Abstract
The paper considers the issue of modeling the control system of general industrial transport equipment such as transport roller tables. The description of technological equipment is given, structural and kinematic schemes of the considered industrial mechanism are given. The key features of mechanisms of this type are considered, the requirements for the control system of electric drives of this equipment are separately mentioned. Lifting and transport mechanisms, which include the considered industrial unit, are widespread in the structure of industrial enterprises. Furnace roller tables, which are a special case of transport roller tables, are characterized by non-stop operation in the line of technological units, where special requirements are placed on the accuracy and overload capacity of the drive. For electric drives of this type, the use of asynchronous motors with a squirrel-cage rotor and sensorless control systems is typical. The control system must maintain the constancy of the speed of roller tables group, provide the necessary rate of acceleration and deceleration according to the mechanical coefficient of friction of the metal on the rollers. Also, such systems are characterized by functioning in the range from 10 to 60-70 Hz. A tool that allows leveling the shortcomings of such features of the object operation can be considered as the method related to the integration of neural network mathematical functions into the structure of the control system. The paper presents various adaptation mechanisms of neural network structures, describes their advantages and disadvantages. The article also mentions the issues of dynamic stability of the above-mentioned electric drive systems, research modeling of structures with different approaches to the architecture of the control system is carried out.
Keywords
simulation, variable speed drive, control system, vector control, asynchronous motor, Predictive controller, observers, sensorless vector control, learning, neural networks
1. Belov M.P., Novikov V.A., Rassudov L.N. Avtomatizirovannyy elektroprivod tipovykh proizvodstvennykh mekhanizmov i tekhnologicheskikh kompleksov [Automated electric drive of typical production mechanisms and technological complexes]. Moscow, Akademiya Publ., 2004. 575 p. (In Russian)
2. Terekhov V.M. Elementy avtomatizirovannogo elektroprivoda [Elements of an automated electric drive]. Moscow, Energoatomizdat Pubbl., 1987. 221 p. (in Russian)
3. Sentsov E.V., Meshcheryakov V.N. Development of an adaptive vector control velocity observer. Primenenie i razvitie neyrosetevogo modelirovaniya dlya resheniya fundamentalnykh zadach v nauke i tekhnike: Materialy Mezhdunarodnoy molodezhnoy nauchno-prakticheskoy konferentsii [Proceedings of the International Youth Scientific and Practical Conference "Application and development of neural network modeling for solving fundamental problems in science and technology"]. Novocherkassk, Lik LLC, 2018, pp. 36-47. (In Russian)
4. Sokolovsky G.G. Elektroprivody peremennogo toka s chastotnym regulirovaniem [AC drives with frequency regulation]. Moscow, Academiya Publ., 2006. 272 p. (In Russian)
5. Novikov V.A., Savva S.V., Tatarintsev N.I. Elektroprivod v sovremennykh tekhnologiyakh [Electric drive in modern technologies]. Moscow, Academy Publ., 2014. 400 p. (In Russian)
6. Sentsov E.V., Meshcheryakov V.N. Neural Network Speed Observer Development to Improve the Dynamic Stability of a Sensorless Vector Control System. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2022, no. 2(55), pp. 18-24. https://doi.org/10.18503/2311-8318-2022-2(55)-18-24 (In Russian)
7. Kalachev Ju.N. Vektornoe regulirovanie (zametki praktika) [Vector regulation (practice notes)]. Moscow, JeFO, 2013. 63 p. (in Russian)
8. Sentsov E.V. Neural network observers of the speed of an asynchronous motor. Tendentsii razvitiya sovremennoy nauki: [collection of proceedings of the scientific and practical conference of students and graduate students of the Lipetsk State Technical University "Trends in the development of modern science"]. Lipetsk, Lipetsk State Technical University Publ., 2021, pp. 109-113. (in Russian)
9. SinyukovaT.V., SentsovE.V., SinyukovA.V. Neural Network Speed Observers. 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA). IEEE, 2019, pp. 320-324. doi: 10.1109/SUMMA48161.2019.8947484
10. Kalachev Ju.N. Nabljudateli sostojanija v vektornom jelek-troprivode (zapiski diletanta) [State observers in a vector electric drive (dilettante notes)]. Moscow, 2015. 60 p. (in Russian)
11. Meshcheryakov V.N. Sistemy asinhronnogo elektroprivoda s upravlyaemymi koordinatami momentoobrazuyushchih vektorov [Systems of asynchronous electric drive with controlled coordinates of moment-generating vectors]. Lipetsk, LGTU Publ., 2008. 120 p. (in Russian)
12. Vinogradov A.B. Vektornoe upravlenie jelektroprivodami peremennogo toka [Vector control of AC drives]. Ivanovo, ISPU Pul., 2008. 98 p. (in Russian)
13. Shihabudheen K.V., Pillai G.N. Recent Advances in Neuro-Fuzzy System: A Survey. Knowledge-Based Systems. 2018, vol. 152, pp. 136-162.doi:10.1016/j.knosys.2018.04.014
14. Sentsov E.V., Mesherekov V.N. Synthesis of a neuroregulator with predictive control of the electric drive of the actuators of technological units of metallurgical production. 18th International Scientific Technical Conference Alternating Current Electric Drives (ACED). IEEE, 2021. 9462259. doi: 10.1109/ACED50605.2021.9462259
15. Cheon K., Kim J., Hamadache M., Lee D. On Replacing PID Controller with Deep Learning Controller for DC Motor System. J. Autom.Control Eng. 2015, no. 6(3), pp. 452-456. doi: 10.12720/joace.3.6.452-456
16. Kashirskich V.G. Dinamicheskaya identifikatsiya asinkhronnykh elektrodvigateley [Dynamic identification of induction motors]. Kemerovo, GU KuzGTU Publ., 2005. 139 p. (in Russian)
17. Usoltsev A.A. Chastotnoe upravlenie asinhronnymi dvigateljami [Frequency control of asynchronous motors]. St. Petersburg, St. Petersburg State University ITMO Publ., 2006. 94 p. (in Russian)
18. Isakov A.S., Ushakov A.V. Realizacija nabljudatelja sostojanij asinhronnogo dvigatelja s korotkozamknutym rotorom v bezdatchikovoj sisteme vektornogo upravlenija [Implementation of the state observer of an induction motor with a squirrel-cage rotor in a sensorless vector control system]. Scientific and technical bulletin. St. Petersburg State University ITMO, 2007, no. 38, pp. 280-286. (in Russian)
19. Sinjukova T.V., Sentsov E.V. Synthesis of the rotor frequency of the asynchronous rotor based on the concept NN. Pribory i sistemy. Upravlenie, kontrol, diagnostika [Instruments and Systems: Monitoring, Control, and Diagnostics], 2019, no. 9, pp. 13-20. doi: 10.25791/pribor.09.2019.870 (in Russian)
20. Pankratov V.V., Kotin D.A. Adaptivnye algoritmy bezdatchikovogo vektornogo upravlenija asinhronnymi jelektroprivodami podemno-transportnyh mehanizmov [Adaptive algorithms for sensorless vector control of asynchronous electric drives of lifting and transport mechanisms]. Novosibirsk, NGTU Publ., 2012. 143 p. (in Russian)
21. Moskalenko V.V. Jelektricheskij privod: uchebnoe posobie dlya sred. prof. obrazovaniya [Electric Drive]. Moscow, Akademiya Publ., 2004. 368 p. (in Russian)
22. Langraf S.V., Glazyrin A.S., Glazyrina T.A., Afanasyev A.S., Timoshkin V.V. Investigation of the parametric robustness of a sensorless vector asynchronous electric drive with Kalman identifier. Izvestiya Tomskogo politekhnicheskogo universiteta [News of the Tomsk Polytechnic University], 2010, vol. 317, no. 4, pp. 120-123. (in Russian)
23. Glazyrin A.S. Sensorless control of an asynchronous electric drive with a synergistic controller. Izvestiya Tomskogo politekhnicheskogo universiteta [News of the Tomsk Polytechnic University], 2012, vol. 321, no. 4, pp. 107-111. (in Russian)
24. Afanasev K.S. Razrabotka nabljudatelja sostojanija dlja asinhronnogo jelektroprivoda s povyshennoj parametricheskoj robastnostju. Kand. Diss. [Development of a state observer for an asynchronous electric drive with increased parametric robustness. Kand. Diss.]. Tomsk, 2015, 106 p. (in Russian)
25. Aizenberg I. Complex-Valued Neural Networks with Multi-Valued Neurons. Berlin: Springer, 2011. 264 p.
26. Veynmeyster, A.V.Kosvennoe izmerenie skorosti vrashcheniya v elektroprivode s asinkhronnym dvigatele na osnove identifikatora sostoyaniya. Kand. Diss. [Indirect measurement of rotation speed in an electric drive with an asynchronous motor based on a state identifier. Kand. Diss. abstract]. St. Petersburg, 2013, 17 p. (in Russian)
27. Litvinenko A.M. Baranov D.S. Adaptive control system for the electric drive of the washing machine. Electrotekhnika [Electrical engineering], 2020, no. 10, pp. 31-36. (In Russian)
28. Schmidhuber J. Deep Learning in neural networks: An overview. Neural Networks. 2015, vol. 61, рp. 85-117. doi: 10.1016/j.neunet.2014.09.003
29. Dotsenko V.V., Sentsov E.V., Litvinenko A.M., Mesherekov V.N., Valtchev S. A Model for Predicting Wind Speed and the Probability of a Wind Gust. 3rd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA). IEEE, 2021, pр. 576-579. doi: 10.1109/SUMMA53307.2021.9632142
Sentsov E.V., Meshcheryakov V.N. Simulation of Electric Drive Sensorless Control System for the Furnace Roller Table Using Neural Network Objects. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2023, no. 1(58), pp. 49-56. (In Russian). https://doi.org/10.18503/2311-8318-2023-1(58)-49-56