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

A Method and Application of Fault Diagnosis Model Construction for Rotating Parts

A fault diagnosis model, a technology of rotating parts, applied in computer parts, character and pattern recognition, and pattern recognition in signals, etc., can solve problems such as poor fault diagnosis accuracy and generality, and achieve improved accuracy and good generality. , the effect of high accuracy

Active Publication Date: 2022-05-20
HUAZHONG UNIV OF SCI & TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a method for constructing a fault diagnosis model of rotating parts and its application to solve the technical problems of poor accuracy and versatility of fault diagnosis of rotating parts existing in the prior art

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
  • A Method and Application of Fault Diagnosis Model Construction for Rotating Parts
  • A Method and Application of Fault Diagnosis Model Construction for Rotating Parts
  • A Method and Application of Fault Diagnosis Model Construction for Rotating Parts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A method for constructing a fault diagnosis model for motor bearings, including the following steps:

[0047] S1. The vibration data segment of n-segment is selected as the sample signal in the vibration data of the acquired motor bearing in different states, and the sample set is constituted; where n is a positive integer;

[0048]Specifically, the length of the n-segment randomly selected from the motor bearings collected from the present embodiment in different states is N in The vibration data segment is used as a sample signal; the vibration data of motor bearings published by Casey Western Reserve University is used as the vibration data set. The vibration signal is collected from the motor drive end of the test set under four fault conditions: normal, outer ring fault (OF), inner ring fault (IF) and ball fault (RF). For the three fault conditions of outer ring fault, inner ring fault and ball fault, vibration signals with fault radii of 0.18 mm, 0.36 mm and 0.53 mm w...

Embodiment 2

[0072] A method for diagnosing motor bearing faults, including:

[0073] The vibration data of the motor bearing in its current state is input to the motor bearing fault diagnosis model constructed using the motor bearing fault diagnosis model provided in Example 1 of the present invention, and the motor bearing fault condition is obtained.

[0074] The relevant technical solution is the same as Example 1, which will not be repeated here.

Embodiment 3

[0076] A machine-readable storage medium, the machine-readable storage medium stores machine-executable instructions, the machine-executable instructions are invoked and executed by the processor, the machine-executable instructions prompt the processor to implement the motor bearing fault diagnosis model construction method as described in Example 1 and / or motor bearing fault diagnosis method as described in Example 2.

[0077] The relevant technical solution with Example 1 and Example 2, which is not described here.

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 method for constructing a fault diagnosis model of a rotating part and its application, including: S1, selecting n segments of vibration data from the collected vibration data of the rotating part in different states as sample signals to form a sample set; S2, Use the sample set to train the sparse filtering model, and input each sample signal in the sample set into the trained sparse filtering model, and the obtained result is processed by the activation function to obtain the learning characteristics of each sample signal; S3. One-to-one correspondence between the learning features of the corresponding rotating parts and the health status of the corresponding rotating parts constitutes a training sample set; S4. Input the training sample set into the machine learning model for training to obtain a fault diagnosis model of the rotating parts. The present invention uses a sparse filtering model to carry out unsupervised learning of features, which has low dependence on prior knowledge and manual work, and only needs to adjust one hyperparameter in the process of feature learning, the effect of feature learning is better, and the accuracy of fault diagnosis is improved. higher.

Description

Technical field [0001] The present invention belongs to the field of rotating equipment fault diagnosis, more particularly, relates to a rotating component fault diagnosis model construction method and application. Background [0002] In modern industry, machines are more automated, precise and efficient than ever before, which makes monitoring their health more difficult. Among the many mechanical equipment, rotating equipment occupies a pivotal role in many fields, and once it fails, it will cause huge losses. As a key general component widely used in rotating equipment, whether rolling bearings, gears and other rotating components can operate safely and reliably is largely related to the safe use of the entire rotating equipment. [0003] Traditionally, the framework for intelligent troubleshooting has consisted of three main steps: 1) signal acquisition; 2) feature extraction and selection; and 3) fault classification. Traditional fault diagnosis methods are manually selected...

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): G06K9/00G06K9/62
CPCG06F2218/04G06F2218/08G06F2218/12G06F18/214Y02T90/00
Inventor 孙伟王昊文
Owner HUAZHONG UNIV OF SCI & TECH