Motor Fault Detection Based on Sound Signal

The importance of detecting motor faults to ensure the stable operation of industrial equipment and reduce maintenance costs cannot be overstated. This research introduces a motor fault detection technology based on analyzing acoustic signals. The methodology involves using microphones to capture real-time sound signals produced by the motor during operation. These signals then undergo a preprocessing stage, including filtering and noise reduction, to improve their quality. Next, we use MFCC algorithms to extract feature parameters from the recorded sound signals and combine these parameters with the convolutional neural network algorithm within deep learning to accurately recognize motor faults.