CNN-ELMNet: fault diagnosis of induction motor bearing based on cross-modal vector fusion

Abstract

As the primary driving equipment in industrial, accurate fault diagnosis and condition monitoring of induction motor is crucial for ensuring operational safety. This paper focuses on the bearing faults of induction motors, which have a substantial impact on both the mechanical and electromagnetic systems of the motors. However, in diagnostic tasks, we are faced with the challenges of multi-source, multi-modal data, significant influence from environmental noise, and minimal differentiation between fault data. This paper proposed a novel cross-modal vector fusion fault diagnosis and classification model (CNN-ELMNet), which includes a Cross-Modal Vector Fusion Network (VF) based on D-S evidence theory, feature extraction layer (FE) and classification layer (CL). Specifically, the VF prioritizes the integration of diagnostic results from individual vibration signals or stator current signals within convolutional neural networks with the features of the input implicit vectors as decision-making evidence, followed by weighted vector fusion through D-S evidence theory at the decision level. The FE focuses on retaining the convolutional, pooling, and fully connected layers of the convolutional network and freezing the final fully connected layer, thus preserving training parameters and fully utilizing the network's powerful feature extraction capabilities. The CL includes an Extreme Learning Machine optimized for random hyperparameters using the SAO algorithm, which offers rapid convergence and high classification recognition rates. The CNN-ELMNet model combines a convolutional network with an Extreme Learning Machine optimized by the SAO algorithm, which not only preserves the model's feature extraction capability but also enhances the convergence speed and classification recognition rate of the model. Experimental results on real datasets demonstrate that the proposed model exhibits strong stability, generalization, and high accuracy in fault diagnosis, achieving an accuracy rate of 99.29% and 98.75%. This provides a more feasible solution for the bearing fault diagnosis of induction motors and holds promising prospects for practical applications.