Bearing fault diagnosis based on CNN-MGO-LSSVM

Bearings play a critical role in rotating machinery, directly determining the safety and operational health of equipment. However, with the advancement of industrial society, bearing failures due to malfunctions have become increasingly prominent.Therefore, this study proposes an integrated model for bearing fault diagnosis by optimizing two key parameters of the Least Squares Support Vector Machine (LSSVM) using a combination of the MGO moss growth optimization algorithm and the PSO particle swarm algorithm: the regularization parameter and the kernel parameter. The high-dimensional feature vectors from the output layer of a two-dimensional convolutional neural network (2D-CNN) are used as input for the LSSVM. This model demonstrates higher accuracy and automation.