Rotating Machinery Fault Prediction Method Based on Bi-LSTM and Attention Mechanism

In order to improve the reliability and accuracy of the prediction results in the prediction of rotating machinery fault trend, this paper proposes a fault prediction method based on Bi-LSTM and Attention mechanism. Firstly, Bi-LSTM is constructed to extract the timing signal data characteristics of the rotating machinery. Then, the Attention mechanism is introduced to highlight the data sequence that has a key influence on the prediction result. Finally, the difference between the predicted value that the model outputs and the empirical threshold is compared to establish a multi-step, multivariable rotating machinery fault prediction model. The actual field data is used to train and model the built network. The results show that this method can achieve high prediction accuracy for rotating machinery faults. At the same time, compared with other traditional methods, this method has good anti-noise performance and generalization ability, and can be well applied in actual engineering.