THE DEVELOPMENT OF MATHEMATICAL MODEL FOR INVESTIGATING THE ALGORITHMS OF ESTIMATION AND PREDICTION OF UAV ELECTROMECHANICAL ACTUATOR TECHNICAL STATE
Abstract
Russian development of unmanned aerial vehicles (UAV) is largely focused on objects of the "Mi-cro", "Mini", "Middle-", "Small-" and "Medium-" range class. A characteristic feature of these objects is the use of servoactuators (SA) in the primary control system with a passband of at least fdb = 0.7 Hz. Such SA are widely used in aircraft modeling, however, in the UAV field, their use is limited by the con-trol quality requirements, power and reliability. KBPA JSC has developed and manufactured a 400 kg average radius UAVs SA prototype. To assess technical requirements compliance, SA samples experi-mental studies were conducted. Based on the components design characteristics and tests results SA mathematical model has been formed in Simulink, which is supposed to be used to simulate the closedloop dynamics of the "UAV - control system - SA". M odel validation was carried out on the basis of the static and dynamic characteristics of the SA natural sample. Detailization of such model in the future will make it possible to introduce algorithms for SA early failure diagnosis, which are currently being developed at TsAGI and ICS RAS. The basis for such algorithms is the SA energy efficiency. The energy efficiency changing is a non-deterministic parameter that substantially depends on its functioning mode and the external influence factors and affects among other things the SA heat loss. Therefore, it seems appropriate to conduct a comprehensive analysis including the use of data mining algorithms. A special target property of the developed diagnostic system is its ability to determine the SA technical condition in non-deterministic modes.
References
2. Mare J.-C. Aerospace actuators 2. Signal-by-Wire and Power-by-Wire // ISTE Ltd. And John Wiley & Sons Inc., 2017, 169 p. ISBN 978-184821-942-7.
3. Bilyaletdinova L., Steblinkin A. Simulation of Direct Drive Electromechanical Actuator with Ballscrew, Procedia Engineering, 2017, Vol. 176, pp. 85-95.
4. Skryabin A.V. Sistemy kontrolya tekhnicheskogo sostoyaniya i prognozirovaniya neispravnostey elektromekhanicheskikh rulevykh privodov letatel'nogo apparata. Sovremennyy uroven' razvitiya [Systems for monitoring the technical condition and predicting malfunctions of Electromechanical steering drives of the aircraft. Modern level of develop-ment], Obshcherossiyskiy nauchno-tekhnicheskiy zhurnal «Polet» [All-Russian scientific and technical magazine "Flight"], 2018, No. 2, pp. 50-64.
5. Glison E., Kopp J.D., Manzanares D. MOOG next generation control and actuation, R3ASC. Toulouse, 2014, pp. 43-54.
6. F. Van Der Linden, Dreyer N., Dorkel A. EMA Health monitoring: an overview, R3ASC Pro-ceedings. Toulouse, 2016, pp. 21-26.
7. Veresnikov G., Skryabin A. The Electromechanical Actuator Technical Condition Monitoring System Based on Data Mining Methods, Proceedings of 2018 11th International Conference Management of Large-Scale System Development, MLSD 2018. Мoscow, 2018.
8. Veresnikov G., Skryabin A. The Health Assessment and Prediction Algorithms Development for Electromechanical Flight Control Actuator Using Data Mining Methods, Proceedings of 2019 12th International Conference Management of Large-Scale System Development, MLSD 2019. Мoscow, 2019.
9. Erofeev E., Skryabin A., Steblinkin A., Khaletskiy L. Methodologies and test-rig configurations for the experimental improvement of flight control actuation systems, Recent Advances in Aerospace Actuation Systems and Component 2018 Conference proceedings, Toulouse, France, 2018, pp. 109-116.
10. Mare J.-C. Friction modeling and simulation at system level: a practical view for the designer, Proc ImechE Part I: Journal of systems and control engineering 226(6) ImechE 2012, pp. 728-741.
11. Kalachev Yu.N. Vektornoe regulirovanie (zametki praktika) [Vector regulation (practice notes)]. Moscow: EFO, 2013, 63 p.
12. Kowalski R., Möller F., Gallun P., Bierig A. Test facility for electro-mechanical actuation systems, Proceedings of the 7th International Workshop on Aircraft Systems Technologies, Hamburg, Germany, 2019, pp. 133-142.
13. Jian F., Mare J.-C., Yongling F. Modelling and simulation of flight control electromechanical actuators with special focus on model architectecting, multidisciplinary effects and power flows, Chinese Journal of Aeronautics, 2017, No. 30 (1), pp. 47-65.
14. Bengio Y. et al. Representation Learning: A Review and New Perspectives, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, Vol. 35 (8), pp. 1798-1828.
15. Schölkopf B. Nonlinear Component Analysis as a Kernel Eigenvalue Problem, Neural Compu-tation, 1998, Vol. 10 (5), pp. 1299-1319.
16. Hinton G.E., Salakhutdinov R.R. Reducing the Dimensionality of Data with Neural Networks, Science, 2006, Vol. 313, Issue 5786, pp. 504-507.
17. Chuang L.-Y., Ke C.-H., Yang C.-H. A Hybrid Both Filter and Wrapper Feature Selection Method for Microarray Classification, Proceedings of International MultiConference of Engi-neers and Computer Scientists, 2008, pp. 146-150.
18. Le-Khac N.-A., Bue M., Whelan M., Kechadi M.-T. A Clustering-Based Data Reduction for Very Large Spatio-Temporal Datasets, International Conference on Advanced Data Mining and Applications. ADMA 2010: Advanced Data Mining and Applications, Chongqing, China, pp. 43-54.
19. Soufan O., Kleftogiannis D., Kalnis P., Bajic V.B. DWFS: a wrapper feature selection tool based on a parallel genetic algorithm, PLoS ONE, 2015, Vol. 10 (2), pp. e0117988.
20. Panthong R., Srivihok A. Wrapper Feature Subset Selection for Dimension Reduction Based on Ensemble Learning Algorithm, The Third Information Systems International Conference: Procedia Computer Science, 2015, Vol. 72, pp. 162-169.
21. Veresnikov G.S., Skryabin A.V. The development of data mining methods criteria to identify failures of aircraft control surface actuator, Procedia Computer Science, 2017, Vol. 112, pp. 1007-1014.
