Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Fault diagnosis of rotating machinery based on one-dimensional depth residual convolution neural network

A technology of convolutional neural network and rotating machinery, applied to biological neural network models, neural architectures, computer components, etc., can solve problems such as difficult to learn features, easy to cause misjudgment, poor domain adaptability, etc., and achieve improved feature The effect on learning ability

Active Publication Date: 2019-02-01
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional intelligent fault diagnosis methods have the following disadvantages: 1) The diagnostic performance depends on the design of the feature extraction method by domain experts, and for each specific diagnostic task, the feature extraction method must be redesigned, so it is time-consuming and labor-intensive; 2 ) Manually extracted features cannot guarantee to fully represent the complex dynamic characteristics of rotating machinery; 3) Fault identification methods such as support vector machines, k-nearest neighbors, random forests, and naive Bayes all use shallow learning models, which are difficult Learn enough features to easily cause misjudgment
However, the published related methods almost all have the problems of low accuracy and poor domain adaptability under complex working conditions

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 of rotating machinery based on one-dimensional depth residual convolution neural network
  • Fault diagnosis of rotating machinery based on one-dimensional depth residual convolution neural network
  • Fault diagnosis of rotating machinery based on one-dimensional depth residual convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0050] ReLU(Rectified Liner Units): corrected linear unit;

[0051] BN (Batch Normalization): batch normalization.

[0052] figure 1 It is a flow chart of a method for diagnosing a rotating machinery fault based on a one-dimensional deep residual convolutional neural network in the present invention.

[0053] In this example, if figure 1 As shown, the present invention is based on a one-dimensional deep residual convolutional neural network fault diagnosis method for rotating machinery, comprising the following steps:

[0054] S1. Acquisition of vibration signals of rotating machinery

[0055] Acquisition of rotating machinery with different faults at a sampling frequency f s Acceleration vibration signals x[n] at 9 o'clock and 12 o'clock under different operating speeds, different vertical loads and axial loads m , to obtain the acceler...

example

[0080] In this implementation case, relying on a certain bearing test bench, such as Figure 7 shown. The specific relevant information is as follows:

[0081] The wheel set bearing fault diagnosis test bench is composed of a driving motor, a belt drive system, a vertical loading device, a lateral loading device, two fan motors and a control system. The vertical and lateral load loading device is designed to simulate the axial and lateral loads carried by the wheel set bearings in actual train operation. Two fan motors can generate wind that is opposite to the train running direction. Two accelerometers are used to ensure that the vibration of the wheel set bearing in the horizontal direction and vertical direction can be detected, and the signal acquisition frequency is set to 5120Hz.

[0082] We machined bearings in 12 different health conditions. Table 1 lists the specific information of 12 kinds of faults, where the labels are respectively C1, C2, C3, ..., C12. In ord...

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 rotating machinery fault diagnosis method based on a one-dimensional depth residual convolution neural network. Firstly, the network learns more deep and abstract fault characteristics of training samples through a stacked one-dimensional residual module. Then, the Adam optimization algorithm is used to optimize all the super-parameters to complete the deep-level featureextraction and fault classification, and the rotating machinery fault diagnosis system model based on one-dimensional depth residual convolution neural network is obtained. Finally, the test samples are inputted into the trained fault diagnosis model, and the deep-seated features are extracted automatically to diagnose the health status of the rotating machinery.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of rotating machinery, and more specifically, relates to a fault diagnosis method of rotating machinery based on a one-dimensional deep residual convolutional neural network. Background technique [0002] Rotating machinery is the most widely used component in industrial equipment. Once a failure occurs, it will inevitably lead to equipment failure, resulting in economic losses and even safety accidents. Therefore, it is of great significance to carry out fault diagnosis on rotating machinery. [0003] Traditional intelligent fault diagnosis methods mainly include data acquisition, feature extraction and fault identification. Among them, feature extraction and fault identification are the two most important steps, which have a direct impact on the accuracy of fault diagnosis results. However, traditional intelligent fault diagnosis methods have the following disadvantages: 1) The diagnos...

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): G06K9/00G06K9/62G06N3/04
CPCG06N3/045G06F2218/08G06F18/214G06F18/24
Inventor 刘志亮彭丹丹王欢
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products