, 2022. doi: 10.1016/j.jmsy.2021.01.012
    R. Jolivet, T. J. Lewis, and W. Gerstner, “Generalized integrate-and-fire models of neuronal activity approximate spike trains of a detailed model to a high degree of accuracy,” Journal of Neurophysiology, vol.92, no.2, pp.959–976, 2004. doi: 10.1152/jn.00190.2004
    Y. F. Hu, G. Q. Li, Y. J. Wu, et al., “Spiking neural networks: a survey on recent advances and new directions,” Control and Decision, vol.36, no.1, pp.1–26, 2021. (in Chinese) doi: 10.13195/j.kzyjc.2020.1006
    P. Panda and K. Roy, “Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition,” in Proceedings of 2016 International Joint Conference on Neural Networks, Vancouver, Canada, pp.299–306, 2016.
    S. R. Kulkarni and B. Rajendran, “Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization,” Neural Networks, vol.103, pp.118–127, 2018. doi: 10.1016/j.neunet.2018.03.019
    Y. J. Wu, L. Deng, G. Q. Li, et al., “Direct training for spiking neural networks: faster, larger, better,” in Proceedings of the 33rd AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, pp.1311–1318, 2019.
    M. Mozafari, S. R. Kheradpisheh, T. Masquelier, et al., “First-spike-based visual categorization using reward-modulated STDP,” IEEE Transactions on Neural Networks and Learning Systems, vol.29, no.12, pp.6178–6190, 2018. doi: 10.1109/TNNLS.2018.2826721
    S. Kim, S. Park, B. Na, et al., “Spiking-YOLO: spiking neural network for energy-efficient object detection,” in Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, NY, USA, pp.11270–11277, 2020.
    Z. Y. Zhang, W. H. Cao, R. Zhu, et al., “Sparse representation with spike convolutional neural networks for scene classification of remote sensing images of high resolution,” Control and Decision, vol.37, no.9, pp.2305–2313, 2022. (in Chinese) doi: 10.13195/j.kzyjc.2021.0279
    L. Zuo, L. Zhang, Z. H. Zhang, et al., “A spiking neural network-based approach to bearing fault diagnosis,” Journal of Manufacturing Systems, vol.61, pp.714–724, 2021. doi: 10.1016/j.jmsy.2020.07.003
    J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.7132–7141, 2018.
    A. Destexhe, “Conductance-based integrate-and-fire models,” Neural Computation, vol.9, no.3, pp.503–514, 1997. doi: 10.1162/neco.1997.9.3.503
    M. Y. Meng, X. Y. Yang, S. L. Xiao, et al., “Spiking inception module for multi-layer unsupervised spiking neural networks,” in Proceedings of 2020 International Joint Conference on Neural Networks, Glasgow, UK, pp.1–8, 2020.
    K. M. He, X. Y. Zhang, S. Q. Ren, et al., “Deep residual learning for image recognition,” Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp.770–778, 2016.
    Y. J. Wu, L. Deng, G. Q. Li, et al., “Spatio-temporal backpropagation for training high-performance spiking neural networks,” Frontiers in Neuroscience, vol.12, article no.articleno.331, 2018. doi: 10.3389/fnins.2018.00331
    S. Daryanavard and B. Porr, “Closed-loop deep learning: Generating forward models with backpropagation,” Neural Computation, vol.32, no.11, pp.2122–2144, 2020. doi: 10.1162/neco_a_01317
    W. Fang, Z. F. Yu, Y. Q. Chen, et al., “Incorporating learnable membrane time constant to enhance learning of spiking neural networks,” in Proceedings of 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Canada, pp.2661–2671, 2021.
    E. O. Neftci, H. Mostafa, and F. Zenke, “Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks,” IEEE Signal Processing Magazine, vol.36, no.6, pp.51–63, 2019. doi: 10.1109/MSP.2019.2931595
    F. Zenke and S. Ganguli, “SuperSpike: supervised learning in multilayer spiking neural networks,” Neural Computation, vol.30, no.6, pp.1514–1541, 2018. doi: 10.1162/neco_a_01086
    B. J. Yin, F. Corradi, and S. M. Bohté, “Effective and efficient computation with multiple-timescale spiking recurrent neural networks,” in Proceedings of the International Conference on Neuromorphic Systems, Oak Ridge, USA, article no.1, 2020.
    K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA, 2015.
    G. Huang, Z. Liu, L. Van Der Maaten, et al., “Densely connected convolutional networks,” in Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp.4700–4708, 2017.
    C. Szegedy, W. Liu, Y. Q. Jia, et al., “Going deeper with convolutions,” in Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp.1–9, 2015.
    D. H. Ge, H. S. Li, L. Zhang, et al., “Survey of lightweight neural network,” Journal of Software, vol.31, no.9, pp.2627–2653, 2020. (in Chinese) doi: 10.13328/j.cnki.jos.005942
    M. Sandler, A. Howard, M. L. Zhu, et al., “MobileNetV2: inverted residuals and linear bottlenecks,” in Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.4510–4520, 2018.
    X. Y. Zhang, X. Y. Zhou, M. X. Lin, et al., “ShuffleNet: an extremely efficient convolutional neural network for mobile devices,” in Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.6848–6856, 2018.
    M. X. Tan and Q. Le, “EfficientNet: rethinking model scaling for convolutional neural networks,” in Proceedings of 36th International Conference on Machine Learning, Long Beach, CA, USA, pp.6105–6114, 2019.
    S. R. Kheradpisheh, M. Ganjtabesh, S. J. Thorpe, et al., “STDP-based spiking deep convolutional neural networks for object recognition,” Neural Networks, vol.99, pp.56–67, 2018. doi: 10.1016/j.neunet.2017.12.005
    C. Zhang and F. Z. Tang, “Self-adaptive coding for spiking neural network,” Application Research of Computers, vol.39, no.2, pp.593–597, 2022. (in Chinese) doi: 10.19734/j.issn.1001-3695.2021.06.0239
    H. Zhang, K. K. Zu, J. Lu, et al., “EPSANet: an efficient pyramid squeeze attention block on convolutional neural network,” in Proceedings of the 16th Asian Conference on Computer Vision, Macao, China, pp.541–557, 2021.
    Q. L. Wang, B. G. Wu, P. F. Zhu, et al., “ECA-Net: efficient channel attention for deep convolutional neural networks,” in Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, pp.11531–11538, 2020.
    J. Park, S. Woo, J. Y. Lee, et al., “BAM: Bottleneck attention module,” in Proceedings of the British Machine Vision Conference 2018, Newcastle, UK, 2018.
    S. Woo, J. Park, J. Y. Lee, et al., “CBAM: convolutional block attention module,” in Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp.3–19, 2018.
    J. X. Liu and G. P. Zhao, “A bio-inspired SOSNN model for object recognition,” in Proceedings of 2018 International Joint Conference on Neural Networks, Rio de Janeiro, Brazil, pp.1–8, 2018.
    K. C. Song and Y. H. Yan, “A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects,” Applied Surface Science, vol.285, pp.858–864, 2013. doi: 10.1016/j.apsusc.2013.09.002
    M. W. Ashour, F. Khalid, A. H. Abdul, et al., “Surface defects classification of hot-rolled steel strips using multi-directional shearlet features,” Arabian Journal for Science and Engineering, vol.44, no.4, pp.2925–2932, 2019. doi: 10.1007/s13369-018-3329-5
    S. F. Li, C. X. Wu, and N. X. Xiong, “Hybrid architecture based on CNN and Transformer for strip steel surface defect classification,” Electronics, vol.11, no.8, article no.articleno.1200, 2022. doi: 10.3390/electronics11081200
    J. Chang, S. Q. Guan, and H. Y. Shi, “Strip defect classification based on improved generative adversarial networks and MobileNetV3,” Laser & Optoelectronics Progress, vol.58, no.4, article no.0410016, 2021. doi: 10.3788/LOP202158.0410016
    Y. P. Gao, L. Gao, X. Y. Li, et al., “A semi-supervised convolutional neural network-based method for steel surface defect recognition,” Robotics and Computer-Integrated Manufacturing, vol.61, article no.101825, 2020. doi: 10.1016/j.rcim.2019.101825
    X. Wan, X. Y. Zhang, and L. L. Liu, “An improved VGG19 transfer learning strip steel surface defect recognition deep neural network based on few samples and imbalanced datasets,” Applied Sciences, vol.11, no.6, article no.2606, 2021. doi: 10.3390/app11062606
  • 加载中


    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(11)  / Tables(10)

    Article Metrics

    Article views (751) PDF downloads(119) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint