Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A design method for on-line fault detection of high-speed railway traction system

A traction system and fault detection technology, applied in the direction of calculation, computer parts, signal pattern recognition, etc., can solve the problems that the change characteristics are not obvious, not suitable for small fault diagnosis, etc., and achieve the effect of improving the detection ability

Inactive Publication Date: 2019-01-15
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the micro-fault is between no fault and fault, its change characteristics are not very obvious, which requires higher sensitivity to the fault diagnosis algorithm, and the original algorithm is not suitable for the diagnosis of micro-faults.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A design method for on-line fault detection of high-speed railway traction system
  • A design method for on-line fault detection of high-speed railway traction system
  • A design method for on-line fault detection of high-speed railway traction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0054] The present invention provides a system design method for detecting and locating minor faults of an electric traction system, comprising the following steps:

[0055] In the offline stage, the high-speed rail has not been running offline, and the accumulated historical data of normal operation is used:

[0056] (1) Store the operating data of the high-speed rail traction system under normal operating conditions;

[0057] (2) Process the stored data with PCA and map it to the pivot space and residual space;

[0058] (3) In the principal component space, use ICA to extract features of non-Gaussian components;

[0059] (4) For the data processed by ICA and the data in the residual space, the statistics are defined according to the Kullback-Leibler divergence;

[0060] (5) Determine the threshold of the statisti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a design method for on-line fault detection of a high-speed railway traction system, comprising an off-line stage and an on-line stage. Off-line phase: (1) storing the operation data of high-speed railway traction system under normal operation conditions; (2) Principal Component Analysis (PCA) is used to process the stored data, which is mapped to principal component spaceand residual space; (3) In principal component space, ICA is used to extract features from non-Gaussian components; (4) According to the Kullback-Leibler divergence, the statistic is defined for the data processed by ICA and the data of residual space; (5) Determining the threshold of statistics. On-line stage: (6) reading on-line data; (7) processing the on-line data according to the offline stages (2) and (3); (8) calculating the value of on-line data statistics; (9) judging whether the fault occurs or not. This method can detect the minor faults in real-time and effectively when the model of high-speed railway traction system is unknown.

Description

technical field [0001] The invention belongs to the field of high-speed rail fault detection, in particular to a design method for online fault detection of high-speed rail traction systems. Background technique [0002] With the extensive market demand and the progress of science and technology, the high-speed rail technology at home and abroad has developed rapidly in the past two decades and has been successfully applied in practice. With its strong advantages, high-speed rail has received extensive attention and attention from the international intelligent transportation field. At present, high-speed rail has gradually become a means of transportation for the public. However, the frequent failures of the traction system of high-speed rail have attracted increasing attention. When a fault occurs, it will affect the performance of the entire high-speed rail operation, and even cause irreversible serious consequences, such as property loss and casualties. Therefore, this...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/02G06F2218/08G06F18/2135
Inventor 陈宏田姜斌涂明吴建萍颜伟
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com