Bearing fault signal detection method and system based on whale algorithm

Abstract

The invention discloses a bearing fault signal detection method and system based on a whale algorithm, and the method is based on a bistable stochastic resonance system model, and optimizes the structural parameters of bistable stochastic resonance through a self-adaptive whale algorithm, thereby enabling a fault signal to be enhanced, and achieving the detection of a bearing fault signal. The method is verified by using an actual bearing fault signal, and a series of contrast experiments are carried out. The result shows that the method is simple in model, few in algorithm parameters, high in convergence speed, large in stochastic resonance system output signal-to-noise ratio and high in local optimum jumping-out capacity, and bearing fault signal detection can be accurately and efficiently achieved.

Description

technical field [0001] The invention belongs to the technical field of bearing fault signal detection, and in particular relates to a bearing fault signal detection method and system based on a whale algorithm. Background technique [0002] The core of many weak signal detection methods is to detect weak signals by suppressing noise. However, in the process of suppressing noise, weak signals are usually damaged and the detection accuracy is affected. In 1981, scholars such as Benzi proposed the concept of stochastic resonance when they studied ancient glacier meteorology. Since then, the stochastic resonance theory has received extensive attention in many fields. The stochastic resonance method is a nonlinear weak signal detection method. Compared with other detection methods, its advantage is that part of the noise energy is superimposed on the signal. When the input and output signals of the system are synchronized, the detection of weak signals can be enhanced. [0003]...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems existing in the prior art, the present invention provides a bearing fault signal detection method and system based on the whale algorithm. The method uses the stochastic resonance principle to increase the accuracy of the bearing fault signal detection, and uses the whale optimization algorithm to solve the problem of stochastic resonance parameters. choose a difficult problem

Images