Bearing fault diagnosis based on wavelet packet energy spectrum with extreme learning machine (ELM)

Rolling bearings, as critical components of rotating machinery, support and reduce friction in mechanical systems. Failures in these bearings can not only disrupt project progress but also lead to substantial economic losses and potentially cause casualties. Consequently, research into rolling bearing fault diagnosis is of paramount importance. This paper addresses the problem of bearing failure by proposing a fault diagnosis method that combines wavelet packet energy spectrum analysis with an Extreme Learning Machine (ELM). To replicate real-world noisy operational environments, high-intensity noise is added to the collected signal samples. These samples undergo wavelet packet decomposition and reconstruction for energy feature extraction, with the band energy being selected via the wavelet packet energy spectrum. The extracted energy features are then used to construct a dataset that is input into the ELM model for multiple training iterations. The diagnostic accuracy of the model reached 95.1429±2.87%, demonstrating the method's effectiveness in bearing fault diagnosis and its ability to enhance the recognition and diagnosis capabilities of bearing fault signals.