Aiming at the problem of the high failure rate of electric vehicle charging piles, a fault prediction method of electric vehicle charging piles based on cooperative game strategy and dung beetle optimization algorithm-bidirectional long-term and short-term memory network-attention mechanism (DBO-BiLSTM-Attention) is proposed. Firstly, the abnormal values are processed by parameter statistical distribution map, the missing values are processed by mean filling, and the processed data are normalized. Secondly, multiple single-weighting methods are selected to calculate the feature weight, the combination weight is calculated by the cooperative game strategy, and the parameter feature matrix is amplified. Then, the DBO-BiLSTM-Attention model is built. Under the simulation experiment, the accuracy and F1 coefficient of the training set and the test set are 0.89,0.89,0.90 and 0.90, respectively. Finally, relevant comparative experiments are constructed. The results show that the proposed model has better performance and verifies the validity and rationality of the proposed model.