WANG Deng-fei1,2， CHEN Guang-wu1,2， XING Dong-feng1,2， LIANG Dou-dou1,2
（1. Automatic Control Research Institute, Lanzhou Jiaotong University， Lanzhou 730070， China；2. Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China）
Abstract： In order to realize the fault diagnosis of the control circuit of all-electronic computer interlocking system (ACIS) for railway signals, taking a five-wire switch electronic control module as an research object, we propose a method of selecting the sample set of the basic classifier by roulette method and realizing fault diagnosis by using SVM-AdaBoost. The experimental results show that the proportion of basic classifier samples affects classification accuracy, which reaches the highest when the proportion is 85%. When selecting the sample set of basic classifier by roulette method, the fault diagnosis accuracy is generally higher than that of the maximum weight priority method. When the optimal proportion 85% is taken, the accuracy is highest up to 96.3%. More importantly, this way can better adapt to the critical data and improve the anti-interference ability of the algorithm, and therefore it provides a basis for fault diagnosis of ACIS.
Key words： all-electronic computer interlocking system (ACIS)； switch control circuit; support vector machine (SVM)；AdaBoost； fault diagnosis
CLD number： U284.5 doi： 10.3969/j.issn.1674-8042.2020.03.008
References
［1］Chen G W. Key technology research of rail transportation safety computer system and safety control mechanism. Lanzhou： Lanzhou Jiaotong University, 2014.
［2］He T, Fan D W, Wei Z S. Research on the allelectronic performance units for computer interlocking systems at railway stations. Journal of the China Railway Society, 2007, 29(2): 118-121.
［3］Wen C L, Lu F Y, Bao Z J. A review of data driven-based incipient fault diagnosis. Acta Automatica Sinica, 2016, 42(9): 1285-1299.
［4］Zheng Y S, Niu X T, Kang Y J. Fault diagnosis research for 25 Hz phase sensitive track circuit based on bat algorithm to optimize fuzzy neural network. Journal of the China Railway Society, 2018, 40(12): 93-100.
［5］Chen J, Roberts C, Weston P. Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems. Control Engineering Practice, 2008, 16(5): 585-596.
［6］Yang Y, Tao C X, Zhang R X. Fault diagnosis of switch control circuit using support vector machine optimized by genetic algorithm. Computer Measurement & Control, 2013, 21(2): 48-49.
［7］Liang X, Wang H F, Guo J. Bayesian network based fault diagnosis method for on-board equipment of train control system. Journal of the China Railway Society, 2017, 8(39): 93-100.
［8］Yang X W, Ma Z, Yuan S. Multi-class adaboost algorithm based on the adjusted weak classifier. Journal of Electronics & Information Technology, 2016, 38(2): 373-380.
［9］Yin Z Y, Hou J. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes. Neurocomputing, 2016, 174: 643-650.
［10］Lee W J, Jun C H, Lee J S. Instance categorization by support vector machines to adjust weights in AdaBoost for imbalanced data classification. Information Sciences, 2017, 381: 92-103.
［11］Feng X, Wang X F. Analysis on reliability and performance of computer-based interlocking system with the dynamic fault tree method. Journal of the China Railway Society, 2012, 33(12): 78-82.
［12］Zhang M Y, Wang D F, Wei Z S. An improved AdaBoost training algorithm. Journal of Northwestern Polytechnical University, 2017, 35(6): 1119-1124.
［13］Hang J, Zhang J Z, Cheng M. Application of multi-class fuzzy support vector machine classifier for fault diagnosis of wind turbine. Fuzzy Sets & Systems, 2015, 297( C): 128-140.
［14］Wang L L, Henry Y, T Ngan, et al. Automatic incident classi?cation for large-scale trafic data by adaptive boosting SVM. Information Sciences, 2018, 467: 59-73.
基于SVM-AdaBoost的道岔控制电路故障诊断方法研究
王登飞1,2， 陈光武1,2， 邢东峰1,2， 梁豆豆1,2
（1. 兰州交通大学 自动控制研究所， 甘肃 兰州 730070； 2. 甘肃省高原交通信息工程及控制重点实验室， 甘肃 兰州 730070）
摘要:为实现铁路信号全电子计算机联锁系统控制电路的故障诊断， 以五线制道岔全电子控制模块为例， 提出了采用轮盘赌转法选择基本分类器的样本集， 采用SVM-AdaBoost算法实现故障诊断的方法。 实验结果表明， 基本分类器样本占比影响分类准确率， 样本占比为85%时准确率最高； 轮盘赌转法选择基本分类器的样本集后故障诊断准确率普遍高于最大权重优先的方式， 准确率达96.3%； 同时该方法能更好地适应临界数据， 提高算法抗干扰能力。 因此本论文的研究内容可为全电子计算机联锁系统的故障诊断提供依据。
关键词:全电子计算机联锁系统； 开关控制电路； 支持向量机； AdaBoost； 故障诊断
引用格式：WANG Deng-fei， CHEN Guang-wu， XING Dong-feng, et al. Fault diagnosis method for switch control circuit based on SVM-AdaBoost. Journal of Measurement Science and Instrumentation, 2020, 11（3）： 251-257. ［doi： 10.3969／j.issn.1674-8042.2020.03.008］
[full text view]
