A new approach for online bearing fault detection of induction motor based on vibration signal wavelet

Due to the widespread use of electric motors in various industries, checking the conditions and diagnosing its possible faults in the early stages is one of the most important goals of intelligent industrial monitoring equipment in modern factories. Bearings are one of the mechanical parts that often fail during operation. The mechanical faults of the electric motor show themselves as vibration in the motor, which can be used to diagnose the fault, especially in the early stages. In addition, noise in industrial environments usually has less impact on vibration because vibration is extracted directly from the motor body or its base. According to this explanation, in this research, a bearing fault detection method is proposed using wavelet transform of the vibration signal in induction motors, which can detect the defect with very high accuracy. The proposed method was implemented on two different databases using Matlab 2021. The obtained results, compared with the latest articles in this field, confirmed the effectiveness of proposed method based on criteria such as accuracy and correctness. In the meantime, the advantages of proposed method, such as high speed, low calculations and its robustness to noise, were also shown.