Rolling element bearing fault diagnosis based on modified Pufferfish optimization assisted efficient customized convolutional neural network with IMI-EMD.

Deep learning (DL) models have become a powerful alternative that learns the relevant features automatically from raw vibration signals without extensive manual intervention. This research addresses the existing gap in fault diagnosis by introducing a novel methodology through an efficient customized convolutional neural network (CCNN) with the modified Pufferfish optimization algorithm (MPOA) model. The proposed method includes two main phases. The initial phase involves preprocessing the input vibration signal using an improved mutual information based empirical mode decomposition technique, which effectively decomposes the signal. In the second phase, fault diagnosis is carried out using the proposed CCNN model. To improve the performance of the model, the weights of the CCNN are optimized through the MPOA. The efficient CCNN model for fault diagnosis is compared with the conventional models through a thorough evaluation using metrics like precision, accuracy, sensitivity, specificity, false positive rate, and false negative rate. The CCNN-MPOA model, exhibited effective performance in fault diagnosis applications. By using a 70/30 training–testing data split, the model achieved an accuracy rate of 96.1% with a moderate computational cost of 12.22 GFLOPS along with a relatively short training time of 64.179 s. The proposed model was less prone to errors since it had a low FNR of 0.039 and an FDR of 0.037, the latter being a feature that reflected its performance in not confusing the present faults with the normal states. The computational efficiency and diagnostic accuracy of the proposed model suggest its potential suitability for future industrial deployment.