Fault Diagnosis Strategy for Flight Control Rudder Circuit Based on SHAP Interpretable Analysis Optimization Transformer with Attention Mechanism

Research on the explanation of the reasons for the output classification results of intelligent diagnostic algorithms is still in its infancy, and interpreting the operation process of intelligent algorithms can help users trust and accept such methods. In this article, we take the intelligent algorithm-based fault diagnosis of the rudder control circuit of an airplane flight control system as an example and carry out research on the interpretability of the diagnostic algorithm based on the Shapley additive explanation (SHAP). The transformer feature capture module is designed in the diagnostic model, which establishes the dependency of the fault timing signals in the time perspective by embedding the attention mechanism and guarantees the ability to classify the dataset with less differentiation. In addition, given the characteristics of circuit data with multiple classes and similar features, this article optimizes the model by designing a new loss function called anomaly data feature enhancement loss (ADFE Loss) in a targeted manner. The loss function can amplify the fault data so that the model can converge faster, thus improving the accuracy and efficiency of fault diagnosis. Based on SHAP, the diagnostic process of the transformer model was analyzed in terms of local and global interpretability, which led to the streamlining of some features and optimization of the model. The results show that the optimized model can maintain a smoother and more accurate diagnostic process in a shorter number of iterations while reducing the consumption of computational resources. Meanwhile, the proposed diagnostic strategy also exhibits better noise robustness.