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

Method and system for detecting faults of point switch based on convolution neural network algorithm

A convolutional neural network and fault detection technology, which is applied in neural learning methods, biological neural network models, test/monitoring control systems, etc., to achieve optimal feature extraction, rich training data, and high detection accuracy

Inactive Publication Date: 2018-08-24
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current fault detection of switch machines requires special feature engineering to extract the features of the power curve. However, the quality of the features has a crucial impact on the generalization performance of the algorithm. Even experts must design high-quality features. it's not easy

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
  • Method and system for detecting faults of point switch based on convolution neural network algorithm
  • Method and system for detecting faults of point switch based on convolution neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Convolutional Neural Network (CNN) is a deep learning model. The power curve is input into the convolutional neural network, and the feature learning ability of the convolutional neural network is used to automatically extract features, thereby realizing fault detection.

[0026] A switch machine fault detection system based on a convolutional neural network algorithm, comprising a switch machine power data acquisition unit (1), a power curve generation unit (2), and a fault detection unit (3) based on a convolutional neural network algorithm , human-computer interaction unit (4); switch machine power data acquisition unit (1), power curve generation unit (2), fault detection unit based on convolutional neural network (3), and human-computer interaction unit (4) have Logically, the power data is generated into a graph, and then the graph is input to the convolutional neural network to intelligently judge the state of the switch machine, and output the fault type correspo...

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 method and a system for detecting faults of a point switch based on a convolution neural network algorithm. The system is improvement for a previous point switch fault detection system based on manual characteristic engineering. A convolution neural network is a deep learning model. A point switch power graph is input to the convolution neural network, and using characteristic learning capability of the convolution neural network, characteristics can be automatically extracted, to realize high-precision fault type detection.

Description

technical field [0001] The invention relates to the technical field of switch machine fault detection in rail transit, in particular to an intelligent detection method and system for a switch machine fault based on a convolutional neural network algorithm. Background technique [0002] The action process of the switch machine generally includes several stages of starting, unlocking, switching, locking and indicating. Under normal conditions, the power curves of each stage in the operation process of the switch machine have different characteristics; at the same time, under different failure modes, the power curves also have different characteristics. Therefore, there is a direct relationship between the power curve of the switch machine and the working state, and the fault type can be identified through the power curve. The current fault detection of switch machines requires special feature engineering to extract the features of the power curve. However, the quality of the ...

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): G05B23/02G06N3/04G06N3/08G06K9/62
CPCG05B23/0221G06N3/084G06N3/045G06F18/214
Inventor 张艳青孙迪钢
Owner SOUTH CHINA UNIV OF TECH
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