Failure prediction method of roller bearing based on partial least squares extreme learning machine

Abstract

The invention relates to a failure prediction method of a roller bearing based on a partial least squares extreme learning machine. The method herein includes: analyzing feature indexes, such as timedomain, frequency domain and time-frequency domain, providing a feature extraction method based on the combination of half-normal distribution and empirical wavelet denoising to perform failure diagnosis on a roller bearing so as to obtain better denoising effect owing to proximity to original signals; for multi-feature parameters, comprehensively evaluating failure attenuation features of the roller bearing, and providing a method with the combination of residual-modified ISOMAP (isometric feature mapping) nonlinear feature dimension reduction and fuzzy C-means, so that change tendency and sorting precision are improved for the roller bearing in different attenuation stages; based on the extreme learning machine theory, providing a data prediction model based on a partial least squares extreme learning machine, optimizing parameters in the ELM (extreme learning machine), selecting node quantity of an optimal hidden layer and weight value of a connection layer, and selecting a Softmaxactivation function. Therefore, prediction precision is high, calculating time is short, and post-clustering feature value detection is effective. The failure stage of the roller bearing can be precisely predicted via the above steps.

Description

technical field [0001] The invention belongs to the research field of fault prediction methods for rotating machinery, and specifically relates to data noise reduction based on the combination of half-normal distribution and EWT, and a method for dimensionality reduction processing of nonlinear signals by using fuzzy C-means combined with equidistant mapping technology. Background technique [0002] Due to its large-scale, high complexity, multi-variable, and closed-loop control characteristics, modern industrial equipment will have many unpreventable factors that lead to equipment failure. Therefore, a series of catastrophic accidents caused by the loss of equipment function are not uncommon. People have also gradually realized that the status detection and fault prediction of equipment play a vital role in ensuring the safe and reliable operation of the unit and preventing accidents. Rolling bearings are one of the important parts of rotating machinery, and the stability ...

AI Technical Summary

Problems solved by technology

[0007] One of the main means of realizing the health maintenance of mechanical equipment is to predict and evaluate the failure changes of mechanical equipment, mainly based on the prediction method of failure physical model, using the life cycle load and failure mechanism knowledge of the product to evaluate its reliability, which can be used in some Under certain circumstances, it is not necessary to establish a dynamic model, which will be time-consuming and labor-intensive; based on statistical forecasting methods, the required information comes from various probability density functions, and the confidence interval can objectively describe the accuracy of the forecast, but the appropriate regression equation type sometimes hard to find

Images