Method for diagnosing faults of bearings on basis of extreme learning machines

Abstract

The invention provides a method for diagnosing faults of bearings on the basis of extreme learning machines, and belongs to the field of technologies for diagnosing mechanical faults. The method includes carrying out variation mode decomposition on vibration acceleration signals to obtain IMF (intrinsic mode function) mode components; acquiring singular values of the IMF mode components by the aid of singular value decomposition (SVD) algorithms; dividing the singular values of each IMF mode component into a training sample and a test sample; utilizing the singular values of the training samples as input values of extreme learning machine (ELM) neural network models and determining input connection weights, offset values and optimal output connection weights of the ELM neural network models; utilizing the singular values of the test samples as input values of the ELM neural network models with the determined input connection weights, the determined offset values and the determined optimal output connection weights and acquiring output results which are bearing fault diagnosis results. The method has the advantages that the signals can be accurately effectively separated, component signal modes are fast in convergence and high in robustness, and the method is high in fault recognition speed and accuracy; model building can be omitted, professional requirements can be lowered, and accordingly the method is suitable for industrial application.

Description

technical field [0001] The invention relates to the technical field of mechanical fault diagnosis, in particular to a bearing fault diagnosis method based on an extreme learning machine. Background technique [0002] Rolling bearings have a prominent feature that their life spans are very large. It is very unscientific to perform regular maintenance on bearings only rigidly according to the design life. During the use of bearings, monitoring of working conditions and identification of faults should be carried out at any time. In this way, it can not only prevent the equipment from falling in accuracy and reduce the probability of accidents, but also maximize the working potential of the bearings and save money. [0003] For slightly damaged bearings, the real cause of failure can be deduced from signs of use, especially the wear condition and wear track of the bearing working surface. Seriously damaged bearings are completely scrapped due to unexpected accidents. The fina...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a bearing fault diagnosis method based on an extreme learning machine that can accurately realize effective separation of signals, fast fault identification, high accuracy, no need to build a model, and fast and convenient diagnosis, so as to solve the problems described in the background technology above. Establish a diagnostic model to diagnose problems that are not timely and accurate

Images