Abstract: This paper proposes an intelligent fault prediction method for mining electrical and mechanical equipment based on deep learning. Firstly, historical data is collected and preprocessed to construct a training set. Then, a deep neural network model is designed and trained to learn the relationship between equipment operating conditions and faults. Finally, in the prediction stage, real-time data is input into the trained model to achieve fault prediction. The experimental results show that this method can effectively predict equipment faults, provide maintenance decision support, reduce downtime, improve equipment utilization, and achieve higher prediction accuracy and adaptability.