|
|
基于深度学习的钢轨病害检测算法研究
|
Abstract:
钢轨病害的存在严重威胁行车安全，因此，对钢轨病害进行有效检测对提升车辆运行的安全性具有至关重要的意义。本文旨在综述基于深度学习的钢轨病害检测算法。首先，对基于深度学习的钢轨病害检测网络进行了全面介绍；其次，根据数据的采集模态，将钢轨病害检测方法划分为两类：基于单一模态数据(轮轨加速度信号、图像、结构光点云)的典型算法以及基于多模态数据融合的算法；最后，对未来钢轨病害检测技术进行了综述和展望。
The presence of rail diseases poses a significant threat to driving safety, underscoring the critical importance of effective rail disease detection to enhance vehicle operational safety. This article endeavors to review algorithms for rail disease detection utilizing deep learning methodologies. Initially, a thorough introduction is provided for the rail disease detection network based on deep learning. Subsequently, rail disease detection methods are categorized into two groups based on the data collection mode: Those reliant on single-modal data (such as wheel-rail acceleration signals, images, and structured light point clouds) and algorithms founded on multi-modal data fusion. Lastly, a comprehensive review and forward-looking insights into future rail disease detection technologies are presented.
| [1] | 王建柱, 李清勇, 张靖, 等. 轨道病害视觉检测: 背景、方法与趋势[J]. 中国图象图形学报, 2021, 26(2): 287-296. |
| [2] | Faghih-Roohi, S., Hajizadeh, S., Nú？ez, A., Babuska, R. and De Schutter, B. (2016) Deep Convolutional Neural Networks for Detection of Rail Surface Defects. Proceedings of 2016 International Joint Conference on Neural Networks, 24-29 July 2016, 2584-2589. |
| [3] | Dong, B.Y., Li, Q.Y., Wang, J.Z., Huang, W., Dai, P. and Wang, S.C. (2019) An End-to-End Abnormal Fastener Detection Method Based on Data Synthesis. Proceedings of the 31st IEEE International Conference on Tools with Artificial Intelligence, 4-6 November 2019, 149-156. |
| [4] | Dou, Y., Huang, Y., Li, Q. and Luo, S. (2014) A Fast Template Matching-Based Algorithm for Railway Bolts Detection. International Journal of Machine Learning and Cybernetics, 5, 835-844.
https://doi.org/10.1007/s13042-013-0223-z |
| [5] | 孙秀秀. 基于深度学习的高铁钢轨波磨检测的研究[D]: [硕士学位论文]. 北京: 北京建筑大学, 2020.
https://doi.org/10.26943/d.cnki.gbjzc.2020.000003 |
| [6] | He, K.M., Zhang, X.Y., Ren, S.Q. and Sun, J. (2014) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 37, 1904-1916.
https://doi.org/10.1109/TPAMI.2015.2389824 |
| [7] | Liang, P., Deng, C., Wu, J. and Yang, Z.X. (2020) Intelligent Fault Diagnosis of Rotating Machinery Via Wavelet Transform, Generative Adversarial Nets, and Convolutional Neural Networks. Measurement, 159, Article ID: 107768.
https://doi.org/10.1016/j.measurement.2020.107768 |
| [8] | 谢清林, 陶功权, 温泽峰. 基于一维卷积神经网络的地铁钢轨波磨识别方法[J]. 中南大学学报(自然科学版), 2021, 52(4): 1371-1379. |
| [9] | 谢烨, 赵闻强, 杨红运, 等. 基于一维深度卷积生成对抗网络的钢轨波磨识别方法[J]. 铁道建筑, 2022, 62(12): 62-66, 71. |
| [10] | Xie, Q.L., Tao, G.Q., Lo, S.M., et al. (2023) A Data-Driven Convolutional Regression Scheme for On-Board and Quantitative Detection of Rail Corrugation Roughness. Wear, 524-525, Article ID: 204770.
https://doi.org/10.1016/j.wear.2023.204770 |
| [11] | 李倩. 基于深度信念网络的图像识别及其应用研究[D]: [硕士学位论文]. 北京: 华北电力大学, 2016. |
| [12] | Krizhevsky, A., Sutskever, I. and Hinton, E.G. (2017) ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. https://doi.org/10.1145/3065386 |
| [13] | 王兵水, 郑树彬, 李立明, 等. 基于YOLO改进算法的轨道扣件状态检测研究[J]. 智能计算机与应用, 2020, 10(1): 137-143. |
| [14] | Li, W., Shen, Z. and Li, P. (2019) Crack Detection of Track Plate Based on YOLO. 2019 12th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, 14-15 December 2019, 15-18.
https://doi.org/10.1109/ISCID.2019.10086 |
| [15] | Girshick, R. (2015) Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Santiago, 7-13 December 2015, 1440-1448. https://doi.org/10.1109/ICCV.2015.169 |
| [16] | Ren, S., He, K., Girshick, R. and Sun, J. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. |
| [17] | 魏秀琨, 魏德华, 贾利民, 等. 基于改进YOLOv3网络模型的轨道线路病害辨识方法[P]. 中国专利, CN110533640B. 2022-03-01. |
| [18] | Mi, Z.Z., Chen, R. and Zhao, S.S. (2023) Research on Steel Rail Surface Defects Detection Based on Improved YOLOv4 Network. Frontiers in Neurorobotics, 17, Article 1119896. https://doi.org/10.3389/fnbot.2023.1119896 |
| [19] | Zhang, C., Xu, D., Zhang, L., et al. (2023) Rail Surface Defect Detection Based on Image Enhancement and Improved YOLOX. Electronics, 12, Article 2672. https://doi.org/10.3390/electronics12122672 |
| [20] | Luo, H., Cai, L. and Li, C. (2023) Rail Surface Defect Detection Based on an Improved YOLOv5s. Applied Sciences, 13, Article 7330. https://doi.org/10.3390/app13127330 |
| [21] | Jin, X.T., Wang, Y.N., Zhang, H., Zhong, H., Liu, L., Wu, Q.M.J. and Yang, Y.M. (2020) DM-RIS: Deep Multimodel Rail Inspection System with Improved MRF-GMM and CNN. IEEE Transactions on Instrumentation and Measurement, 69, 1051-1065. https://doi.org/10.1109/TIM.2019.2909940 |
| [22] | Wang, H., Li, M. and Wan, Z. (2022) Rail Surface Defect Detection Based on Improved Mask R-CNN. Computers and Electrical Engineering, 102, Article ID: 108269. https://doi.org/10.1016/j.compeleceng.2022.108269 |
| [23] | Yang, H.J., Liu, J.X., Mei, G.M., et al. (2023) Research on Real-Time Detection Method of Rail Corrugation Based on Improved ShuffleNet V2. Engineering Applications of Artificial Intelligence, 126, Article ID: 106825.
https://doi.org/10.1016/j.engappai.2023.106825 |
| [24] | 董艳茹. 基于多线结构光视觉的钢轨波磨检测[D]: [硕士学位论文]. 长沙: 湖南大学, 2019.
https://doi.org/10.27135/d.cnki.ghudu.2019.002552 |
| [25] | 李文虎. 基于双目视觉的钢轨波磨测量方法及其应用[D]: [硕士学位论文]. 武汉: 武汉理工大学, 2019.
https://doi.org/10.27381/d.cnki.gwlgu.2019.000124 |
| [26] | 崔文凯. 基于虚实结合的钢轨表面缺陷检测研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2022.
https://doi.org/10.26944/d.cnki.gbfju.2022.001335 |
| [27] | Chen, Z., Wang, Q., He, Q., et al. (2022) CUFuse: Camera and Ultrasound Data Fusion for Rail Defect Detection. IEEE Transactions on Intelligent Transportation Systems, 23, 21971-21983.
https://doi.org/10.1109/TITS.2022.3189677 |
| [28] | Yang, T., Xu, T., Cheng, Y., et al. (2023) A Fusion Method Based on 1D Vibration Signals and 2D Images for Detection of Railway Surface Defects. 2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE), Guangzhou, 24-26 February 2023, 282-286.
https://doi.org/10.1109/NNICE58320.2023.10105728 |
