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

A non-intrusive real-time dynamic monitoring method for external power receiving devices of intelligent trains

A power receiving device, non-invasive technology, applied in the field of fault identification, can solve the problems of inability to realize pantograph crack diagnosis, few types of identifiable faults, and low identification accuracy, and achieve high computing efficiency and identification accuracy, strong The effect of global optimization ability and strong model robustness

Active Publication Date: 2020-05-19
CENT SOUTH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) Pantograph fault diagnosis based on image recognition, but this method cannot realize pantograph crack diagnosis under train running state, and is easily affected by obstructions and installation angles of view;
[0005] (2) Fault diagnosis based on ground equipment, but this method needs to arrange various hardware devices such as sensors along the road network, which is costly, and pantograph fault diagnosis can only be realized in the corresponding road section;
[0006] (3) Fault diagnosis based on the analysis of pantograph vibration characteristics, but this method needs to install external equipment to realize fault diagnosis, and the recognition accuracy is low, and there are few types of faults that can be identified

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 non-intrusive real-time dynamic monitoring method for external power receiving devices of intelligent trains
  • A non-intrusive real-time dynamic monitoring method for external power receiving devices of intelligent trains
  • A non-intrusive real-time dynamic monitoring method for external power receiving devices of intelligent trains

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The following is a detailed description of the embodiments of the present invention. This embodiment is carried out based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes to further explain the technical solution of the present invention.

[0070] The embodiment of the present invention provides a non-intrusive real-time dynamic monitoring method for the external power receiving device of the intelligent train, and realizes the non-intrusive real-time dynamic monitoring method for the external power receiving device of the intelligent train by combining neural network pre-screening and deep learning for final identification. Monitoring and early warning. First, by extracting the relevant information of each sub-band after the original data vector is decomposed by wavelet packet as a feature, it is imported into the SVM neural network for pre-judgment, and real-time dynamic early warning is r...

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 non-intrusive real-time dynamic monitoring method for an external power receiving device of an intelligent train, which includes: obtaining the original current signal of the pantograph and performing preprocessing to obtain a plurality of original data vectors; performing wavelet packet decomposition on the original data vectors , extract feature quantities from each obtained sub-band and construct feature vectors; use feature vectors and pantograph fault classification marks as input and output data respectively, and train fault identification and prediction models; use original data vectors and fault types as input Output data and train the fault identification model; process the real-time current signal of the pantograph according to the aforementioned method to obtain the original data vector and eigenvector, and the fault identification and prediction model predicts the fault of the pantograph according to the eigenvector. If there is a fault, The fault recognition model recognizes the fault type of the pantograph according to the original data vector. The invention realizes the real-time on-line monitoring and fault type identification of the pantograph under the running state of the train.

Description

technical field [0001] The invention relates to the field of fault identification, in particular to a non-invasive real-time dynamic monitoring method for an external power receiving device of an intelligent train. Background technique [0002] With the acceleration of my country's urbanization process and the rapid development of economic construction, people's requirements for comfort, convenience and safety during travel are getting higher and higher. In the field of rail transit, the concept of intelligent trains will play an extremely important role in alleviating the traffic pressure between cities in the future, increasing the comfort and reliability of high-speed trains, and improving the service level of the railway industry. Among them, the external current-receiving equipment of the train is currently the common train pantograph, and its stable operation and safety diagnosis are of great significance for the realization of intelligent trains. [0003] The fault t...

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 Patents(China)
IPC IPC(8): G01R31/00G06N3/04G06N3/08
CPCG01R31/005G06N3/08G06N3/044G06N3/045
Inventor 刘辉刘泽宇
Owner CENT SOUTH UNIV
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