With the continuous development of aviation technology, the safety and reliability of aircraft systems are increasingly concerned. Fault diagnosis and prediction, as an important part of aircraft maintenance management, plays a vital role in improving the safety and availability of aircraft systems. The purpose of this study is to design and implement an efficient and accurate aircraft fault diagnosis and prediction algorithm by combining the advantages of deep learning and Markov model. Firstly, the paper uses deep learning technology to extract features and identify patterns from the sensor data of the aircraft system, so as to realize effective monitoring and analysis of the aircraft system state. Then Markov model is introduced to model the state transition of aircraft system, so as to realize the prediction and diagnosis of fault state. Finally, the deep learning model and Markov model are integrated, and an integration algorithm based on deep learning and Markov model is proposed to realize accurate diagnosis and prediction of aircraft system faults. Through the experimental verification on the actual aircraft data set, the research proves the effectiveness and advantages of the integration algorithm in fault diagnosis and prediction. Compared with the single deep learning model or Markov model, the integration algorithm has significantly improved the accuracy, recall and F1 value, and has higher accuracy and robustness. This study provides effective technical means and methods for improving the safety, reliability and maintenance efficiency of aircraft systems, and has important practical application value.
Aircraft Fault Diagnosis and Prediction Algorithm Based on Deep Learning and Markov Model
29.07.2024
340916 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Fault Diagnosis Method Based on Hidden Markov Model
Springer Verlag | 2016
|Deep Learning Based Machinery Fault Diagnosis
Springer Verlag | 2023
|Aircraft actuator fault diagnosis method based on AdaBoost-ASVM algorithm
Europäisches Patentamt | 2020
|Aircraft engine fault diagnosis research using model identification based method
British Library Online Contents | 2003
|