Bearing fault signal enhancement method and system

Abstract

The invention relates to a bearing fault signal enhancement method and system. The method comprises the steps of presetting a particle population, initializing a parameter of a particle swarm, collecting a primary fault signal, and preprocessing the primary fault signal into an envelope demodulation signal; receiving the envelope demodulation signal to trigger stochastic resonance, calculating according to a controlled system output data to obtain fitness data, updating individual extreme values and overall extreme values of all particles in the particle swarm and corresponding positions thereof according to the fitness data, and updating speeds and positions of the next generation of particles according to a speed and position calculation formula; obtaining iterative data of the particlepopulation, and judging whether iteration is stopped according to the iterative data of the particle population; if not, circulating the abovementioned steps; and if so, outputting an optimization parameter combination, triggering the stochastic resonance according to the optimization parameter combination to obtain enhancement data, and analyzing the enhancement data. With the bearing fault signal enhancement method and system, the technical problems in the prior art that the resonance effect is not obvious, the parameter is dependent on manual selection and the signal enhancement effect is poor are solved.

Description

technical field [0001] The invention relates to a mechanical fault signal processing method, in particular to a bearing fault signal enhancement classification method and system. Background technique [0002] The stochastic resonance signal enhancement method uses the nonlinear vibration theory to convert the random noise energy in the signal into the energy of a specific signal, so as to achieve the purpose of enhancing the signal strength and performing effective detection. [0003] In recent years, scholars at home and abroad have carried out a series of research on the theoretical method of stochastic resonance signal enhancement. The stochastic resonance method of a bistable system coupled with a single input signal does not guarantee that both the control system and the controlled system can achieve stochastic resonance. In the existing technology, Hilbert transform and high-pass filter preprocessing are performed on the fault vibration signal, and then the obtained s...

AI Technical Summary

Problems solved by technology

However, it needs to rely on the auxiliary processing of the high-pass filter, and the filter parameters need to be selected subjectively. If the parameters are not selected properly, it is difficult to achieve the expected effect

[0004] To sum up, the prior art fault signal enhancement method has the technical problems of insignificant resonance effect, parameter dependent selection and poor signal enhancement effect.

Images