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

Fault feature parameter selection method based on fuzzy preference relationship and adaptive hierarchical clustering

A technology of fault characteristic parameters and preference relationship, applied in the field of big data processing, can solve the problems of no uniform standard for end conditions and large amount of calculation, and achieve the effect of avoiding dimension disaster, reducing feature dimension and improving efficiency.

Active Publication Date: 2020-11-06
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Hierarchical clustering algorithm is an unsupervised classification algorithm, which is suitable for clustering data sets of any shape. It does not need to determine parameters such as cluster center and number of clusters in advance, but there is no uniform standard for the end condition, and corresponding thresholds still need to be set. Large amount of calculation

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 feature parameter selection method based on fuzzy preference relationship and adaptive hierarchical clustering
  • Fault feature parameter selection method based on fuzzy preference relationship and adaptive hierarchical clustering
  • Fault feature parameter selection method based on fuzzy preference relationship and adaptive hierarchical clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] like figure 1 , image 3 shown.

[0046] A fault characteristic parameter selection method based on fuzzy preference relationship and adaptive hierarchical clustering, comprising the following steps:

[0047] 1) Calculation of fuzzy preference relationship

[0048] 1.1) Given a system S=, where X={x 1 , x 2 ,...,x N} represents the sample set, Q={q 1 ,q 2 ,...,q J} is the feature set, U={u 1 , u 2 ,...,u C} is the failure set;

[0049] x K ∈X, with respect to q l The fuzzy preference relation of ∈Q is:

[0050]

[0051] Among them, q i1 ,q j1 ∈Q; i≠j; k is the number of clusters;

[0052] Depend on figure 2 It can be seen that d ij (q)=d ji (q), when i=j, d ij (q)=0.5, with the increase of |Δq|, d ij (q) increases continuously from 0.5, when q i，l >>q j，l when d ij (q)→1. Therefore, in feature selection, as long as the size of the difference between the two features is represented, there is no need to describe q in detail i，l is greater ...

Embodiment 2

[0077] like Figure 4 shown.

[0078] Using the method described in Example 1 to perform fault diagnosis and determine the fault type of the bearing simulation system, the steps are as follows:

[0079] Use the vibration sensor to collect 4 states of the bearing simulation system: normal state, outer ring fault, inner ring fault, rolling element fault;

[0080] serial number Operating status status flag 1 normal 0 2 Outer ring failure 1 3 Inner ring failure 2 4 rolling element failure 3

[0081] A1) Feature extraction

[0082] Extract the time-domain features and frequency-domain features of the original vibration signal, the IMF component features of EEMD decomposition and the energy of sub-bands after wavelet packet decomposition to form a feature set;

[0083] A1.1) Temporal features

[0084] mean: Standard Deviation:

[0085] RMS: Peak-to-peak value: F p =max|x(n)|;

[0086] Waveform indicators: Pulse factor: ...

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 fault feature parameter selection method based on a fuzzy preference relationship and adaptive hierarchical clustering. According to the method, adaptive hierarchical clustering based on a fuzzy relation is provided based on a logsig function and is applied to fault diagnosis of equipment; sensitive features are calculated and selected based on the fuzzy relation, prioriknowledge is not needed, and the intelligence of the method is improved; the optimized features are used, so that a feature set is simplified, dimensionality disasters are avoided, the calculation burden is reduced, and the fault diagnosis efficiency is improved; and the adaptive hierarchical clustering combined with feature optimization has relatively high diagnosis precision.

Description

technical field [0001] The invention relates to a fault characteristic parameter selection method based on fuzzy preference relationship and self-adaptive hierarchical clustering, which belongs to the technical field of big data processing. Background technique [0002] With the development of science and technology, large-scale equipment is becoming more and more complex, and the cooperation between components is getting closer and closer. The failure of components may cause downtime losses, resulting in large economic losses, and even endanger personal safety in severe cases. In addition, if the fault cannot be accurately located, blind repairs will cause accuracy errors and reduced reliability. Therefore, fault diagnosis technology is the premise to ensure the safe and stable operation of the equipment, and it is also very important to the maintenance of the equipment. [0003] Due to many measuring points, many monitoring parameters (force, temperature, vibration, sound...

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): G06K9/62G06F17/16G06F17/18
CPCG06F17/16G06F17/18G06F18/231G06F18/24137
Inventor 郝慧娟程广河唐勇伟郝凤琦李娟
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN