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

Combined convolutional neural network diagnosis method for rotating machine fault

A convolutional neural network and rotating machinery technology, applied in neural learning methods, biological neural network models, neural architectures, etc., to achieve good diagnostic performance and good data adaptability

Pending Publication Date: 2022-04-22
ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the use of one-dimensional convolutional neural network to directly process the original signal, due to the limitation of information utilization ability, is either only us

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
  • Combined convolutional neural network diagnosis method for rotating machine fault
  • Combined convolutional neural network diagnosis method for rotating machine fault
  • Combined convolutional neural network diagnosis method for rotating machine fault

Examples

Experimental program
Comparison scheme
Effect test
No Example Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a combined convolutional neural network diagnosis method for rotating machine faults. The method comprises the steps of data acquisition, data preprocessing, 1D-2D JCNN model construction, model training, verification, diagnosis and the like. According to the method, the multi-scale feature vectors of the signals are acquired more clearly by using one-dimensional convolution in a self-adaptive manner for the vibration signals acquired in different states, the feature vectors are constructed into two-dimensional vectors, and the two-dimensional vectors are used as the input of a two-dimensional convolutional neural network. According to the invention, when the 1D-2D JCNN model is constructed, the two-dimensional structure expression of a signal is adaptively constructed by fully utilizing the one-dimensional convolutional neural network, and the strong feature learning capability of the two-dimensional convolutional neural network is utilized, so that the two convolutional neural networks with different structures are unified into an integral framework; and developing a combined convolutional neural network model for fault diagnosis of the rotating machinery.

Description

technical field [0001] The invention relates to a combined convolutional neural network diagnosis method for rotating machinery faults, and belongs to the technical field of rotating machinery intelligent fault diagnosis. Background technique [0002] Rotating machinery is widely used in all walks of life, and is developing towards precision and intelligence. Once the mechanical equipment breaks down, it will cause abnormal shutdown of the equipment, which will not only bring great property losses, but also may endanger people's lives. Fault diagnosis of rotating machinery has always been a hot topic of research by scholars. Since the vibration signal of the equipment carries a large amount of state information, a large number of research results have been obtained in the fault diagnosis technology based on data driven by using the vibration signal of the equipment. Generally speaking, this diagnostic technology requires several steps such as information collection, data p...

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
CPCG06N3/08G06N3/045G06F18/2433G06F18/214
Inventor 杜文辽王宏超李川胡鹏杰侯绪坤巩晓赟赵峰谢贵重孟凡念郭志强王良文
Owner ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
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