摘要
针对S700K转辙机动作功率曲线非线性、非平稳的特点,提出一种基于模糊聚类的信号分析及故障诊断方法。该方法对转辙机故障下的动作功率曲线提取特征值,由各模式下的10种特征值组成特征模式矩阵,利用模糊聚类分析算法求该矩阵的模糊相似矩阵与模糊等价矩阵,在模糊等价矩阵中,当可变阈值λ在[0,1]内变动时,模糊等价矩阵转化为等价的布尔矩阵,由布尔矩阵可以形成动态聚类图并得到分类结果,从而实现故障诊断。研究结果表明:该算法能够准确地提取故障特征且支持多种故障同时检测,有效提高了S700K转辙机故障诊断的精度与诊断效率。
According to the nonlinear and non-stationary characteristics of the S700K switch machine's action power curve,a signal analysis and fault diagnosis method based on fuzzy clustering was proposed.The eigenvalues of the action power curve under the fault of the switch machine were extracted,and a feature pattern matrix was constructed from the 10 eigenvalues in each mode.The fuzzy clustering analysis algorithm was used to obtain the fuzzy similarity matrix and fuzzy equivalent of the matrix.In the fuzzy equivalence matrix,when variable thresholdλchanged in[0,1],the fuzzy equivalence matrix was transformed into an equivalent Boolean matrix.The dynamic clustering graph was formed by the Boolean matrix and the classification result was obtained.Thereby the fault diagnosis was achieved.The results show that the algorithm can accurately extract fault features and support multiple fault detection at the same time,which effectively improves the accuracy and diagnostic efficiency of S700K switch fault diagnosis.
作者
刘新发
魏文军
LIU Xinfa;WEI Wenjun(School of Automation&Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Key Laboratory of Opto-technology and Intelligent Control,Ministry of Education,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2019年第9期2148-2155,共8页
Journal of Central South University:Science and Technology
基金
国家重点研发计划资助(2017YFB1201003-020)~~
作者简介
通信作者:魏文军,教授,博士,从事智能故障诊断的研究,E-mail:weiwenjun@mail.lzjtu.cn。
