An early fault diagnosis method for large mining electric motors based on vibration and temperature analysis

The stable operation of large mining electric motors is crucial for mining production, and their early fault diagnosis is a key technical means to ensure equipment safety and avoid malignant accidents. This paper proposes an early fault diagnosis method integrating vibration and temperature signal analysis. Firstly, the random forest algorithm is used to screen the key feature parameters representing faults, then the wavelet soft threshold method is adopted to denoise the collected signals, and finally the MISSA-SVM fault diagnosis model is constructed to realize the accurate identification of three typical faults of motor stator, rotor and bearing. The experimental results show that the overall fault diagnosis accuracy of this method reaches 98.095 2%, and after 10 stability tests, the average accuracy is 97.676 2% with excellent stability, which can provide reliable technical support for the predictive maintenance of large mining electric motors.