Unlock instant, AI-driven research and patent intelligence for your innovation.

Machine Intelligence Fault Diagnosis Method Based on Signal Resolution Enhancement

A technology of resolution enhancement and machine intelligence, which is applied in the field of machine intelligence fault diagnosis based on signal resolution enhancement, can solve the problem of not being able to improve the resolution of a single sample, and achieve the effect of enhancing effectiveness

Active Publication Date: 2022-03-04
JINING AVOVE ELECTRONICS TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above methods cannot improve the resolution of individual samples

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
  • Machine Intelligence Fault Diagnosis Method Based on Signal Resolution Enhancement
  • Machine Intelligence Fault Diagnosis Method Based on Signal Resolution Enhancement
  • Machine Intelligence Fault Diagnosis Method Based on Signal Resolution Enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0038] The network structure of ESPCN is as follows: figure 1 shown. ESPCN is mainly composed of convolutional neural network and sub-pixel convolutional layer. It uses L-channel convolutional neural network to generate low-resolution images, and then uses sub-pixel convolutional layer to sample low-resolution images to generate high-resolution images. The first L-1 channel of a convolutional neural network is described as follows:

[0039]

[0040] Autoencoder (AE) is the basic unit of SAE, which is mainly used for feature extraction and dimensionality reduction of data. Such as figure 2 As shown, the structure of AE is a three-layer feed-forward neural network, including data input layer, hidden layer and output layer. AE is divided into two parts, the encoder part and the decoder part. The encoder is used to map...

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 mechanical intelligent fault diagnosis method based on signal resolution enhancement and relates to the field of mechanical fault diagnosis. The machine intelligence fault diagnosis method based on signal resolution enhancement performs full connection operation on the original input samples, and outputs four-channel low-resolution features through hidden layer feature mapping; through sub-pixel fully connected layers, the four-channel low-resolution features Periodically arranged, a set of high-resolution features is finally obtained, and then the sample resolution is enhanced. Finally, a set of special bearing experiments are set up to evaluate the performance of the generative model. The experimental results verify the effectiveness of the ESPFCN framework and demonstrate the feature learning process of ESPFCN through visualization.

Description

technical field [0001] The invention relates to the field of mechanical fault diagnosis, in particular to a mechanical intelligent fault diagnosis method based on signal resolution enhancement. Background technique [0002] In modern industry, the traditional machinery industry is rapidly transforming into automation and intelligence. In order to ensure the normal operation of the machine, various intelligent fault diagnosis methods emerge in endlessly. Lei Yaguo and others designed a multi-layer stacked DAE, and added noise to the frequency domain signal, thus realizing the intelligent fault diagnosis of the gearbox. Fan Wei et al. designed a bearing fault diagnosis system based on wavelet-based sparse signal feature extraction to realize the effective extraction of weak characteristic vibration signals of bearings under strong background noise. In order to improve the efficiency of model training and at the same time solve the problem of gradient disappearance in the tra...

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 Patents(China)
IPC IPC(8): G01M13/045G06K9/62G06N3/04G06N3/08G06V10/762G06V10/764G06V10/82
CPCG01M13/045G06N3/08G06N3/045G06F18/23G06F18/2415
Inventor 王晓玉王金瑞季珊珊闫振豪贾思祥
Owner JINING AVOVE ELECTRONICS TECH CO LTD