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

High-speed train running gear system fault diagnosis method based on semi-quantitative information fusion

A technology for high-speed trains and system failures, applied to computer parts, instruments, calculations, etc., can solve problems such as no analysis, achieve the effects of improving results, realizing fault classification, and realizing fault diagnosis

Active Publication Date: 2021-06-18
CHANGCHUN UNIV OF TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of not analyzing the influence of the reliability of existing knowledge on the fault diagnosis process based on the confidence rule base in the current research, and propose a high-speed train running part system fault diagnosis method with semi-quantitative information fusion

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
  • High-speed train running gear system fault diagnosis method based on semi-quantitative information fusion
  • High-speed train running gear system fault diagnosis method based on semi-quantitative information fusion
  • High-speed train running gear system fault diagnosis method based on semi-quantitative information fusion

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT One, a kind of semi-quantitative information fusion method for fault diagnosis of the high-speed train running part system described in the present embodiment, the method specifically includes the following steps:

[0021] Step 1. Collect the monitoring data of the running system during actual operation, then use the collected monitoring data to construct a training data set, and record the labels;

[0022] Initialize the parameter vector in the confidence rule base, and establish the confidence rule base model of the training part;

[0023] Step 2, analyze the reliability of the initialization parameters in the confidence rule base model, and obtain the reliability factor of each confidence rule;

[0024] Step 3: Integrate the reliability factor into the evidence reasoning part of the confidence rule base model by using the evidence discount theory to realize the optimization of model reasoning;

[0025] Step 4. The tra...

specific Embodiment approach 2

[0029] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the first step, the monitoring data of the running part system is collected during actual operation, and then the collected monitoring data is used to construct a training data set. The specific process is :

[0030] Collect the N of the running part system of the high-speed train during actual operation 1 The monitoring data of each moment, wherein, the monitoring data of each moment is the temperature data of different components in the running system; then N 1 Time information, collected monitoring data and corresponding labels are stored as a two-dimensional data matrix X 1 , two-dimensional data matrix X 1 The first column is N 1 Time information, the second column is the temperature data collected at each time, and the third column is the label corresponding to each time (marked as whether there is a failure and what type of failure);

[0031] For a two-dimension...

specific Embodiment approach 3

[0033] Specific embodiment three: the difference between this embodiment and specific embodiment two is that in the first step, the parameter vector in the confidence rule base is initialized, and the confidence rule base model is established. The specific process is:

[0034] Initialize the parameter vector in the confidence rule base, select the kth confidence rule R shown in formula (1) k As the knowledge representation of the established initial belief rule base model:

[0035]

[0036] where x mIndicates the mth numeric observation value of the input, Indicates the mth input reference value under the kth confidence rule, m=1,2,...,M, M is the total number of input numerical observation values, is relative to the nth fault type D under the kth confidence rule n Confidence degree of , n=1,2,...,N, N is the total number of fault types, θ k is the rule weight of the kth confidence rule, δ m is the weight of the mth input reference value, r k is the reliability fact...

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 high-speed train running gear system fault diagnosis method based on semi-quantitative information fusion, and belongs to the field of fault diagnosis. The method solves the problem that the influence of the reliability of the existing knowledge on the fault diagnosis process based on the belief rule base is not analyzed in the current research. According to the method, a large amount of knowledge and monitoring data accumulated in actual operation of the high-speed train are used for modeling, an accurate analytical model of the running gear is not needed, a large amount of monitoring data of the running gear under the abnormal working condition is not needed, the diagnosis function can be well achieved under the small sample condition, and actual application is facilitated; and the difficulty of the belief rule base theory in the fault diagnosis of the running gear is also considered, that is, the fault diagnosis is difficult under the unreliable expression of knowledge. The knowledge reasoning of the confidence rule base is corrected by quantifying the unreliable part of the knowledge, so that the fault diagnosis effect is improved; and meanwhile, fault diagnosis and fault classification of the axial bearing of the running gear system are realized. The method can be applied to fault diagnosis of the running gear system.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, and in particular relates to a method for fault diagnosis of a running part system of a high-speed train with semi-quantitative information fusion. Background technique [0002] With the development and progress of science and technology, the scale and complexity of high-speed railways have been greatly improved. As the core carrier of high-speed rail, high-speed trains are a successful example of my country's independent innovation and a representative of high-end equipment. Its safe and reliable operation is the fundamental prerequisite for the development of transportation. The running gear system is one of the core systems of high-speed trains. It plays an important role in supporting the car body, transmitting loads, braking force, and traction. The performance of the running gear directly affects the reliability and safety of vehicles on rail. Fault diagnosis technology is an effective measu...

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): G06K9/62
CPCG06F18/22G06F18/24G06F18/214
Inventor 程超王久赫王威珺谢普邵俊捷付彩欣
Owner CHANGCHUN 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