Mikhail I. Nadezhin
Baltic State Technical University «VOENMEH» (BSTU «VOENMEH»), Research Laboratory «Robotic and mechatronic systems», Junior Research Scientist, 1, 1-ya Krasnoarmeyskaya ulitsa, Saint Petersburg, 190005, Russia, tel.: +7(904)618-09-28, This email address is being protected from spambots. You need JavaScript enabled to view it.
Nikita S. Slobodzyan
BSTU «VOENMEH», Research Laboratory «Robotic and mechatronic systems», Re-search Scientist, 1, 1-ya Krasnoarmeyskaya ulitsa, Saint Petersburg, 190005, Russia, tel.: +7(953)345-38-27, This email address is being protected from spambots. You need JavaScript enabled to view it.
Aleksei А. Kiselev
BSTU «VOENMEH», Research Laboratory «Robotic and mechatronic systems», Engineer, 1, 1-ya Krasnoarmeyskaya ulitsa, Saint Petersburg, 190005, Russia, tel.: +7(952)243-80-68, This email address is being protected from spambots. You need JavaScript enabled to view it.
Received 30 September 2021
Abstract
The research is part of the current work carried out at BSTU «VOENMEH» named after D.F. Ustinov with the finan-cial support of the Ministry of Science and Higher Education of the Russian Federation for the design and creation of high-resource electric pumping units for aviation, transport, and space technology. Recommendations are given on the hardware and algorithmic support of the on-board system for diagnosing the technical condition of spacecraft electromechanical units. Ground testing of the proposed solutions was carried out in the course of experimental studies of an electric pump unit laboratory sample. The advantages of the hybrid feature selection algorithm for improving the accuracy and speed of diagnostics with a feedforward artificial neural network with a significant decrease in the number of input values are shown. The quantities that are sensitive to changes in the state of the electrical parts of electromechanical systems have been determined.
Key words
Diagnostics, electric motor, machine learning, feature selection, classification.
DOI
10.31776/RTCJ.10108
Bibliographic description
Nadezhin, M., Slobodzyan, N. and Kiselev, A., 2022. Improving quality of the faults’ classification models for electromechanical systems’ diagnostics. Robotics and Technical Cybernetics, 10(1), pp.73-80.
UDC identifier:
681.518.5
References
Matveev, S.A. et al., 2020. Methods for diagnosing the technical condition of spacecraft electric pump units and predicting their remaining useful life. Russian Aeronautics, 63(4), pp.561–567.
Spolaôr, N. et al., 2016. A systematic review of multi-label feature selection and a new method based on label construction. Neurocomputing, 180(5), pp.3-15.
Wang, Z., Huang, H. and Wang, Y., 2021. Fault diagnosis of planetary gearbox using multi-criteria feature selection and heterogeneous ensemble learning classification. Measurement, 173. DOI: 10.1016/j.measurement.2020.108654.
Howell, D., 2002. Statistical Methods for Psychology. Duxbury: Thomson Learning, p.802.
Vuong, Q.H. and Wang, W., 1993. Minimum chi-square estimation and tests for model selection. Journal of Econometrics, 56(1–2), pp.141-168.
Chaudhuri, A. and Sahu, T.P., 2021. A hybrid feature selection method based on Binary Jaya algorithm for micro-array data classification. Computers & Electrical Engineering, 90. DOI: 10.1016/j.compeleceng.2020.106963.
Gibbons, J.D. and Dekker, M., 1985. Nonparametric Statistical Inference. New York, p.408.
Milandr, u.d. 32-razryadnyy mikrokontroller s povyshennoy stoykost'yu k SVVF na baze mikroprotsessornogo RISC yadra [32-bit microcontroller with increased resistance to SVVF based on microprocessor RISC core]. Available at: <https://ic.milandr.ru/products/radiatsionno_stoykie_mikroskhemy/1986ve8t/> (Accessed 25 January 2022).
Muenchhof, M., Beck, M. and Isermann, R., 2009. Fault-tolerant actuators and drives: Structures, fault detection principles and applications. Annual Reviews in Control, 33, pp.136–148.
Matveev, S.A. et al., 2020. Obzor metodov diagnostiki elektronasosnykh agregatov sputnikovykh platform [Review of methods for diagnosing electric pump units of satellite platforms]. Radiopromyshlennost' [Radio Industry], 30(3), pp.86–98. (in Russian).
Kimotho, J.K. and Sextro, W., 2014. An approach for feature extraction and selection from non-trending data for machinery prognosis. Proceedings of the European Conference of the PHM Society, 2(1). DOI: 10.36001/phme.2014.v2i1.1462.
Korotkov, E.B. et al., 2019. Nazemnaya sistema kompleksnoy diagnostiki elektromekhanicheskikh ustroystv kosmicheskikh apparatov [Ground-based system for complex diagnostics of spacecraft electromechanical devices]. Radiopromyshlennost' [Radio Industry], 29(4), pp.54–62. (in Russian).
