1. School of Traffic and Transportation Beijing Jiaotong University,Beijing 100044, China; 2. Dynamic Integration and Energy Storage Systems Engineering Technology Research Center, Qingdao University, Qingdao 266071, China
Abstract：In order to better predict failure rate of urban rail trains, the paper proposes a fault predict model based on PSO-BP neural network. Using Matlab with Newff function, failure rate prediction of urban rail train is modeled and simulated using the error back propagation (BP) neural network and BP neural network based on particle swarm algorithm optimization (PSO-BP).The simulation results show that the effect of failure rate predictive model with PSO-BP neural network is better than BP neural network. As a result, PSO-BP neural network is chosen as the failure rate predictive model and the theoretical basis for the decision of preventive maintenance.
[1] 谌爱文.基于BP和RBF神经网络的数据预测方法研究[D].长沙:中南大学,2007. Zhan Aiwen.Data forecasting methods research based on BP ANN and RBF ANN[D].Changsha: Journal of Central South University,2007. [2] Pham H T,Yang B S.Estimation and forecasting of machine health condition using.ARMA/GARCH model[J].Mechanical Systems and Signal Processing,2010,24(2):546-558. [3] Chen Z S,Yang Y M,Hu Z,et al.Detecting and predicting early faults of complex rotating machinery based on cyclostationary time series model[J].Journal of Vibration and Acoustics,2006,128(5):666-671. [4] Pieter-Jan Vlok,Maciej wnek,Maciej Zygmunt.Utilising statistical residual life estimates of bearings to quantify the influence of preventive maintenance actions[J].Mechanical Systems and Signal Processing,2004,18: 833-847. [5] 李建伟,程晓卿,秦勇,等.基于BP神经网络的城市轨道交通车辆可靠性预测[J].中南大学学报(自然科学版),2013,(S1):42-46. Li Jianwei,Cheng Xiaoqing,Qin Yong,et al.Reliability prediction based on the BP neural network of urban rail transit vehicle[J].Journal of Central South University:Science and Technology,2013,(S1):42-46. [6] 李瑞莹,康锐.基于ARMA模型的故障率预测方法研究[J].系统工程与电子技术,2009,30(8):1588-1591. Li Ruiying,Kang Rui.Research on failure rate forecasting method based Oil ARMA model[J].Systems Engineering and Electronics,2009,30(8):1588-1591. [7] Huang R,Xi L,Li X,et al.Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods[J].Mechanical Systems and Signal Processing,2007,21(1):193-207. [8] Kutylowska,Malgorzata.Neural network approach for failure rate prediction[J].Engineering Failure Analysis, 2015,47(1):41-48. [9] 余江.地铁车辆关键系统可靠性分析及应用研究[D].北京:北京交通大学,2012. Yu Jiang. Reliability analysis and application research of Metro key system[D].Beijing:Beijing Jiaotong University,2012. [10] 郭阳明,冉从宝,姬昕禹,等.基于组合优化BP神经网络的模拟电路故障诊断[J].西北工业大学学报,2013,31(1):44-48. Guo Yangming,Ran Congbao,Ji Xinyu,et al.Fault diagnosis in analog circuits based on combined·optimization BP neural networks[J].Journal of Northwestern Polytechnical University,2013,31(1):44-48. [11] 龙泉,刘永前,杨勇平.基于粒子群优化BP神经网络的风电机组齿轮箱故障诊断方法[J].太阳能学报,2012,33(1):120-123. Long Quan,Liu Yongqian,Yang Yongping.Fault diagnosis method of wind turbine gearbox based on BP neural network trained by particle swarm optimization algorithm[J].Acta Energiae Solaris Sinica,2012,33(1):120-123.
