Fault diagnosis of rolling bearing using CNN and PCA fractal based feature extraction

Abstract

A novel adaptive decomposition algorithm based on CEEMDAN and fractal dimension is proposed in this study to overcome limitations like redundancy and mode confusion in traditional EMD-based algorithms. An intelligent fault diagnosis model is developed using CNN and the proposed CEEMDAN to enhance rolling bearing state recognition. Sub-signals generated by CEEMDAN are selected and reconstructed using PCA and fractal dimension. In feature extraction and pattern recognition, the proposed Improve Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), coupled with CNN, extracts advanced features from the reconstructed signal for intelligent diagnosis. The methodology is validated through empirical experiments involving rolling bearings, where its superiority and reliability are compared with approaches based on CNN. The accuracy of this method reaches 99.79%