Blind deconvolution algorithm for enhancing rotating machinery fault signal features

Abstract

The invention relates to a blind deconvolution algorithm for enhancing rotating machinery fault signal features, and the algorithm comprises the following steps: S1, constructing a plurality of cascaded FIR filters, determining the maximization criterion of the blind deconvolution algorithm according to the features of original vibration signals, and taking the maximization criterion as a target function; S2, performing convolution operation on the original vibration signals in sequence by using a cascaded FIR filter to obtain filtered signals, and calculating an objective function value of the filtered signals; S3, calculating the gradient of the target function value to the filter under the current iteration number by adopting a backward automatic differential algorithm; S4, updating the values of all filters; and S5, repeating the steps S2-S4, and outputting a final filtered signal after the maximum number of iterations is reached. The technical problem that the rotating machine fault diagnosis precision is not high due to the fact that iteration algorithms of different blind deconvolution algorithms cannot be universal and the blind deconvolution algorithms are poor in performance is solved.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis calculation of rotating machinery based on deep learning, in particular to a blind deconvolution algorithm for enhancing the characteristics of fault signals of rotating machinery. Background technique [0002] Gearboxes and bearings are critical components of rotating machinery, and their failure is the most common cause of mechanical failure. In order to reduce potential safety hazards and ensure the normal operation of equipment, it is particularly important to monitor the condition of components such as gearboxes and bearings of rotating machinery. After a gearbox or bearing fault develops, a transient pulse will be generated that will be periodic. However, due to the influence of the transmission path and environmental noise, the fault pulse of the signal collected by the vibration sensor is greatly attenuated, which brings great obstacles to the fault analysis. [0003] Blind decon...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the present invention provides a blind deconvolution algorithm that enhances the characteristics of f

Images