2023, Volume 25, Issue 2
Strategic Study of CAE >> 2023, Volume 25, Issue 2 doi: 10.15302/J-SSCAE-2023.02.019
Prognostics and Health Management of High-Speed Trains in China: Progress and Prospect
1. CRRC Co., Ltd., Beijing 100039, China;
2. CRRC Zhuzhou Institute Co., Ltd., Zhuzhou 412001, Hunan, China
Received：2023-01-27 Revised：2023-03-23 Available online：2023-04-10Next Previous
Abstract
Higher requirements have been imposed for the safety and economical operation and maintenance (O&M) of high-speed trains as a result of increasing operating speed, number of train sets in service, and vehicle types as well as complex service conditions such as long routing and multi-physics coupling. The research and application of prognostics and health management (PHM) technology in the field of high-speed trains provides important technical support for the steady operation of China’s high-speed trains over long distance, on large scale, and in high density. This study presents the significance of PHM for high-speed trains and reviews the development process of high-speed train PHM in China, which has evolved from the initial safety monitoring to breakthroughs in health monitoring technologies of key systems and then the current integrated lifecycle O&M management in the past two decades. It further summarizes the major technical breakthroughs in four aspects, namely, comprehensive train condition monitoring, accurate assessment and diagnosis prediction, vehicle remote O&M services, and intelligent O&M decision support. In the face of the future challenges of efficient and safe O&M, substantial cost reduction, and consumption reduction of China’s high-speed trains, suggestions are proposed in the following aspects: wide-area and entire-process adaptability, centralized management and application of train data and computing resources, train design based on PHM, and train–line–station integrated intelligent O&M, so as to promote China’s high-speed train technology to maintain a lead.
Keywords
high-speed train ; prognostics and health management ; fault diagnosis and prediction ; intelligent operation and management ; train–line–station integration
Image
图1
图2
图3
图4
图5
图6
图7
图8
图9
图10
References
[1] Ezhilarasu C M, Skaf Z, K Jennions I. The application of reasoning to aerospace integrated vehicle health management(IVHM): Challenges and opportunities [J]. Progress in Aerospace Sciences, 2019; 105(2): 60‒73.
[2] 裴大茗 , 王建峰 , 周鹏太 , 等 . 船舶PHM技术综述 [J ]. 电子测量与仪器学报, 2016 , 30 9:1289‒1297.
[3] 王军 . 面向PHM的高速列车谱系化产品技术平台开发和实践 [J]. 中国铁道科学 , 2021 , 42 1 : 80 ‒ 86 .
[4] 黄学文 , 刘春明 , 冯璨 , 等 . CRH3高速动车组故障诊断系统 [J]. 计算机集成制造系统 , 2010 , 16 10 : 2311 ‒ 2318 .
[5] 王后闯 , 曾陆洋 , 郝国梁 , 等 . 铁路客车故障预测与健康管理PHM系统 [J]. 铁道机车车辆 , 2022 , 42 2 : 94 ‒ 98 .
[6] 刘彬 , 邵军 , 陆航 , 等 . 动车组故障预测与健康管理PHM体系架构研究思考 [J]. 中国铁路 , 2022 3 : 1 ‒ 9 .
[7] 王军 , 马云双 . 中国高速动车组发展模式探索与实践 [M]. 北京 : 中国铁道出版社 , 2020 .
[8] 申瑞源 . 机车车载安全防护系统6A系统总体方案研究 [J]. 中国铁路 , 2012 12 : 1 ‒ 6 .
[9] 刘峰 , 申宇燕 , 张瑞芳 , 等 . 机车车载安全防护系统应用研究 [J]. 铁路技术创新 , 2015 2 : 17 ‒ 21 .
[10] 张志波 , 张振先 , 冯永华 , 等 . 高速动车组转向架综合智能检测技术研究 [J]. 铁道车辆 , 2021 , 59 6 : 40 ‒ 44 .
[11] 高速铁路供电安全检测监测系统 6 C系统总体技术规范 [EBOL]. 2022-04-06 [ 2023-02-15 ]. http: www.nra.gov.cnjglzfgzdgfwjbmqtbm202204P020220406014464258880.pdf .
[12] 彭文静 . 车载远程数据传输设备在高速动车组上的应用 [J]. 铁道车辆 , 2013 , 51 10 : 29 ‒ 30 .
[13] 朱彦 , 尹振坤 , 张国芹 , 等 . 复兴号动车组智能技术创新应用及展望 [J]. 城市轨道交通研究 , 2022 , 25 2 : 1 ‒ 4 .
[14] 王同军 . 智能铁路总体架构与发展展望 [J]. 铁路计算机应用 , 2018 , 27 7 : 1 ‒ 8 .
[15] 王同军 . 中国铁路大数据应用顶层设计研究与实践 [J]. 中国铁路 , 2017 1 : 8 ‒ 16 .
[16] 常振臣 , 逯骁 , 张海峰 . 轨道交通车辆大数据管理平台建设与实施 [J]. 城市轨道交通研究 , 2019 , 22 2 : 1 ‒ 4 .
[17] 秦勇 , 马慧 , 贾利民 . 先进轨道交通系统发展趋势与主动安全保障技术 [J]. 中国铁路 , 2015 12 : 77 ‒ 81 .
[18] Milojevic A, Tomic M, T Pavlović N. Application of FBG sensors in smart railway [C]. Niš: XV International Scientific-expert Conference on Railways, 2012.
[19] Ju Z Y, Wang Z Z, Ma L. The damage diagnostic techniques and experimental research of high-speed EMU aluminum car-body bolster based on lamb guided waves [EB/OL]. (2018-01-15)[2023-02-15]. https: //www.dpi-proceedings.com/index.php/shm2017. link1
[20] Cerrone C, Cerulli C, Golden B. Carousel greedy: A generalized greedy algorithm with applications in optimization [J]. Computers & Operations Research, 2017, 85(9): 97‒112.
[21] Ren M Y, Triantafillou E, Ravi S, al et. Meta-learning for semi-supervised few-shot classification [EB/OL]. (2018-03-02)[2023-02-15]. https: //arxiv.org/abs/1803.00676. link1
[22] Zhou Z H. A brief introduction to weakly supervised learning [J]. National Science Review, 2018, 5(1): 44‒53.
[23] Zhang Z, Saligrama V. Zero-shot learning semantic similarity embedding [C]. Washington DC: 2015 Proceedings of the IEEE International Conference on Computer Vision, 2015.
[24] Ren S Q, He K M, Girshick R, al et. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137‒1149.
[25] 彭云聪 , 秦小林 , 张力戈 , 等 . 面向图像分类的小样本学习算法综述 [J]. 计算机科学 , 2022 , 49 5 : 1 ‒ 9 .
[26] van Dyk D A, Meng X L. The art of data augmentation [J]. Journal of Computational and Graphical Statistics, 2001, 10(1): 1‒50.
[27] Song C, Zhao J J, Wang K, al et. A survey of few shot learning based on intelligent perception [J]. Acta Aeronautica et Astronautica Sinica, 2020, 41 (S1): 723756.
[28] Zhao G, Gao H D, Zhang G F, al et. Active health monitoring of an aircraft wing with embedded piezoelectric sensor/actuator network: I. Defect detection, localization and growth monitoring [J]. Smart Materials and Structures, 2007, 16(4): 1208‒1217.
[29] 郑跃滨 , 武湛君 , 雷振坤 , 等 . 基于超声导波的航空航天结构损伤诊断成像技术研究进展 [J]. 航空制造技术 , 2020 , 63 18 : 24 ‒ 43 .
[30] Li Z H, Cheng Y Y, Zhang L, al et. Strain field reconstruction of high-speed train crossbeam based on FBG sensing network and load-strain linear superposition algorithm [J]. IEEE Sensors Journal, 2022, 22(4): 3228‒3235.
[31] Cheng Y Y, Li Z H, Wang G J, al et. Strain field reconstruction of crossbeam structure based on load-strain linear superposition method [J]. Smart Materials & Structures, 2021, 30(7): 1‒12.
[32] Feng Z P, Zuo M J, Hao R J, al et. Ensemble empirical mode decomposition-based teager energy spectrum for bearig fault diagnosis [J]. Journal of Vibration and Acoustics, 2013, 135(3): 031013.
[33] 于萍 , 金炜东 , 秦娜 . 基于EEMD 降噪和流形学习的高速列车走行部故障特征提取 [J]. 铁道学报 , 2016 , 38 4 : 16 ‒ 21 .
[34] 贺德强 , 陈二恒 , 李笑梅 , 等 . 基于RS-LSSVM 的高速列车走行部滚动轴承故障诊断研究 [J]. 广西大学学报自然科学版 , 2017 , 42 2 : 403 ‒ 408 .
[35] 梁建英 , 邓学寿 , 刘韶庆 , 等 . 基于大数据技术的动车组数字化智能运维平台 [R]. 青岛 : 中车青岛四方机车车辆股份有限公司 , 2020 .
京公网安备 11010502051620号
