Bearing fault diagnosis method based on data-driven and stochastic intuitionistic fuzzy strategy

Abstract

The invention discloses a bearing fault diagnosis method based on a data driving and random intuitive fuzzy strategy. The method comprises the following steps that (1) a massive data idea is used for building a fuzzy expert system, and data driving is realized; (2) the fault feature membership degree of a bearing to be inspected is built; (3) random fuzzy set matching and intuitive fuzzy decision fusion are carried out. According to the bearing fault diagnosis method, mass experiment data is used as the basis, the frequency spectrum analysis is carried out, and the feature frequency is found through the amplitude value occurring position. In addition, the fuzzy evidence is fused and converted into the random fuzzy set matching and intuitive fuzzy set decision. The uncertainty information is a part of energy of frequency spectrum information, and the objectiveness is lost when the evidence theory is directly omitted. The energy loss is sufficiently considered by the intuitive fuzzy strategy.

Description

technical field [0001] The invention relates to a bearing fault diagnosis method based on data-driven and random intuition fuzzy strategy. Background technique [0002] The types of bearing faults are nothing more than four faults of inner ring, outer ring, rolling element and cage. [0003] 1. Traditional bearing fault characteristic frequency calculation [0004] (1) Calculate the vibration characteristic frequency of the inner ring, outer ring, drum body, cage, etc. according to the characteristic parameters of the bearing. The formula is as follows: [0005] Outer ring failure: [0006] Inner race failure: [0007] Rolling element failure: [0008] Cage contact outer ring failure: [0009] Cage contact inner ring failure: [0010] where f r - bearing rotation frequency; z - number of rollers; d 1 —Rolling element diameter; D 1 —Bearing pitch diameter; α—bearing pressure angle. [0011] After the characteristic frequency is obtained, the frequency spec...

AI Technical Summary

Problems solved by technology

[0016] (2) There are incompleteness and ambiguity in the expert system

[0017] The fault diagnosis expert system established by experimental means cannot contain all fault types, and in each of the existing fault types, due to changes in the time, place, occasion and operating environment of the equipment measured by the sensor, as well as the drift of the sensor and other There are many uncertainties in the measured equipment operation information due to human factors, especially fuzziness

[0018] (3) The feature extraction of bearing faults to be inspected is also ambiguous due to the factors in (2)

[0019] (4) The largest problem of fuzzy evidence fusion, ignoring the uncertainty probability

But there may be 1 or 2 people who do not take a stand, or even abstain

Images