CONTROL AND MODELING PARAMETERS FOR HEAT DIAGNOSTICS OF POWER ELECTRICAL EQUIPMENT FAILURE
Keywords:artificial neural network, perceptron, remote control, modeling, parameter converter, modulator, transport, traction electric motor, identification
It has been analyzed the advantages and disadvantages of the popular methods of thermal diagnostics of electric motors used in electric vehicles and public utilities. The research results of a remote sensor-transmitter for monitoring the heating temperature of various parts of the equipment relatively the ambient temperature are presented. It has been illustrated the examples of using a temperature sensor with a modulator for converting information messages according to the principle of "temperature-frequency", which made it possible to achieve measurement accuracy with an error of ± 0.25 to ± 0.07 ° C.
It has been proposed a hardware path of the selective heating assessment of traction electric motors with various classes insulation. Examples of modeling the normalized thermal regimes of direct current traction electric motor and the identification of possible failures during abnormal components heating are illustrated. Using the Matlab package tools, it has been given examples of thermal processes approximation, used to analyze stochastic thermal conditions and form a primary audio library of possible failures for training a neural network expert of traction electric motors heating.
It has been considered the application of the forward propagation perceptron with one hidden layer in the synthesis of an artificial neural network expert for the heat generation problems classification in traction electric motors. It has been determined the algorithm for comparing input and output features using a frequency comparator, which modeling is performed in the Matlab environment. The training neural network expert methods using a test board with low-frequency generators and the teacher synthesis methods, reducing the time spent for experimental testing of a neural network system for thermal diagnostics of traction electric motors, which allowed with an error (SSE / MSE) of 0.01 to achieve this result with less 100 eras.
In the experimental artificial neural experts (ANE), the approximation time of the initial random data and the technical state identification of the TED did not exceed 0.5 s. This ANE allows to expand the diagnosed range of problems through additional training, using control tools: levels of brush sparking and vibration; smoke from heated zones, etc., specified by the user. The proposed real-time remote diagnosis system of vehicle failures can significantly reduce costs of daily maintenance on routes and affect the vehicle service culture.
Nosov, V. V. (2012). Diagnostics of machines and equip-ment: study guide. St. Petersburg : Publishing house «Lan", 384.
Kruglov, V. V. (2001). Fuzzy logic and artificial neural networks. Moscow : FIZMATLIT, 201.
Khaikin, S. (2006). Neural networks: a full course. Moscow : Williams Publishing House, 1104.
Gutnikov, V. S. (1980). Integrated electronics in measuring devices. Leningrad: Energy, 387.
Bellini, A. Bellini, A., Filippetti, F., Tassoni, C., Capo-lino G. A. (2008). Advances in diagnostic techniques for induction machines. IEEE Transactions on Industrial Elec-tronics, Vol. 55, No. 12, pp. 4109 – 4126.
Esaulov, S. M. (2007). Automation of equipment health monitoring at electric transport facilities - Urban services. Kiev: Technics, Iss. 76, pp. 359 − 363.
Levshina, E. S. (1983). Electrical measurements of physical quantities: (Measuring transducers). Textbook manual for universities. Leningrad: Energoatomizdat, 320.
Lutai, S. N. (2014). Methods and analysis of the diagnosis of asynchronous electric motors. Electrical and computer systems. No. 15 (91), pp. 306 – 310.
Goldberg, O. D. (1991). Automation of parameter control and diagnostics of induction motors. Moscow : Energoatomizdat, 160.
Esaulov, S. M. (2009). The design of components for systems for the automatic diagnosis of transport. East European Journal of Advanced Technologies. Issue 5/3 (41), рр.28 − 32.
Esaulov, S. M. (2019). Control and modeling parameters for thermal diagnostics of the failure of the power range. Communal gospodarstvo mіst. Kiev: Technics, Issue 3 (149), рр. 19 − 28.
Safonov, L. N. (1977). Precision angle sensors with printed windings. Moscow : Mechanical Engineering, 276.
Semenenko, M. G. (2002). Introduction to mathematical modeling. Moscow : Solon-R, 319.
Dyakonov, V.P. (2005). MATLAB 6.5 SP1 / 7 + Simulink 5/6 in mathematics and modeling. Moscow : Solon-R, 412.
MATLAB. The Language of Technical Computing. Getting Started with MATLAB.The Math Works, Inc. USA, 2000.
Simulink. Model-Based and System-Based Design. Using Simulink. The Math Works, Inc. USA, 2002.
Dyakonov, V.P. (2006). MATLAB 6.5 SP1 / 7/7 SP1 / 7 SP2 + Simulink 5 / 6v. Tools of artificial intelligence and bioinformatics. Moscow : Solon-Press, 576.
Khaikin, S. (2006). Neural networks: a full course. Mos-cow : Williams, 1104.
Babicheva, O. F. (2018). Visualization of information messages mechatronic devices in transport. IV International Scientific-Practical Internet-Conference Conference «The present ruch of science
How to Cite
The authors who publish in this collection agree with the following terms:
• The authors reserve the right to authorship of their work and give the magazine the right to first publish this work under the terms of license CC BY-NC-ND 4.0 (with the Designation of Authorship - Non-Commercial - Without Derivatives 4.0 International), which allows others to freely distribute the published work with a mandatory reference to the authors of the original work and the first publication of the work in this magazine.
• Authors have the right to make independent extra-exclusive work agreements in the form in which they were published by this magazine (for example, posting work in an electronic repository of an institution or publishing as part of a monograph), provided that the link to the first publication of the work in this journal is maintained. .
• Journal policy allows and encourages the publication of manuscripts on the Internet (for example, in institutions' repositories or on personal websites), both before the publication of this manuscript and during its editorial work, as it contributes to the emergence of productive scientific discussion and positively affects the efficiency and dynamics of the citation of the published work (see The Effect of Open Access).