Performance degradation evaluation method of rolling bearing on the basis of FOA-WSVDD (Fruit fly Optimization Algorithm-Wavelet Support Vector Data Description)

Abstract

The invention discloses a performance degradation evaluation method of a rolling bearing on the basis of FOA-WSVDD (Fruit fly Optimization Algorithm-Wavelet Support Vector Data Description). The method is characterized in comprising the following steps that: firstly, extracting the feature vectors of the time domain and the time-frequency domain of bearing vibration data, and carrying out featureselection on the basis of monotonicity; then, utilizing a normal state feature vector to establish a performance degradation evaluation model; importing a wavelet kernel function into an SVDD (SupportVector Data Description) algorithm by aiming at a problem that a Gaussian kernel function is not sensitive to early failures; by aiming at a problem that the SVDD algorithm is difficult in selectingparameters, taking the specific value of the number of support vectors and a total sample number as a fitness function, optimizing the nuclear parameter of the fitness function by an improved FOA, andestablishing an FOA-WSVDD evaluation model; and finally, calculating the evaluation index of the full life circle vibration data of the bearing so as to evaluate the performance degradation situationof the bearing. Compared with an SVDD performance degradation evaluation model established on the basis of the Gaussian kernel function, a performance degradation evaluation model of the rolling bearing on the basis of the FOA-WSVDD is more sensitive to the early failures of the bearing, exhibits better monotonicity with a failure degree and accurately reflects the health state of the bearing.

Description

technical field [0001] The invention belongs to the technical field of bearing performance degradation evaluation, and in particular relates to a rolling bearing performance degradation evaluation method based on FOA-WSVDD (Fruitfly Optimization Algorithm-Wavelet support vector data description). Background technique [0002] With the continuous improvement of industry and technology, mechanical equipment is constantly improving in terms of complexity, efficiency, and lightness, and it is also facing a more demanding working environment. Once a key component of the equipment fails, it may affect the entire production process, causing huge economic losses, and even causing casualties and other problems. Therefore, equipment maintenance is changing from traditional post-event maintenance and planned maintenance to condition-based maintenance. As a prerequisite for establishing a reasonable maintenance strategy, equipment performance degradation assessment has also begun to att...

AI Technical Summary

Problems solved by technology

However, when the data has a multimodal distribution, its accuracy will be greatly affected, and it cannot reflect the local information of the signal

Images