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

Fault diagnosis method for rotary machine based on noise reduction automatic encoder and incremental learning

A technology for noise reduction, automatic coding, and rotating machinery. It is used in the testing of mechanical components, the testing of machine/structural components, and instruments. It can solve the problem of wasting time and computing resources, poor diagnosis results, and poor generalization ability of diagnostic models. problems, to achieve the effect of improving efficiency and saving computing resources

Active Publication Date: 2019-01-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Or when a new failure mode appears in the rotating machinery, a sample of the new failure mode is obtained, and the classification model trained before is discarded and retrained, which will inevitably waste a lot of time and computing resources
Moreover, in the traditional intelligent diagnosis method of rotating machinery, feature selection and extraction is a necessary step, and this step needs to rely on expert experience and knowledge. Improper feature selection may lead to poor generalization ability of the diagnostic model and poor diagnostic effect

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
  • Fault diagnosis method for rotary machine based on noise reduction automatic encoder and incremental learning
  • Fault diagnosis method for rotary machine based on noise reduction automatic encoder and incremental learning
  • Fault diagnosis method for rotary machine based on noise reduction automatic encoder and incremental learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] figure 1 It is a flow chart of the method for diagnosing a fault in a rotating machine based on a noise reduction autoencoder and incremental learning in the present invention.

[0034] In this example, if figure 1 As shown, a kind of rotating machinery fault diagnosis method based on noise reduction automatic encoder and incremental learning of the present invention comprises the following steps:

[0035] S1. Acquisition of vibration signals of rotating machinery

[0036] Use the vibration data acquisition instrument to separately collect the vibration signal of the rotating machinery under a single failure mode, and obtain the failure data of the rotating machinery under each type of failure mode d k , where k represents the failure mode number;

[0037] S2, split the vibration signal

[0038] For fault data d k Perform equidistant segmentation to obtain N segments of fault data, and assume that each segment of fault data contains n data points;

[0039] In this...

example

[0058] In this embodiment, taking the data collected by a high-speed train axle bearing test bench as an example, the specific process is as follows:

[0059] The bearing test bench is composed of drive motor, conveyor belt system, horizontal loading table, vertical loading table, wheel axle and wheel-to-axle box, etc. The test bearing is installed in the axle box. The bearing model used in the experiment is SKF197726. The failure mode of the bearing is shown in Table 1. For each failure mode, vibration signals under 9 working conditions are collected, as shown in Table 2, and the sampling rate is 5120Hz.

[0060] Table 1 is a list of tested bearing failure modes for diagnostic analysis;

[0061] Table 2 is a list of 9 working conditions simulated in the experiment.

[0062]

[0063]

[0064] Table 1

[0065]

[0066] Table 2

[0067] For each type of failure mode in Table 1, the number of samples is 1350, there are 11 types in total, and the total number of sampl...

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 fault diagnosis method for a rotary machine based on a noise reduction automatic encoder and incremental learning. The method comprises the steps of: performing acquisition and segmentation on the vibration signals under a single fault mode of the rotary machine; training a DAE with a sample set consisting of the segmented signals; obtaining a corresponding network weightvalue matrix and deviation vectors W1, k, b1, k, w2, k, and b2, k; for a testing sample y of the rotary machine, calculating the reconstruction error Ek_y of the sample reconstructed by the DAE corresponding to each type of fault mode, and then finding the minimum value of the reconstruction error, wherein the corresponding fault mode is the fault mode to which the to-be-tested rotary machine belongs.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of rotating machinery, more specifically, [0002] It relates to a method for fault diagnosis of rotating machinery based on denoising autoencoder and category incremental learning. Background technique [0003] As a key mechanism in mechanical equipment, rotating machinery plays an important role in modern large-scale industrial equipment such as airplanes, trains and fans. Due to the complex system, high working intensity, harsh working environment and other factors, rotating machinery is prone to various failures during operation. If these failures cannot be detected and dealt with in time, the reliability and safety of mechanical equipment will be reduced, resulting in economic losses and even personal safety accidents. Therefore, it is of great significance to carry out fault diagnosis on rotating machinery. [0004] With the development of computer software and hardware technology...

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): G01M13/00G01M13/045G06K9/62
CPCG01M13/00G01M13/045G06F18/241G06F18/214
Inventor 刘志亮康金龙孙文君左明健
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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