Rolling bearing fault diagnosis method based on multi-scale convolutional neural network

A convolutional neural network and rolling bearing technology, applied in the field of intelligent fault diagnosis, can solve problems such as difficulty in being satisfied, and achieve the effect of reducing influence and dependence

Pending Publication Date: 2021-08-17
国家能源集团宿迁发电有限公司 +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the construction of intelligent diagnostic models requires a large number of training samples covering various operating conditions, which is difficult to meet in practical engineering applications
Therefore, traditional diagnostic methods face great challenges in industrial applications

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
  • Rolling bearing fault diagnosis method based on multi-scale convolutional neural network
  • Rolling bearing fault diagnosis method based on multi-scale convolutional neural network
  • Rolling bearing fault diagnosis method based on multi-scale convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The specific embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0038] Step 1: Decompose the original vibration signal into eigenmode components by adaptive variational mode decomposition, the specific steps are as follows:

[0039] Step 11: Obtain the original vibration signal: use the sensor to measure the original vibration signal,

[0040] Step 12: Let the number of initialized modal components K=2;

[0041] Step 13: The original vibration signal is iteratively calculated by the alternating multiplier method until convergence:

[0042]

[0043]

[0044] in is the original vibration signal; is the kth eigenmode component decomposed after n iterations; is the ith eigenmode component before the nth iteration; is the Lagrangian multiplier, which can be a constant 0; and are the k-th center frequency after the nth iteration and before the iteration respectively; ω is the angular frequency;

[...

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 rolling bearing fault diagnosis method based on a multi-scale convolutional neural network. The method comprises the following steps: decomposing an original vibration signal into intrinsic mode components through adaptive variational mode decomposition; performing envelope demodulation on the intrinsic mode component through an energy operator to calculate an envelope signal of the intrinsic mode component; calculating an envelope order spectrum of an envelope signal through angular domain resampling and Fourier transform, calculating envelope kurtosis of the envelope order spectrum, selecting a component with the maximum envelope kurtosis as an effective component, and learning a mapping relation between the envelope order spectrum of the effective component and a fault category through a multi-scale convolutional neural network to accurately identify the health state of the fan rolling bearing. The rolling bearing fault diagnosis method method has the advantages of being high in identification precision and small in sample dependence, and can be effectively applied to intelligent fault diagnosis of the fan rolling bearing under the variable working conditions only according to the historical monitoring data training model under the single working condition.

Description

technical field [0001] The invention relates to the technical field of intelligent fault diagnosis, in particular to a rolling bearing fault diagnosis method based on a multi-scale convolutional neural network. Background technique [0002] Fans are one of the most important auxiliary machines in thermal power plants. Accurate monitoring and evaluation of their health status is of great significance for improving the safety and economy of thermal power generation. Affected by factors such as harsh working environment and complex operating conditions, it is difficult to effectively extract and identify the fault characteristics of key components such as rolling bearings, which seriously affects the reliability of power production. It has become an urgent task for the thermal power industry to effectively evaluate the running state of the rolling bearing of the wind turbine, give early warning of failures, and avoid major failures. [0003] With the development of artificial ...

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): G06K9/62G06K9/00G06N3/04G06N3/08G01M13/045
CPCG06N3/08G01M13/045G06N3/047G06N3/048G06N3/045G06F2218/12G06F2218/08G06F18/2415G06F18/214
Inventor 周文宣王春许园许立环蒋坤周阳邓敏强邓艾东
Owner 国家能源集团宿迁发电有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products