학술논문

Fault diagnosis of high-speed railway turnout based on support vector machine
Document Type
Conference
Source
2016 IEEE International Conference on Industrial Technology (ICIT) Industrial Technology (ICIT), 2016 IEEE International Conference on. :1539-1544 Mar, 2016
Subject
Communication, Networking and Broadcast Technologies
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Engineering Profession
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Feature extraction
Rail transportation
Support vector machines
Fault diagnosis
Principal component analysis
Rails
Maintenance engineering
turnout
fault diagnosis
SVM
feature vector geneartion
Language
Abstract
With the fast development of Chinese high speed railway, the demand for the maintenance of railway equipment has increased rapidly. This paper studies an intelligent diagnosis method for high-speed railway turnout based on the support vector machine. We focus on the study about the methods of generating the feature vector and propose a rule-based method that utilizes the experts' experience knowledge. By experimenting on the current curve collected on the real turnouts, we compare the advantages of different feature vector generation methods and demonstrate that our rule-based method performs best in the fault diagnosis. This work realizes the purpose of identifying the fault curves by computer automatically and can save a lot of manpower and resources. It provides a basis for the intelligent fault diagnosis of turnouts.