OPTIMIZATION OF PID PARAMETERS OF SERVO SYSTEMS USING A GENETIC ALGORITHM AND A NEURAL NETWORK CLASSIFIER
Abstract
Machine learning algorithms play a vital role in enhancing the performance of industrial systems, providing high precision and operational efficiency in real time. In servo motor control systems, these algorithms help reduce noise and vibration, improving efficiency and extending equipment lifespan. This article examines various types of noise that occur and their negative impact on industrial processes. The primary research objective is to optimize PID controller parameters in servo systems using a combined algorithm that combines neural networks and genetic algorithms. Unlike traditional methods such as genetic algorithms (GA) and particle swarm optimization (PSO), which suffer from slow convergence and risk of motor damage, the proposed solution is based on a control software platform. This platform ensures safe real-time interaction with the servo motor. A CAN Bus-based control system has been developed that enables developers to: read all servo motor parameters (speed, current, voltage, encoder position); modify PID coefficients with a single click, eliminating the need for manual tuning as in MOTO-MASTER. The implementation of the developed control system allowed the use of a trained neural classifier to constrain PID parameters within safe limits, reducing search space and accelerating the optimization process. Experimental results on SPH-S servo motors demonstrated significant reduction in noise and mechanical vibrations during real-time operation while maintaining stability across a wide speed range (0-1500 rpm).
References
1. Saini S., Hernandez J., Nayak S. Auto-Tuning PID Controller on Electromechanical Actuators Using Machine Learning, SAE Technical Paper, 2023.
2. Shi G., Dai C., Liu S., Li D., Ding Y. The Design of a Reference Model-Based Proportional-Integral-Derivative Controller with the Generalized Derivative, 2023 23rd International Conference on Control, Automation and Systems (ICCAS). IEEE, 2023, pp. 547-552.
3. Majeed D.A., Yaseen M., Ghaffori A.J., Ahmed S.R., Hakim B.A., Hussain A.-S.T. Advanced Optimiza-tion Techniques for CNC Machining: A Comparative Study of Genetic Algorithms, Simulated Anneal-ing, and Particle Swarm Optimization, 2024 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA). IEEE, 2024, pp. 1-6.
4. Akhmad Z. Sravnenie kolets PID-regulirovaniya i nechetkikh regulyatorov dlya regulirovaniya skorosti servodvigatelya [Comparison of PID control loops and fuzzy controllers for servo motor speed control], Mater. XV vserossiyskoy konferentsii s mezhdunarodnym uchastiem "Mashinostroenie: traditsii i inno-vatsii (MTI –2022)" [Proceedings of the XV All-Russian Conference with International Participation "Mechanical Engineering: Traditions and Innovations (MIT-2022)"]. Moscow: Moskovskiy gosudar-stvennyy tekhnologicheskiy universitet "STANKIN", 2022, pp. 141-148.
5. Wang J.S., Wang J.C., Wang W. Self-tuning of PID parameters based on particle swarm optimization, Control and Decision, 2005, Vol. 20, pp. 73-76.
6. Mishra D.P., Raut U., Gaur A.P., Swain S., Chauhan S. Particle swarm optimization and genetic algo-rithms for PID controller tuning, 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE, 2023, pp. 189-194.
7. Isa S.S.M., Azri M., Ibrahim Z., Talib M., Sulaiman M., Meng Q., Khanipah N.H.A., Rahim N. Experi-mental investigation on scaling factor of fuzzy logic speed control for induction motor drives, 2017 6th International Conference on Electrical Engineering and Informatics (ICEEI), 2017.
8. Servoprivod SPŠ [Servo drive SPSh]. Available at: https://www.servotechnica.ru/catalog/type/brand/ index.pl?id=18 (accessed 19 April 2025).
9. Servotekhnika [Servo technology]. – URL: http://servotechnica.ru/ (дата обращения: 18.04.2025).
10. Balachandra D., Mani K., Ramesh B. Anti-windup Robust Controller Considering Saturation of Current and Speed for Speed Servo System, International journal of engineering research and technology, 2014.
11. Kaneko K., Ohishi K. Anti-windup robust controller considering motor dynamics for speed servo sys-tem, 2013 IEEE International Conference on Mechatronics (ICM), 2013.
12. Hinokimoto K. [et al.]. A Data‐driven Design Method of PID Controller with Noise Filter, IEEE Transactions on Electrical and Electronic Engineering, 2017.
13. Zhivkovich T., Draganovich M. Zashchita ot shuma v okruzhayushchey srede goroda Belgrada [Noise protection in the environment of the city of Belgrade], Alternative Energy and Ecology, 2015.
14. Akhmad Z., Martinov G.M. Razrabotka sistemy upravleniya servoprivodom na baze shiny CAN i mikrokomp'yutera Raspberry Pi [Development of a servo drive control system based on the CAN bus and the Raspberry Pi microcomputer], Avtomatizatsiya v promyshlennosti [Automation in Industry], 2025, No. 5.
15. Kanojiya R.G., Meshram P.M. Optimal tuning of PI controller for speed control of DC motor drive using particle swarm optimization, 2012 International Conference on Advances in Power Conversion and Energy Technologies (APCET), 2012.
16. Kamal M., Mathew L., Chatterji S. Speed control of brushless DC motor using intelligent controllers, 2014 Students Conference on Engineering and Systems, 2014.
17. Meena D., Chauhan S. Speed control of DC servo motor using genetic algorithm, 2017 International Conference on Information, Communication, Instrumentation and Control (ICICIC), 2017.
18. Mishra P., [et al.]. Optimization of PID Controller with First Order Noise Filter, 2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE), 2015.
19. Kravchenko Yu.A. Postroenie prognoznykh modeley dinamicheskikh sistem na osnove integratsii ney-ronnykh setey i geneticheskikh algoritmov [Construction of predictive models of dynamic systems based on the integration of neural networks and genetic algorithms], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2006, Vol. 64, No. 9-1, pp. 103-104.
20. Gladkov L.A., Kureychik V.V., Kureychik V.M. Geneticheskie algoritmy [Genetic algorithms], 2010
