Methods of Features Selection to Assess the Technical Condition of the Aircraft Electromechanical Actuator

The paper examines the issue of feature selection in the construction of classification models for the diagnosis of the aircraft electromechanical actuators (EMA). The widespread use of EMA in aircraft with a high degree of electrification (electric aircraft, unmanned aircraft) and the need to ensure flight safety determines the relevance of the research conducted. This problem of feature selection should be solved to reduce the extent of the analyzed data and increase the efficiency of algorithms for assessing the technical condition of the aircraft EMA. The servo actuator of an unmanned aircraft of an airplane type, which is used to deflect steering surfaces, is considered as an object of research in the work. At the same time, the main attention is focused on internal methods and filtering methods, which are based on simplified models that allow assessing the importance of features and do not require significant computational efforts. This paper presents results of comparing the methods of feature selection based on data obtained as a result of mathematical modeling of the operation of the servo actuator of an unmanned aircraft in various technical conditions. 

1. Liu W., Zou Z., Gu F., Shen G. Machine Learning for Fault Diagnosis of Electric Motors in Actuator Systems, Actuators, 2025, vol. 14, pp. 596.

2. Aliluev S. V., Bolshakov A. A., Popov A. N., Teterin D. P. Methods and Algorithms for Control and Diagnostics of the Steering Gear of the Autonomous Underwater Vehicles, Mekhatronika, Avtomatizatsiya, Upravlenie, 2017, vol. 18, no. 4, pp. 264—269 (in Russian).

3. Quattrocchi G., Berri P. C., Dalla Vedova M. D. L., Maggiore P. An Improved Fault Identification Method for Electromechanical Actuators, Aerospace, 2022, vol. 9, no. 7, pp. 341.

4. Yin Z., Neil H., Chen J., Yang Y, Shen G. А Review of Fault Diagnosis, Prognosis and Health Management for Aircraft Electromechanical Actuators, IET Electric Power Applications, 2022, vol. 16, iss. 11, pp. 1249—1272.

5. Grehan J., Ignatyev D., Zolotas А. Fault Detection in Aircraft Flight Control Actuators Using Support Vector Machines, Machines, 2023, vol. 11, no. 2, pp. 211.

6. Peng Z., Sun Z., Chen J., Ping Z., Dong K., Li J., Fu Y., Zio E. А Fault Diagnosis Approach for Electromechanical Actuators with Simulating Model under Small Experimental Data Sample Condition, Actuators, 2022, vol. 11, no. 3, pp. 66.

7. Qiao G., Liu G., Shi Z., Wang Y., S. Ma Y., Lim T. C. А Review of Electromechanical Actuators For More/All Electric Aircraft Systems, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2018, vol. 232, pp. 4128—4151.

8. Thanaraj T., Kin H. L., Bing F. N. Actuator Fault Detection and Isolation on Multi-rotor UAV using Extreme Learning Neurofuzzy Systems, ISA Transactions, 2023, vol. 138, pp. 168—185.

9. Verleysen M., François D. The Curse of Dimensionality in Data Mining and Time Series Prediction, Lecture Notes in Computer Science, 2005, vol. 3512, pp. 758—770.

10. Mutlag W. K., Ali S. K., Aydam Z. M., Taher В. H. Feature Extraction Methods: А Review, Journal of Physics: Conference Series, 2020, vol. 1591, pp. 012028.

11. Zhufeng L., Lvjun Q., Xiaodong W., Wen J., Caixia W. Research on Fault Diagnosis Method of Electro-Hydrostatic Actuator, Shock and Vibration, 2021, pp. 6688420.

12. Büyükkeçeci M., Okur M. А Comprehensive Review of Feature Selection and Feature Selection Stability in Machine Learning, Gazi University Journal of Science, vol. 36, iss. 4, pp. 1506—1520.

13. Chebel-Morello B., Malinowski S., Senoussi Н. Feature Selection for Fault Detection Systems: Application to the Tennessee Eastman Process, Applied Intelligence, 2016, vol. 44, pp. 111—122.

14. Sahraoui M. A., Rahmoune C., Meddour I., Bettahar T., Zair M. New Criteria for Wrapper Feature Selection to Enhance Bearing Fault Classification, Advances in Mechanical Engineering, 2023, vol. 15, iss. 6.

15. Balogun A. O., Basri S., Capretz L. F., Mahamad S., Imam A. A., Almomani M. A., Adeyemo V. E., Alazzawi A. K., Bajeh A. O., Kumar G. Software Defect Prediction Using Wrapper Feature Selection Based on Dynamic Re-Ranking Strategy, Symmetry, 2021, vol. 13, pp. 2166.

16. Yaman O., Yol F., Altinors A. А Fault Detection Method Based on Embedded Feature Extraction and SVM Classification for UAV Motors, Microprocessors and Microsystems, 2022, vol. 94, pp. 104683.

17. Mochammad S., Noh Y., Kang Y.-J., Park S., Lee J., Chin S. Multi-Filter Clustering Fusion for Feature Selection in Rotating Machinery Fault Classification, Sensors, 2022, vol. 22, pp. 2192.

18. Phuong H. T. M., My Hanh L. T., Binh N. T. А Study of Filter-Based Feature Selection in Software Fault Prediction, Lecture Notes on Data Engineering and Communications Technologies, vol. 148, pp. 58—67.

19. Udu A., Lecchini-Visintini A., Dong Н. Feature Selection for Aero-Engine Fault Detection, Lecture Notes in Computer Science, 2023, vol. 14146, pp. 522—527.

20. Garcia C. E., Camana M. R., Koo I. Machine Learningbased Scheme for Multi-class Fault Detection in Turbine Engine Disks, ICT Express, 2021, vol. 7, iss. 1, pp. 15—22.

21. Chen J., Chen S., Ma C., Jing Z., Xu Q. Fault Detection of Aircraft Control System Based on Negative Selection Algorithm, International Journal of Aerospace Engineering, 2020, vol. 2020, pp. 8833825.

22. Serebrenny V. V., Boshlyakov A. A., Ogorodnik А. I. Mathematical Model of Executive Modules of Robot Gripping Devices, Vestnik BSTU im. V. G. Shukhova, 2019, no. 6, pp. 123—135 (in Russian).