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

Method for fault diagnosis based on power-average operator and DS evidence theory

A technology of evidence theory and fault diagnosis, applied in the field of fault diagnosis, can solve problems such as reduction, catastrophic accidents, loss of function, etc., and achieve the effect of simple calculation, realization of fault diagnosis, and realization of treatment

Active Publication Date: 2018-11-30
NORTHWESTERN POLYTECHNICAL UNIV
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the application of modern science and technology on equipment, the structure of the equipment is becoming more and more complex, the functions are becoming more and more perfect, and the degree of automation is getting higher and higher. Due to the influence of many unavoidable factors, various failures of the equipment will occur, thus Degradation or loss of intended function, or even serious or even catastrophic accidents

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
  • Method for fault diagnosis based on power-average operator and DS evidence theory
  • Method for fault diagnosis based on power-average operator and DS evidence theory
  • Method for fault diagnosis based on power-average operator and DS evidence theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with accompanying drawings and examples. An example of engine fault diagnosis is given here. The experimental data are as follows: figure 2 , image 3 and Figure 4 . Three states of the engine: "No fault: X 0 ", "Exhaust valve failure: X 1 " and "Piston ring failure: X 2 ". Data is collected using three sensors: an acceleration sensor and an acoustic sensor. An acceleration sensor is mounted on the cylinder head near the outlet valve and is marked S 1 ;Another acceleration sensor is mounted on the cylinder head near the intake valve, marked S 2 ;Acoustic sensor located directly above the cylinder head, marked S 3 . For acceleration signals, we compute their peak-to-peak (P-to-P) and frequency of maximum spectrum (F-max) in the time domain. For acoustic signals, we calculate the mean pressure level (MPL) and the center frequency (F-c) of the spectrum.

[0033] Step 1: The method of determini...

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 provides a method for fault diagnosis based on a power-average operator and a D-S evidence theory and relates to the field of fault diagnosis. An identification framework is generated according to a fault mode, and a power-average operator operation is performed on sample data to obtain a feature value; a basic probability distribution function is generated according to a Minkowski distance of the feature value between a to-be-tested model and a fault model, and the generated basic probability distribution function is fused through an evidence theory combination rule to achieve fault diagnosis. According to the method, the feature value is constructed using the power-average operator, and the influence of sample points having large measurement errors on the construction of the feature value is avoided. According to the method for generating the basic probability distribution function based on the evidence distance, the processing of fuzzy information is achieved well; andaccording to the method for fault diagnosis, fault diagnosis on a device can be achieved.

Description

technical field [0001] The invention relates to the field of fault diagnosis, and is a method for realizing fault diagnosis based on a power-average operator and DS evidence theory. Background technique [0002] Fault diagnosis technology is an engineering science that is closely combined with the actual production and is the product of the development of modern production. With the application of modern science and technology on equipment, the structure of the equipment is becoming more and more complex, the functions are becoming more and more perfect, and the degree of automation is getting higher and higher. Due to the influence of many unavoidable factors, various failures of the equipment will occur, thus Reduce or lose the intended function, and even cause serious or even catastrophic accidents. [0003] Fault diagnosis technology is to grasp the operating status of the equipment when the equipment is running or basically does not disassemble the equipment, analyze a...

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): G06F17/16G06F17/18G06K9/62G06Q10/06
CPCG06F17/16G06F17/18G06Q10/0639G06F18/25
Inventor 蒋雯刘海斌马泽宇邓鑫洋
Owner NORTHWESTERN POLYTECHNICAL UNIV