An intelligent fault diagnosis method for rotating machinery under time-varying speed

Abstract

The invention discloses a method for intelligent fault diagnosis of rotating machinery under time-varying rotational speed. By resampling the time-domain vibration signal of a rolling bearing in the angular domain, the non-stationary time-domain signal is converted into a stable angular-domain signal, which can eliminate the variation of the rotational speed. The impact on the analysis of vibration signals; the Gabor transform that can well describe the transient characteristics of the sharply changing signal is used for the speed estimation method based on time-spectrum ridge fitting; the keyless phase order tracking without installing the speed sensor is adopted The method can be applied to occasions where the speed sensor cannot be installed; the LSTM model that can adaptively extract time series features without expert experience and domain knowledge is used, and the existence of the BN generalization layer can speed up the convergence of the model and prevent overfitting and improve the model. Its generalization ability realizes self-adaptive intelligent fault diagnosis and identification of rotating machinery under variable speed conditions.

Description

technical field [0001] The invention relates to a mechanical fault diagnosis method, in particular to an intelligent fault diagnosis method for rotating machinery under time-varying rotating speed conditions lacking expert experience and prior domain knowledge, and belongs to the technical field of mechanical fault detection and diagnosis. Background technique [0002] In the current research on fault diagnosis of rotating machinery, machine learning methods are mainly used for intelligent adaptive diagnosis. In recent years, the deep learning method has been widely used with stronger fault classification performance, but the existing intelligent adaptive diagnosis method It has a good application mainly in the fault diagnosis of rotating machinery under constant working conditions, but there are few related studies on the fault diagnosis of rotating machinery under variable speed conditions, especially under the condition of irregular speed and time-varying, the deep learnin...

AI Technical Summary

Problems solved by technology

[0002] In the current research on fault diagnosis of rotating machinery, machine learning methods are mainly used for intelligent adaptive diagnosis. In recent years, the deep learning method has been widely used with stronger fault classification performance, but the existing intelligent adaptive diagnosis method It has a good application mainly in the fault diagnosis of rotating machinery under constant working conditions, but there are few related studies on the fault diagnosis of rotating machinery under variable speed conditions, especially under the condition of irregular speed and time-varying, the deep learning method cannot solve the problem. Troubleshooting Problems

Images