Fault Diagnosis Method of Equipotential Planet Map Based on Fusion Features

In recent years, signal processing theory and deep learning theory have been developed rapidly, providing a solid theoretical foundation for feature extraction and classification of bearing fault signals. Bearing fault signals are usually nonlinear and non-steady, traditional time-domain or frequency-domain methods are difficult to classify fault signals. Therefore, this paper proposes a bearing fault signal diagnosis method based on entropy feature fusion equipotential planet map, combined with constellation diagram the principle extracts the approximate entropy and permutation entropy of the original fault signal into two-dimensional features, uses the equipotential planet map to convert the entropy feature fault signal into images, uses the deep learning PCANet network to classify the fault signal, and performs the bearing fault data set simulation shows that the accuracy of the fault diagnosis model has reached 100%. The study of this method is expected to provide a reliable theoretical basis for related engineering practices in the field of fault diagnosis.