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

Mechanical equipment fault type diagnosis method

A technology of mechanical equipment and fault types, applied in the field of artificial intelligence, can solve the problems of small sample size and simplification of fault data, and achieve the effect of improving versatility and accuracy and expanding spatial distribution

Active Publication Date: 2021-08-06
中国人民解放军92578部队 +1
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To solve the problem of small sample size and simplification of fault data, and improve the versatility and scalability of the machine fault diagnosis model

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
  • Mechanical equipment fault type diagnosis method
  • Mechanical equipment fault type diagnosis method
  • Mechanical equipment fault type diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The diagnostic method of mechanical equipment fault type that the present invention proposes, comprises:

[0013] Collect mechanical equipment failure data sets of different models and working conditions, and preprocess the data sets; establish an initial network model, multiple generators are connected by sharing local weights, and each generator corresponds to the health status of mechanical equipment in a data set , confrontation learning features; the model is trained adversarially until it reaches the Nash equilibrium state; the weight of the generator remains unchanged, and the discriminator is trained until the discriminator obtains an effective ability to distinguish the types of mechanical equipment failures.

[0014] Below in conjunction with accompanying drawing, introduce an embodiment of the inventive method:

[0015] (1) Obtain four data sets for fault diagnosis from four public data sets, including Case Western Reserve University Bearing Data Center Beari...

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 belongs to the technical field of artificial intelligence, and particularly relates to a mechanical equipment fault type diagnosis method. According to the method, mode collapse is relieved and a fault data space is expanded by learning effective fault features, so that diagnosis of mechanical fault types is carried out. The set of weight sharing generators is designed to generate fault data of the same type. Universal features of the same fault can pass through a local sharing layer. Through discriminator training based on generated data and real data, the discriminator can obtain fault diagnosis capability. According to the method, a fault data generation network of multiple generators is constructed, so that the problem of'mode collapse 'easily occurring in a current method for generating fault data based on a single-generator neural network is solved, and the problem of a single mode of generating fault data is solved; and, through a local weight sharing mechanism of the group generator, basic fault features of data of the same fault type are effectively learned, so that spatial distribution of fault data is effectively expanded, and universality and accuracy of fault classification are improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method for diagnosing mechanical equipment faults. Background technique [0002] In modern industrial society, mechanical equipment is an indispensable and common component, which plays a vital role in industrial production based on mechanical equipment. The complex working environment and irregular operation process affect the safety of industrial equipment and cause abnormalities in mechanical equipment. Moreover, the effective maintenance of mechanical equipment is the basic requirement for maintaining normal operation. Preventing equipment failures can reduce property losses and avoid serious accidents. Therefore, it is necessary to prevent and discover mechanical equipment failures, correctly identify the types of failures, and provide corresponding solutions for mechanical failures. [0003] With more and more data accumulated by mechanical e...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/048G06N3/045G06F18/24
Inventor 高晟耀郭庆稳宋艳李沂滨高辉
Owner 中国人民解放军92578部队
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