VERİ GÜDÜMLÜ KONTROLDE VERİ KALİTESİNİN KRİTİK ROLÜ: BİR DA MOTOR UYGULAMASI

Abstract

Bu çalışmada, veri güdümlü kontrol (VGK) kapsamında doğru akım (DA) motorlarının hız denetiminde giriş verisi türlerinin etkisi incelenmiştir. Bu amaçla, klasik PID ve öğrenme tabanlı olarak çalışan Yapay Sinir Ağları (YSA) denetleyicileri karşılaştırılmıştır. VGK, bir sistemin matematiksel modeline ihtiyaç duymadan giriş-çıkış verilerine dayalı olarak denetim parametrelerinin hesaplanabilmesini sağlayan bir yaklaşımdır. Bu kapsamda, basamak, sinüs, testere dişi, rastgele ve karışık olmak üzere beş farklı türde sentetik veri seti üretilmiş, normalize edilerek DA motorlara giriş voltajı olarak uygulanmış ve motor milinin çıkış hızları ölçülmüştür. Toplanan veriler ile tasarlanan veri güdümlü PID ve YSA denetleyiciler en uygun veri seti/ denetleyici çiftini tespit etmek için gerçek zamanlı deneylere tabi tutulmuştur. Gerçek zamanlı deneylerden elde edilen sonuçlar, ortalama karesel hata, yükselme süresi, oturma süresi ve en yüksek yüzde aşma gibi performans ölçütleri ile değerlendirilmiştir. Ayrıca, DA motorun kontrol yanıtlarını optimize etmek amacıyla bulanık mantık tabanlı bir ölçekleme çarpanı tahmin sistemi geliştirilmiştir. Deneysel bulgular, öğrenme tabanlı stratejilerle eğitilen YSA denetleyicilerinin, özellikle yüksek çeşitlilik içeren veri setleri ile daha başarılı performans sergilediğini göstermiştir.

Keywords

• DA Motor Kontrolü
• Veri Güdümlü Kontrol
• Yapay Sinir Ağları
• PID
• Sentetik Veri

THE CRITICAL ROLE OF DATA QUALITY IN DATA-DRIVEN CONTROL: A DC MOTOR CASE STUDY

Abstract

This study looked into the effect of different forms of input data on the speed control of direct current (DC) motors under data-driven control (DDC). For this purpose, traditional PID and learning-based Artificial Neural Network (ANN) controllers were evaluated. DDC is a method for calculating control parameters based on input-output data without the requirement for a mathematical model of the system. In this context, five distinct types of synthetic data sets, namely step, sine, sawtooth, random, and mixed, were produced, normalized, and applied as input voltage to DC motors, with the output shaft speeds monitored. Real-time experiments were performed on the data-driven PID and ANN controllers developed with the obtained data to determine the best dataset/controller combination. The results of the real-time experiments were evaluated using performance criteria such as mean squared error, rising time, settling time, and maximum percentage overshoot. In addition, a fuzzy logic-based scaling factor prediction system was built to optimize the DC motor's control responses. The experimental results show that ANN controllers trained with learning-based strategies perform better, especially with high-diversity data sets.

Keywords

• DC Motor Control
• Data-Driven Control
• Artificial Neural Network
• PID
• Synthetic Data

References

1. Baciu, A., Lazar, C., 2023. Iterative feedback tuning of model-free intelligent PID controllers. Actuators, 12(2), 56. https://doi.org/10.3390/act12020056
2. Carlet, P.G., Favato, A., Bolognani, S., Dorfler, F., 2020. Data-driven predictive current control for synchronous motor drives. IEEE Energy Conversion Congress and Exposition (ECCE), 5148-5154. https://doi.org/10.1109/ECCE44975.2020.9235958
3. Chaudhary, H., Khatoon, S., Singh, R., 2017. ANFIS based speed control of DC motor. IEEE International Conference on Innovative Applications of Computational Intelligence on Power, Energy and Controls with Their Impact on Humanity (CIPECH), 63-67. https://doi.org/10.1109/CIPECH.2016.7918738
4. Chi, R., Hou, Z., Jin, S., Huang, B., 2018. Computationally efficient data-driven higher order optimal iterative learning control. IEEE Transactions on Neural Networks and Learning Systems, 29(12), 5971-5980. https://doi.org/10.1109/TNNLS.2018.2814628
5. Hamoodi, S.A., Sheet, I.I., Mohammed, R.A., 2019. A comparison between PID controller and ANN controller for speed control of DC motor. International Conference on Electrical, Communication, Computer, Power and Control Engineering (ICECCPCE), 221-224. https://doi.org/10.1109/ICECCPCE46549.2019.203777
6. Hou, Z., Chi, R., Gao, H., 2017. An overview of dynamic-linearization-based data-driven control and applications. IEEE Transactions on Industrial Electronics, 64(5), 4076-4090. https://doi.org/10.1109/TIE.2016.2636126
7. Ismeal, G.A., Kyslan, K., Fedák, V., 2014. DC motor identification based on recurrent neural networks. 16th International Conference on Mechatronics (Mechatronika), 701-705. https://doi.org/10.1109/MECHATRONIKA.2014.7018347
8. Jeng, J.C., Ge, G.P., 2016. Disturbance-rejection-based tuning of proportional-integral-derivative controllers by exploiting closed-loop plant data. ISA Transactions, 62, 312-324. https://doi.org/10.1016/J.ISATRA.2016.02.011

9. Kamal, M.M., Mathew, L., Chatterji, S., 2014. Speed control of brushless DC motor using intelligent controllers. IEEE Conference on Engineering and Systems for Global Sustainability (SCES), 1-5. https://doi.org/10.1109/SCES.2014.6880121
10. Keles, Z., Sonugur, G., Alcın, M., 2023. The modeling of the Rucklidge chaotic system with artificial neural networks. Chaos Theory and Applications, 5(2), 59-64. https://doi.org/10.51537/CHAOS.1213070
11. Khan, S., Paul, A., Sil, T., Basu, A., Tiwari, R., Mukherjee, S., Mondal, U., Sengupta, A., 2017. Position control of a DC motor system for tracking periodic reference inputs in a data driven paradigm. International Conference on Intelligent Control, Power and Instrumentation (ICICPI), 17-21. https://doi.org/10.1109/ICICPI.2016.7859665
12. Mishra, M., 2009. Speed control of DC motor using novel neural network configuration. National Institute of Technology Rourkela, Odisha, India. http://ethesis.nitrkl.ac.in/245/1/10502014.pdf
13. Mohamed, T.L.T., Mohamed, R.H.A., Mohamed, Z., 2010. Development of auto tuning PID controller using graphical user interface (GUI). 2nd International Conference on Computer Engineering and Applications (ICCEA), 491-495. https://doi.org/10.1109/ICCEA.2010.101
14. Moussavi, S.Z., Alasvandi, M., Javadi, S., 2012. Speed control of permanent magnet DC motor by using combination of adaptive controller and fuzzy controller. International Journal of Computer Applications, 52(20), 11-15. https://doi.org/10.5120/8316-1774
15. Munagala, V.K., Jatoth, R.K., 2022. A novel approach for controlling DC motor speed using NARXnet based FOPID controller. Evolving Systems, 14, 101-116. https://doi.org/10.1007/s12530-022-09437-1
16. Özbaltan, M., Çaşka, S., 2024. Altitude control of quadcopter with symbolic limited optimal discrete control. International Journal of Dynamics and Control, 12(5), 1533-1540. https://doi.org/10.1007/s40435-023-01278-3
17. Purnama, H.S., Sutikno, T., Alavandar, S., Subrata, A.C., 2019. Intelligent control strategies for tuning PID of speed control of DC motor - A review. IEEE Conference on Energy Conversion, 24-30. https://doi.org/10.1109/CENCON47160.2019.8974782
18. Salah, M., Abdelati, M., 2010. Parameters identification of a permanent magnet DC motor. IASTED International Conference on Modelling, Identification and Control, 177-182. https://doi.org/10.2316/P.2010.675-085
19. Suleimenov, K., Do, T.D., 2019. Data-driven LQR for permanent magnet synchronous machines. IEEE Vehicle Power and Propulsion Conference (VPPC), 1-5. https://doi.org/10.1109/VPPC46532.2019.8952466
20. Timurkutluk, B., Ciflik, Y., Sonugur, G., Altan, T., Genc, O., Colak, A.B., 2023. Microstructural design of solid oxide fuel cell electrodes by micro-modeling coupled with artificial neural network. Powder Technology, 425, 118551. https://doi.org/10.1016/J.POWTEC.2023.118551
21. Umlauft, J., Hirche, S., 2020. Feedback linearization based on Gaussian processes with event-triggered online learning. IEEE Transactions on Automatic Control, 65(10), 4154-4169. https://doi.org/10.1109/TAC.2019.2958840
22. Uysal, A., Gokay, S., Soylu, E., Soylu, T., Çaşka, S., 2019. Fuzzy proportional-integral speed control of switched reluctance motor with MATLAB/Simulink and programmable logic controller communication. Measurement and Control, 52(7-8), 1137-1144. https://doi.org/10.1177/0020294019858188
23. Vural, A.M., Bayindir, K.C., 2010. Optimization of parameter set for STATCOM control system. IEEE PES Transmission and Distribution Conference and Exposition: Smart Solutions for a Changing World. https://doi.org/10.1109/TDC.2010.5484230
24. Weng, Y., Wang, N., 2020. Data-driven robust backstepping control of unmanned surface vehicles. International Journal of Robust and Nonlinear Control, 30(9), 3624-3638. https://doi.org/10.1002/RNC.4956
25. Yu, X., Hou, Z., Polycarpou, M.M., Duan, L., 2021. Data-driven iterative learning control for nonlinear discrete-time MIMO systems. IEEE Transactions on Neural Networks and Learning Systems, 32(3), 1136-1148. https://doi.org/10.1109/TNNLS.2020.2980588