Effective Fault Diagnosis Based on Wavelet and Convolutional Attention Neural Network for Induction Motors

Induction motors are important equipment in modern industry. However, the occurrence of fatigue failure following an extended period of operation invariably results in a catastrophic failure. As a result, monitoring and diagnosing induction motors is critical to avoiding unplanned shutdowns caused by premature failures. This article aims to develop an effective method for motor fault detection using time–frequency contents of vibration signals and an attention-based convolutional neural network model. First, the vibration signals are collected and labeled into five different categories: normal condition, outer ring fault, inner ring fault, misalignment condition, and broken rotor bar. Then, using the Morlet function, continuous wavelet transform (CWT) converts the vibratory time-series signals to the scalogram feature images. The time–frequency feature images are created after downsampling and converting the measured vibration signals to the frequency domain. These images are then resized and fed into the proposed convolutional attention neural network (CANN) to identify various induction motor failures. The experimental results demonstrate that the suggested model can provide an excellent diagnosis accuracy of 99.43%, significantly better than the state-of-the-art deep learning approaches for fault diagnosis. Moreover, the developed model’s robustness is validated against adversarial attacks based on the fast gradient sign method (FGSM) by including white Gaussian noise.

I. Introduction

Induction machines have been widely utilized in many industrial fields owing to their cost effectiveness, simple structure, and easy maintenance. However, many types of failures may occur after a long operating time that would cause a catastrophic malfunction, in which bearing defects, stator faults, and rotor faults are the most common failures of induction motors. Those failures would generate more heat, decrease output torque, require more energy consumption, and also cause a catastrophic failure [1]. Therefore, early detection and diagnosis could prevent failures from becoming more serious and reduce the cost of maintenance. Moreover, it is more flexible compared with periodic maintenance.