DOI 10.17586/0021-3454-2023-66-2-125-130
UDC 62-523
APPLICATION OF MACHINE LEARNING METHODS TO LOCALIZE QUADCOPTER SENSOR FAILURES
ITMO University, Faculty of Control Systems and Robotics;
A. A. Margun
ITMO University, Saint Petersburg, 197101, Russian Federation; Institute for Problems in Mechanical Engineering of the Russian Academy of Sciences, Saint Petersburg, 199178, Russian Federation; Associate professor; Scientific Researcher
A. A. Pyrkin
ITMO University, Saint Petersburg, 197101, Russian Federation; Full Professor, Dean
Read the full article
Abstract. The problem of localizing failures of sensors (accelerometer and gyroscope) of an unmanned aerial vehicle of the "quadcopter" type is considered. An algorithm is developed that provides the ability to detect and classify quadcopter sensor failures using machine learning methods. To solve the problem, the following machine learning methods were used: logistic regression, random forest method, LASSO and ridge regression, as well as elastic net. Experimental results obtained in the course of computer simulation confirm the efficiency of the proposed algorithm. A comparative analysis of the used methods of machine learning is performed.
Keywords: failure localization, quadcopter, UAV, logistic regression, random forest method, LASSO regression, ridge regression, elastic net, accelerometer, gyroscope
References:
References:
- Kozlov D.S., Tyumentsev Y.V. Trudy MAI, 2012, no. 52, https://mai.ru/upload/iblock/0e5/neyrosetevye-metody-obnaruzheniya-otkazov-datchikov-i-privodov-letatelnogo-apparata.pdf?referer=https%3A%2F%2Fyandex.ru%2Fclck%2Fjsredir%3Ffrom%3Dyandex.ru%3Bsearch%2F%3Bweb%3B%3B. (in Russ.)
- Lee D., Burg T., Dawson D., Shu D., Xian B., and Tatlicioglu E. IEEE International Conference on Systems, Man and Cybernetics, SMC 2009, 2009, pp. 3187–3192.
- Pyrkin A.A., Maltseva T.A., Labadin D.V., Surov M.O., Bobtsov A.A. Journal of Instrument Engineering, 2013, no. 4(56), pp. 47–51. (in Russ.)
- Patan K. Lecture Notes in Control and Information Sciences, vol. 377, Berlin, Springer-Verlag, 2008, 206 p.
- Blanke M. et al. Diagnosis and fault-tolerant control, Berlin, Springer-Verlag, 2006, 672 p.
- Sobhani-Tehrani E., Khorasani K. Lecture Notes in Control and Information Sciences, vol. 383, NY, Springer-Verlag, 2009, 265 p.
- Shakhanov N.I., Varfolomeev I.A., Yudina O.V., Ershov E.V. Software products and environments, 2018, no. 1(36), pp. 212–217, DOI:10.15827/0236-235X.121.212-217. (in Russ.)
- Mian A.A. and Wang Dao-bo, Journal of Zhejiang University Science A, 2008, no. 4(9), pp. 539–545.
- Min B.C., Cho C.H., Choi K.M. & Kim D.H. Part of the Lecture Notes in Computer Science book series, vol. 5744, Advances in Robotics, pp. 262–271.
- Tayebi A., and McGilvray S. IEEE Transactions on Control Systems Technology, 2006, no. 3(14), pp. 562–571.
- Giron A. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems, O'Reilly Media, Inc., 2019, pp. 187–189.
- Chen J. and Patton R.J. Robust Model-Based Fault Diagnosis for Dynamic Systems, Kluwer Academic Publishers, 1999, 356 p.
- Wei W. Proceedings of the 2010 American Control Conference, 2010, pp. 1937–1941.
- Melnik M. Osnovy prikladnoy statistiki (Fundamentals of Applied Statistics), Moscow, 1983, 416 p. (in Russ.)
