Fault Diagnosis Strategy for Flight Control Rudder Circuit Based on SHAP Interpretable Analysis Optimization Transformer With Attention Mechanism
- 30 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
Abstract
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 paper, 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 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 paper optimizes the model by designing a new loss function called Anomaly Data Feature Enhancement (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.Keywords
Funding Information
- Shaanxi Provincial Natural Science Basic Research Program (2024JC-YBQN-0521)
- National Natural Science Foundation Fund (52072309)
- National Natural Science Foundation of China (62303379)
- Natural Science Foundation of Shaanxi province, China (2023-JC-QN-0665)
- Industry-University-Research Innovation Fund of Ministry of Education for Chinese Universities (2022IT189)
- Fundamental Research Funds for the Central Universities (G2022WD01017)
This publication has 31 references indexed in Scilit:
- Transformer based contextual text representation framework for intelligent information retrievalExpert Systems with Applications, 2023
- Automated ICD coding using extreme multi-label long text transformer-based modelsArtificial Intelligence in Medicine, 2023
- A hybrid strategy of AutoML and SHAP for automated and explainable concrete strength predictionCase Studies in Construction Materials, 2023
- Position control of a DC servo motor using various controllers: A comparative studyMaterials Today: Proceedings, 2022
- Servo motor sliding mode control based on fuzzy power index methodComputers and Electrical Engineering, 2021
- Robust Actuator Fault Diagnosis Algorithm for Autonomous Hexacopter UAVsIFAC-PapersOnLine, 2020
- A linear ADRC-based robust high-dynamic double-loop servo system for aircraft electro-mechanical actuatorsChinese Journal of Aeronautics, 2019
- Flight control system failure modeling and verification based on SPINEngineering Failure Analysis, 2017
- Table‐Based Circuits for DSP Applications2017
- Class Noise vs. Attribute Noise: A Quantitative StudyArtificial Intelligence Review, 2004