«Automation and Informatization of the fuel and energy complex»

Design of a neural network PID regulator for a direct current motor control system

UDC: 681.51
DOI: -

Authors:

¹ Tyumen Industrial University, Tyumen, Russia
¹ Tyumen Industrial University, Tyumen, Russia

Keywords: PID controller, modeling, neural network, back propagation method, adaptive control, DC motor, field programmable logic arrays (FPGA)

Annotation:

Programmable logic controllers (PLCs), commonly utilized in various industries, lack the ability to dynamically adjust proportionally-integral-differentiating (PID) controllers in real-time using neural networks. The authors of the article designed a DC motor speed control system based on a PID controller, adjusted by means of using a neural network by the error back propagation method using field programmable logic arrays (FPGA), The neural network PID controller is built on a modular principle. The direct propagation module is used to perform the direct propagation operation from the input layer to the output layer. The PID module implements the transfer of the calculated control impact on registers level and is responsible for completing the output of the control sum The main state machine module generates an enable signal that controls the sequential execution of each module. The mistake back propagation and weight updating module updates the weights of each network layer. ModelSim and Simulink are used to simulate and test the system. The results show that the developed system can perform self-tuning of PID controller parameters, and also has high operational reliability and real-time performance.

Bibliography:

1. Spasibov V.M., Kabeeva N.V. Tsifrovizatsiya neftegazovogo mestorozhdeniya i kadrovyy potentsial // Neft'. Gaz. Novatsii. – 2018. – № 12. – S. 24–28.
2. Razrabotka uchebnogo programmno-tekhnicheskogo kompleksa dlya issledovaniya algoritmov avtomaticheskoy nastroyki regulyatorov / V.E. Popad'ko, R.L. Barashkin, P.K. Kalashnikov, D.K. Danilov // Avtomatizatsiya, telemekhanizatsiya i svyaz' v neftyanoy prom-sti. – 2021. – № 8(577). – S. 63–68. – DOI: 10.33285/0132-2222-2021-8(577)-63-68
3. Ha Quang Thinh Ngo, Huynh Duc Nguven, Quang Vinh Truong. A Design of Pid Controller Using FPGA-Realization for Motion Control Systems // 2020 Int. Conf. on Advanced Computing and Applications (ACOMP), Quy Nhon, Vietnam, Nov. 25–27, 2020. – IEEE, 2020. – P. 150–154. – DOI: 10.1109/ACOMP50827.2020.00030
4. Huaiqin Liu, Qinghe Yu, Qu Wu. PID Control Model Based on Back Propagation Neural Network Optimized by Adversarial Learning-Based Grey Wolf Optimization // Applied Sciences. – 2023. – Vol. 13, Issue 08. – P. 4767. – DOI: 10.3390/app13084767
5. Bouzaiene R., Hafsi S., Bouani F. Adaptive neural network PID controller for nonlinear systems // 2021 IEEE 2nd Int. Conf. on Signal, Control and Communication (SCC), Tunis, Tunisia, Dec. 20–22, 2021. – P. 264–269. – DOI: 10.1109/SCC53769.2021.9768352
6. A backpropagation neural network controller trained using PID for digitally-controlled DC-DC switching converters / Jianfu Liu, Tingcun Wei, Nan Chen [et al.] // 2021 IEEE 16th Conf. on Industrial Electronics and Applications (ICIEA), Chengdu, China, Aug. 01–04, 2021. – P. 946–951. – DOI: 10.1109/ICIEA51954.2021.9516423
7. Haoyu Xi, Qingsong Wang. Design of Back Propagation Neural Network PID Control for Boost Converter // 2021 IEEE Sustainable Power and Energy Conf. (iSPEC), Nanjing, China, Dec. 23–25, 2021. – P. 3889–3893. – DOI: 10.1109/iSPEC53008.2021.9735583
8. Hardware implementation and improvement of BP neural network based on FPGA / Yang J., Du W., Wu S. [et al.] // Computer Engineering and Design. – 2018. – Vol. 39. – P. 1733–1737.
9. Zhang Y., Dai W. Design and verification of neural network sliding mode controller based on FPGA // 2021 IEEE Int. Conf. on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China, Jan. 15–17, 2021. – P. 255–258.
10. Zhu R., Wu H. DC motor speed control system based on incremental PID algorithm // Instrum. Tech. Sens. – 2017. – Vol. 7. – P. 121–126.
11. Liu H., Yang Z., Ai Y. Research on DC motor control system based on particle swarm optimization algorithm // Modern Electronic Tech. – 2018. – Vol. 41. – P. 121–124.