Fault Prediction of Double Toothed Roller Crusher Failure in Open Pit Mines Based on Digital Twinning Technique of ASL-CatBoost Algorithm

The bearings of double toothed roller crushers in open pit mines are prone to failure during prolonged operation, resulting in reduced productivity and shortened equipment life. Therefore, a bearing fault prediction model based on asymmetric loss function gradient boosting algorithm and digital twin has been proposed for effective fault prediction of double toothed roller crusher bearings. First, the fault signal is extracted by Wigner-Ville time-frequency distribution and empirical mode decomposition. Then, the asymmetric loss function gradient boosting algorithm is used to model and predict the signal characteristics. Finally, a digital twin model is constructed to visualize bearing fault information by combining sensor data and historical fault data. The experimental results showed that the fault prediction model achieved a precision rate of 98%, a recall rate of 99%, and an F1 value of 98.5% in predicting bearing rolling element failures. Among them, the running time of fault prediction was 1 minute and 49s. The experimental results demonstrate that the proposed fault prediction model can learn complex feature representations from large amounts of data, with good fault prediction performance and efficiency, and has certain practical application value. The research results contribute to improving the accuracy and intelligence level of fault prediction methods, thereby ensuring the stable operation of open-pit mine double toothed roller crushers.