Fault diagnosis using ISMA to optimize SVM parameters for aircraft engine damage repair

Area of Science:

• Aerospace Engineering
• Mechanical Engineering
• Artificial Intelligence

Background:

• Aviation engines require robust Condition Monitoring (CM) for safety and efficiency.
• Current CM signal fault diagnosis methods suffer from low accuracy and poor real-time capabilities.
• Identifying subtle fault signals in complex engine environments is a significant challenge.

Purpose of the Study:

• To develop an integrated model for enhanced aviation engine CM signal fault diagnosis.
• To improve the accuracy and real-time performance of fault detection in aviation engines.
• To leverage deep learning and optimization algorithms for superior fault identification.

Main Methods:

• Proposed an AE-BiGRU model for effective feature extraction from CM signals.
• Introduced an Improved Slime Mould Algorithm (ISMA) to optimize Support Vector Machine (SVM) parameters for classification.
• Validated the model's performance on the C-MAPSS dataset.

Main Results:

• The ISMA demonstrated superior variance reduction in function optimization.
• The AE-BiGRU-ISMA-SVM model achieved high precision (0.90), recall (0.95), and F1 score (0.92).
• The model excelled in extracting weak fault signals and identifying fault frequencies.

Conclusions:

• The proposed AE-BiGRU-ISMA-SVM method significantly enhances aviation engine fault diagnosis.
• This approach improves the safeguarding of engine health status and aids in timely damage repair.
• The integrated model offers a promising solution for real-time, accurate CM in aviation.