Fault-tolerant control for levitation systems of high-speed maglev train based on diversified basis neural networks
Article Text (Baidu Translation)
-
摘要: 针对高速磁浮车辆长期服役下的系统参数摄动，执行器故障和左、右电磁铁耦合问题的综合影响，分析了磁浮车辆悬浮系统搭接结构在通过车体连接过程中所出现的左、右电磁铁的相互耦合关系和执行器故障，并提出了一种基于多元基函数的神经网络自适应容错悬浮控制方法；将多元基函数引入到神经网络中，并针对控制过程中的复杂和不连续问题，引入了神经网络的上范数界处理的方法；通过基于Lyapunov函数证明所提方法对故障的容错性和对不确定系统动态的鲁棒性，在此基础上证明了控制方法的最终一致有界性。试验结果表明：在电磁铁发生部分失效的情况下，自适应变量能根据故障情况发生变化并影响控制电流，进而实现容错性能；分别跟踪平稳信号时，左、右电磁铁的最大跟踪误差分别为0.2、0.1 mm，平均误差分别为0.14、0.09 mm；分别跟踪正弦信号时，左、右电磁铁的最大跟踪误差分别为0.2、0.1 mm，平均误差分别为0.18、0.10 mm；分别跟踪方波信号时，左、右电磁铁的最大跟踪误差均为1.1 mm，平均误差分别为0.18、0.14 mm。所提方法在左、右电磁铁上均能够适应故障问题，快速跟踪期望信号，满足磁浮车辆在运行中的可靠性与安全性。Abstract: To address the effects of system parameter perturbations, actuator faults, and left and right electromagnet coupling in high-speed maglev vehicles during long-term service, the mutual coupling relationship between left and right electromagnets and the actuator faults in the joint-structure of the maglev vehicle suspension system during the process of connecting the vehicle bodies were analyzed. A neural network method for adaptive fault-tolerant suspension control based on diversified basis functions was proposed. Diversified basis functions were introduced into neural networks, and an upper norm boundary processing method for neural networks was incorporated to address complex and discontinuous issues in the control process. Through Lyapunov functions, the fault tolerance of the proposed method against failures and its robustness to uncertain system dynamics were verified. On this basis, the ultimately uniformly boundness of the control method was proven. Experimental results indicate that when partial failure occurs in electromagnets, adaptive variables are adjusted according to fault conditions and affect control currents, thereby achieving fault tolerance performance. For steady-state signal tracking, left and right electromagnets show maximum errors of 0.2 and 0.1 mm and average errors of 0.14 and 0.09 mm, respectively. For sinusoidal signal tracking, left and right electromagnets demonstrate maximum errors of 0.2 and 0.1 mm and average errors of 0.18 and 0.10 mm, respectively. For square wave signal tracking, left and right electromagnets exhibit maximum errors of both 1.1 mm and average errors of 0.18 and 0.14 mm, respectively. The proposed method displays adaptability to faults in both left and right electromagnets, enabling rapid tracking of desired signals and ensuring operational reliability and safety of maglev vehicles.
-
Key words:
- maglev train /
- levitation system /
- fault-tolerant control /
- adaptive control /
- neural network
-
图 3 发生部分短路劣化的电磁铁现场照片
Figure 3. On-site photos of electromagnet with partial short-circuit degradation
图 7 平稳信号跟踪气隙误差对比
Figure 7. Comparisons of tracking air gap errors of steady-state signal
图 11 正弦信号跟踪气隙误差对比
Figure 11. Comparison of tracking air gap errors of sinusoidal signal
图 15 方波信号跟踪气隙误差对比
Figure 15. Comparison of tracking air gap errors of square wave signal
表 1 悬浮系统参数
Table 1. Levitation system parameters
物理参数 取值 M1、M2/kg 350 Mh+Mc/kg 2 100 ke/(N·m2·A－2) 0.004 g/(m·s－2) 9.8 
下载: 导出CSV
表 2 平稳信号跟踪误差
Table 2. Errors of steady-state signal tracking
控制方法 左/右电磁铁悬浮气隙的最大跟踪误差/mm 左/右电磁铁悬浮气隙的平均跟踪误差/mm 所提方法 0.2/0.1 0.14/0.09 PID 1.4/1.4 0.83/0.77 LQR 2.8/2.6 2.73/2.61
下载: 导出CSV
表 3 正弦信号跟踪误差
Table 3. Errors of sinusoidal signal tracking
控制方法 左/右电磁铁悬浮气隙的最大跟踪误差/mm 左/右电磁铁悬浮气隙的平均跟踪误差/mm 所提方法 0.2/0.1 0.14/0.10 PID 1.3/1.3 0.76/0.71 LQR 4.4/4.3 2.54/2.41
下载: 导出CSV
表 4 方波信号跟踪误差
Table 4. Errors of square wave signal tracking
控制方法 左/右电磁铁悬浮气隙的最大跟踪误差/mm 左/右电磁铁悬浮气隙的平均跟踪误差/mm 所提方法 1.1/1.1 0.18/0.14 PID 1.1/1.0 0.68/0.61 LQR 3.7/3.5 2.60/2.47
下载: 导出CSV
-
[1] 林国斌, 刘万明, 徐俊起, 等. 中国高速磁浮交通的发展机遇与挑战[J]. 前瞻科技, 2023, 2(4): 7-18.LIN Guo-bin, LIU Wan-ming, XU Jun-qi, et al. Opportunities and challenges for the development of high-speed maglev transportation in China[J]. Science and Technology Foresight, 2023, 2(4): 7-18. [2] 丁叁叁, 付善强, 梁鑫. 中国高速磁浮交通工程实践与展望[J]. 前瞻科技, 2023, 2(4): 40-48.DING San-san, FU Shan-qiang, LIANG Xin. Engineering practice and prospect of high-speed maglev transportation in China[J]. Science and Technology Foresight, 2023, 2(4): 40-48. [3] 熊嘉阳, 邓自刚. 高速磁悬浮轨道交通研究进展[J]. 交通运输工程学报, 2021, 21(1): 177-198. doi: 10.19818/j.cnki.1671-1637.2021.01.008XIONG Jia-yang, DENG Zi-gang. Research progress of high-speed maglev rail transit[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 177-198. doi: 10.19818/j.cnki.1671-1637.2021.01.008 [4] 马卫华, 罗世辉, 张敏, 等. 中低速磁浮车辆研究综述[J]. 交通运输工程学报, 2021, 21(1): 199-216. doi: 10.19818/j.cnki.1671-1637.2021.01.009MA Wei-hua, LUO Shi-hui, ZHANG Min, et al. Research review on medium and low speed maglev vehicle[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 199-216. doi: 10.19818/j.cnki.1671-1637.2021.01.009 [5] LI F X, SUN Y G, XU J Q, et al. Control methods for levitation system of EMS-type maglev vehicles: an overview[J]. Energies, 2023, 16(7): 2995. doi: 10.3390/en16072995 [6] 刘恒坤, 郝阿明, 常文森. 磁悬浮系统的非线性PID控制[J]. 控制工程, 2007, 14(6): 653-656. doi: 10.3969/j.issn.1671-7848.2007.06.027LIU Heng-kun, HAO A-ming, CHANG Wen-sen. Nonlinear PID control of magnetic suspension systems[J]. Control Engineering of China, 2007, 14(6): 653-656. doi: 10.3969/j.issn.1671-7848.2007.06.027 [7] SUN Y G, QIANG H Y, WANG L, et al. A fuzzy-logic-system-based cooperative control for the multielectromagnets suspension system of maglev trains with experimental verification[J]. IEEE Transactions on Fuzzy Systems, 2023, 31(10): 3411-3422. doi: 10.1109/TFUZZ.2023.3257036 [8] SUN Y G, XU J Q, QIANG H Y, et al. Adaptive sliding mode control of maglev system based on RBF neural network minimum parameter learning method[J]. Measurement, 2019, 141: 217-226. doi: 10.1016/j.measurement.2019.03.006 [9] 钟志贤, 蔡忠侯, 祁雁英. 单自由度磁悬浮系统无模型自适应控制的研究[J]. 西南交通大学学报, 2022, 57(3): 549-557, 581.ZHONG Zhi-xian, CAI Zhong-hou, QI Yan-ying. Model-free adaptive control for single-degree-of-freedom magnetically levitated system[J]. Journal of Southwest Jiaotong University, 2022, 57(3): 549-557, 581. [10] LENG P, YU P C, GAO M, et al. Optimal control scheme of maglev train based on the disturbance observer[C]//IEEE. 2019 Chinese Control Conference. New York: IEEE, 2019: 1935-1940. [11] SUN Y G, HE Z Y, XU J Q, et al. Cooperative model predictive levitation control for two-points electromagnetic levitation system of high-speed maglev vehicle[J]. IEEE Transactions on Intelligent Vehicles, 2023, DOI: 10.1109/TIV.2023.3329073. [12] DEY S, BANERJEE S, DEY J. Frequency-domain tuning of a robust optimal 2-DOF fractional order PID controller for a maglev system[J]. IEEE Transactions on Industrial Informatics, 2024, 20(9): 11348-11361. doi: 10.1109/TII.2024.3403249 [13] KANG J S, HUANG X Y, XIA C, et al. Ultra-local model-free adaptive super-twisting nonsingular terminal sliding mode control for magnetic levitation system[J]. IEEE Transactions on Industrial Electronics, 2024, 71(5): 5187-5194. doi: 10.1109/TIE.2023.3285925 [14] JIN L, LONG Z Q, ZENG J W. Research on fault-tolerant control problem for suspension system of medium speed maglev train[C]//IEEE. 29th Chinese Control and Decision Conference (CCDC). New York: IEEE, 2017: 2993-2998. [15] MICHAIL K, ZOLOTAS A C, GOODALL R M. Optimised sensor selection for control and fault tolerance of electromagnetic suspension systems: a robust loop shaping approach[J]. ISA Transactions, 2014, 53(1): 97-109. doi: 10.1016/j.isatra.2013.08.006 [16] YETENDJE A, SERON M M, DE DONÁ J A, et al. Sensor fault-tolerant control of a magnetic levitation system[J]. International Journal of Robust and Nonlinear Control, 2010, 20(18): 2108-2121. doi: 10.1002/rnc.1572 [17] 龙志强, 翟明达, 王志强, 等. 磁浮列车状态监测、故障诊断与容错控制[M]. 上海: 上海科学技术出版社, 2023.LONG Zhi-qiang, ZHAI Ming-da, WANG Zhi-qiang, et al. Condition monitoring, fault diagnosis and fault-tolerant control of the maglev train[M]. Shanghai: Shanghai Scientific and Technical Publishers, 2023. [18] AMIN A A, HASAN K M. A review of fault tolerant control systems: advancements and applications[J]. Measurement, 2019, 143: 58-68. doi: 10.1016/j.measurement.2019.04.083 [19] JI W, LYU D Y, LUO S H, et al. Multiple models-based fault tolerant control of levitation module of maglev vehicles against partial actuator failures[J]. IEEE Transactions on Vehicular Technology, 2025, 74(2): 2231-2240. doi: 10.1109/TVT.2024.3399235 [20] ZHAI M D, LONG Z Q, LI X L. Fault-tolerant control of magnetic levitation system based on state observer in high speed maglev train[J]. IEEE Access, 2019, 7: 31624-31633. doi: 10.1109/ACCESS.2019.2898108 [21] SUN Y G, LI F X, LIN G B, et al. Adaptive fault-tolerant control of high-speed maglev train suspension system with partial actuator failure: design and experiments[J]. Journal of Zhejiang University-SCIENCE A, 2023, 24(3): 272-283. doi: 10.1631/jzus.A2200189 [22] SONG Y D, HE L, ZHANG D, et al. Neuroadaptive fault-tolerant control of quadrotor UAVs: a more affordable solution[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(7): 1975-1983. doi: 10.1109/TNNLS.2018.2876130 [23] ZHAO K, SONG Y D, SHEN Z X. Neuroadaptive fault-tolerant control of nonlinear systems under output constraints and actuation faults[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(2): 286-298. doi: 10.1109/TNNLS.2016.2619914 [24] CHENG H, HUANG X C, LI Z Q. Unified neuroadaptive fault-tolerant control of fractional-order systems with or without state constraints[J]. Neurocomputing, 2023, 524: 117-125. doi: 10.1016/j.neucom.2022.12.035 [25] SUN Y G, XU J Q, LIN G B, et al. RBF neural network-based supervisor control for maglev vehicles on an elastic track with network time delay[J]. IEEE Transactions on Industrial Informatics, 2022, 18(1): 509-519. doi: 10.1109/TII.2020.3032235 [26] LIU L, LIU Y J, TONG S C. Neural networks-based adaptive finite-time fault-tolerant control for a class of strict-feedback switched nonlinear systems[J]. IEEE Transactions on Cybernetics, 2019, 49(7): 2536-2545. doi: 10.1109/TCYB.2018.2828308 [27] PARK J, SANDBERG I W. Universal approximation using radial-basis-function networks[J]. Neural Computation, 1991, 3(2): 246-257. doi: 10.1162/neco.1991.3.2.246 [28] ZHANG S Z, LIU Q, WU X B, et al. A self-adaptive and multiple activation function neural network for facial expression recognition[C]//ACM. 2021 5th International Conference on Electronic Information Technology and Computer Engineering. New York: ACM, 2021: 1106-1111. [29] SONG Y D, HUANG X C, JIA Z J. Dealing with the issues crucially related to the functionality and reliability of NN-associated control for nonlinear uncertain systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(11): 2614-2625. doi: 10.1109/TNNLS.2016.2598616 [30] GAO Z, YU W, YAN J. Neuroadaptive fault-tolerant control embedded with diversified activating functions with application to auto-driving vehicles under fading actuation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(5): 6255-6264. doi: 10.1109/TNNLS.2023.3248100 [31] GE S S, HANG C C, ZHANG T. A direct method for robust adaptive nonlinear control with guaranteed transient performance[J]. Systems and Control Letters, 1999, 37(5): 275-284. doi: 10.1016/S0167-6911(99)00032-8 [32] LONG Z W, SHI G H, WANG L C. Suspension influence analysis of track irregularity of maglev train[C]//IEEE. 2010 Chinese Control and Decision Conference. New York: IEEE, 2010: 942-947. -
点击查看大图
图(15) / 表(4)
计量
- 文章访问数: 727
- HTML全文浏览量: 166
- PDF下载量: 49
- 被引次数: 0
