基于APSO-HSMM的转辙机PHM模型研究（英文）  

A PHM model of switch machine based on APSO-HSMM

作　　者：戴乾军 蒋敏建[2] 张娟娟[2] 王兴仁[2] Qian-jun DAI;Min-jian JIANG;Juan-juan ZHANG;Xing-reng WANG(School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China;College of Electronic Technology, Liuzhou Railway Technical College, Liuzhou 545616, China)

机构地区：[1]兰州交通大学自动化与电气工程学院,兰州730070 [2]柳州铁道职业技术学院电子技术学院,广西柳州545616

出　　处：《机床与液压》2019年第18期63-69,共7页Machine Tool & Hydraulics

基　　金：National Natural Science Foundation of China(61164101)~~

摘　　要：针对转辙机故障发生的随机性与不确定性,提出基于自适应粒子群算法(APSO)优化隐半马尔科夫(HSMM)的设备故障预测与健康管理(PHM)模型,旨在现对传统信号维修策略进行优化改进研究。首先,将S700K型转辙机的机械部件的退化过程按全生命周期进行划分,建立设备退化状态的一般HSMM模型;其次,选择APSO算法对转辙机PHM模型进行智能优化;再次,采用前向-后向算法(F-B)对优化的模型(APSO-HSMM)进行参数估计;最后,通过实例分析验证了该优化模型对转辙机健康状态评估及剩余寿命预测的有效性。As far as the randomness and uncertainty of switch machine fault was concerned, the equipment fault prognostics and health management (PHM) model based on the adaptive particle swarm optimization is proposed to optimize the hidden semi-markov. Firstly, the degradation process of mechanical parts of S700K switch machine is divided according to the whole life cycle, then the general HSMM model of equipment degradation state is established. Secondly, APSO algorithm is selected to optimize the PHM model of switch machine intelligently. Thirdly, the parameters of the optimized model are estimated using the forward-backward algorithm. Finally, the effectiveness of the model for state assessment and remaining life prognostics is verified by an example analysis.

关 键 词：转辙机 自适应粒子群 故障预测与健康管理 状态评估 剩余寿命预测 

分 类 号：U283.21[交通运输工程—交通信息工程及控制]