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

Selective integrated learning-based rotating machinery fault diagnosis method

An integrated learning and fault diagnosis technology, applied in neural learning methods, complex mathematical operations, computer components, etc., can solve problems such as data complexity of rotating machinery

Active Publication Date: 2017-07-25
BEIHANG UNIV
View PDF2 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of the complexity of rotating machinery data existing in the prior art, the present invention proposes a method for fault diagnosis of rotating machinery based on selective ensemble learning

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
  • Selective integrated learning-based rotating machinery fault diagnosis method
  • Selective integrated learning-based rotating machinery fault diagnosis method
  • Selective integrated learning-based rotating machinery fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] 1. Generation of base classifier

[0044]The present invention adopts probabilistic neural networks (PNN) as a base classifier to realize the recognition of the fault mode of the rotating machinery. PNN is a forward neural network based on Bayesian minimum risk criterion and nuclear Fisher discriminant, which was invented by D.F.Specht in 1990. Usually, the PNN network structure is as figure 1 shown.

[0045] exist figure 1 In, we can find that the PNN network can usually be divided into four layers: the input layer, the model layer, the accumulation layer and the output layer. When a test input signal is given to the network, the input layer will first calculate the distance between the data point in the signal and the training vector point; then, the pattern layer will use a radial basis function to convert the distance into Corresponding weight parameters; in the overlay layer, the weight parameters of each point in the input data for different failure modes will...

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 present invention discloses a selective integrated learning-based rotating machinery fault diagnosis method. The method comprises the steps of pre-processing a known input signal to obtain a training sequence; based on the Bagging algorithm, processing the training sequence to generate a series of differentiation-based learning machines; through the selective integrated learning process, giving a preference on the series of differentiation-based learning machines to obtain a well trained PSOSEN model; by utilizing the trained PSOSEN model, diagnosing a rotating machinery fault. The method solves the problem in the prior art that a classifier with better performances is difficult to be selected out of a series of classifiers can be solved.

Description

technical field [0001] The present invention relates to the field of fault diagnosis of rotating machinery, in particular to a method and device for identifying fault patterns of rotating machinery based on adaptive particle swarm optimization based selective ensemble learning (PSOSEN). Background technique [0002] Fault diagnosis technology is a device diagnosis technology that has emerged with the development of modern industrial mass production. It aims to grasp the operation of the device through signal processing and pattern recognition when the device is running or shutting down without disassembly. The status quo, determine the location, cause, severity and status of equipment failure, and then realize the prediction of equipment life and reliability, and provide effective reference for making maintenance decisions. In recent years, the research on fault diagnosis technology of rotating machinery represented by bearings, gearboxes and pumps has received more and more...

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): G06K9/00G06K9/62G06N3/08G06F17/14
CPCG06F17/148G06N3/084G06F2218/08G06F2218/12G06F18/214
Inventor 吕琛王振亚马剑周博
Owner BEIHANG UNIV
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