Equipment fault diagnosis method based on improved 1DCNN-BiLSTM

A diagnostic method, a technology for equipment failure, applied in neural learning methods, testing of mechanical components, recognition of patterns in signals, etc., to achieve the effect of reducing interference

Pending Publication Date: 2021-12-21
HEBEI UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the problem of signal mixed with strong noise, improv

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
  • Equipment fault diagnosis method based on improved 1DCNN-BiLSTM
  • Equipment fault diagnosis method based on improved 1DCNN-BiLSTM
  • Equipment fault diagnosis method based on improved 1DCNN-BiLSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0076] The present invention uses industrial mechanical equipment fault diagnosis as the carrier, and uses LSTM and CNN algorithms as the main algorithm framework, and its model is as follows: figure 1 shown. The feature extraction module designs 1DCNN-BiLSTM dual-model channels, which are BiLSTM single-model channel and 1DCNN single-model channel. Among them, Channel1 is the Stacked Bi-LSTM neural network model, adjust the number of memory units of the BiLSTM network and the number of layers of the neural network, and realize the extraction of signal features of different dimensions; Channel4 is set as a 1DCNN model, and adjust the number of convolution kernels to realize different scales of signals Feature extraction; Channel2 and Channel3 add the improved SENet module on the basis of Channel1 and Channel4 respectively to perform ...

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 an equipment fault diagnosis method based on an improved 1DCNN-BiLSTM, and the method comprises the following steps: S1, preprocessing an original vibration acceleration signal by a self-adaptive white noise complete empirical mode decomposition (CEEMDAN) technology, and taking the preprocessed signal as input of a model; S2, constructing a 1DCNN-BiLSTM dual-channel model, inputting the preprocessed signal into two channels of a bidirectional LSTM model and a one-dimensional CNN model, and fully extracting the time sequence correlation characteristics of the signal, the non-correlation characteristics of the local space and the weak periodicity rule; S3, improving a SENet module and acting on two different model channels aiming at the problem that the signal is mixed with strong noise; and S4, fusing the two-channel extraction characteristics in a full connection layer, and realizing accurate identification of equipment faults by means of a Softmax classifier. To solve the problems of time sequence and noise inclusion of fault data in the industrial field, filtering and denoising preprocessing is carried out on original signals, a 1DCNN-BiLSTM dual-channel feature extraction module is constructed, a modified SENet module is integrated to realize weighting of feature channels, and the fault diagnosis efficiency of mechanical equipment is effectively improved.

Description

technical field [0001] The invention relates to the technical field of industrial equipment fault diagnosis and deep learning model construction, in particular to an equipment fault diagnosis method based on improved 1DCNN-BiLSTM. Background technique [0002] With the rapid development of modern industry, the mechanical equipment in the "smart factory" is also developing vigorously in the direction of integration and complexity. Rolling bearings are one of the widely used parts in rotating machines. With the continuous operation of mechanical equipment, various failures of bearings are inevitable. According to statistics, among the faults of rotating machinery, the fault of bearing damage accounts for about 30%. The causes of failures are often complex and diverse. Condition monitoring and fault diagnosis of rolling bearings are important contents of fault diagnosis technology for mechanical equipment. Therefore, the fault diagnosis of mechanical equipment bearings is of ...

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): G06K9/00G06N3/04G06N3/08G01M13/045
CPCG06N3/08G01M13/045G06N3/044G06F2218/04G06F2218/08G06F2218/12Y02T90/00
Inventor 刘晶孙跃华季海鹏周鹏飞
Owner HEBEI UNIV OF TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap