Recurrent single-neural PID control for Gunt-RT030 pressure control unit
Corressponding author's email:
ncngon@ctu.edu.vnDOI:
https://doi.org/10.54644/jte.63.2021.65Keywords:
RBF neural network, PID, model identification, online training, Jacobian informationAbstract
This study aims to develop a recurrent single neural PID (Proportional Integral Derivative) controller to control unknown plants, experimentally applying on the Gunt-RT030 pressure control unit. The PID controller is organized as a recurrent single neuron with 4 inputs. Where, an input receives feedback value from previous output of the controller; and 3 remaining inputs receive corresponding components of the PID controller. In order to update the weights of neuron, an online training algorithm needs a value of the controlled plant's sensitivity, called the Jacobian information. Thus, a radial basic function (RBF) neural network is also trained online for model identification and estimation of that Jacobian information. Experimental results on the Gunt-Hamburg RT030 pressure control unit, and comparison with the classical PID provided by the manufacturer show that the recurrent single neural PID controller can be self-tuning and obtain better responses with setting time shortened (archived 6±0.3 seconds), overshoot reduced and steady-state error eliminated.
Downloads: 0
References
M.A. Johnson and M.H. Moradi, Chapter 8, in: PID Control - New Identification and Design Methods, pp. 297-337, Springer-Verlag London Ltd, 2005.
J. Chen and T.-C. Huang, Applying neural network to on-line updated PID controllers for nonlinear process control, J. of Process Control, No.14, pp. 211–230, 2004.
Lee C.-h., Y.-H. Lee, A Novel robust PID controller design by fuzzy nerual network, IEEE Proc. of the American Control Conf. (ACC2002), pp. 1561-1566, 2002.
Z. She, D. Hu, J. Liu and Q. Liang, Single Neuron Speed Control Based on Current FAC for PMSM Vector Control, 2019 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), pp. 1-5, 2019. doi: 10.1109/APPEEC45492.2019.8994676.
M.-g. Zhang, X.-g. Wang and M.-q. Liu, Adaptive PID Control Based on RBF Neural Network Identification, IEEE Proc. of 17th Inter. Conf. on Tools with Artificial Intelligence (ICTAI'05), pp.681-683, 2005.
J.B. Gomm and D.L. Yu, Selecting radial basis function network centers with recursive orthogonal least squares training, IEEE Trans. Neural Network, 11 (2), pp. 306–314, 2000.
Chi-Ngon Nguyen and Minh Hoang Nguyen, Improvement of power output of the Wind Turbine by pitch angle control using RBF neural network, Inter. J. of Mechanical Engineering and Technology (IJMET), Vol. 10, Issue 10, pp. 64-74, 2019.
J. Jiao, J. Chen, Y. Qiao, W. Wang, C. Wang and L. Gu, Single Neuron PID Control of Agricultural Robot Steering System Based on Online Identification, IEEE 4th Inter. Conf. on Big Data Computing Service and Applications (BigDataService), Bamberg, pp. 193-199, 2018.
C. Rosales, C.M. Soria, and F.G. Rossomando, Identification and adaptive PID Control of a hexacopter UAV based on neural networks, Inter. J. Adaptive Control and Signal Process, No. 33, pp. 74– 91, 2019.
X.-d. Zhang, Y.-m. Cheng and Y.-x. Hao, Application of Single Neuron Adaptive PID Approach in Rolling Tension Control, 2nd Inter. Conf. on Materials Science, Machinery and Energy Engineering (MSMEE 2017), Advances in Engineering Research, Vol. 123, Atlantis Press, pp. 1185-1190, 2017.
M. Rif'an, F. Yusivar and B. Kusumoputro, Adaptive PID controller based on additional error of an inversed-control signal for improved performance of brushless DC motor, 15th Inter. Conf. on Quality in Research: Inter. Sympo. on Electrical and Comp. Engineering, pp. 315-320, 2017.
J. Liu, On a method of single neural PID feedback compensation control, Third Inter. Confer. on Artificial Intelligence and Pattern Recognition (AIPR), Lodz, pp. 1-4, 2016.
Jiao, J. Chen, Y. Qiao, W. Wang, C. Wang and L. Gu, Single Neuron PID Control of Agricultural Robot Steering System Based on Online Identification, 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService), Bamberg, pp. 193-199, 2018.
Liang, Y., S. Xu , K. Hong, G. Wang and T. Zeng, Neural network modeling and single-neuron proportional–integral–derivative control for hysteresis in piezoelectric actuators, Measurement and Control, vol. 52, issue 9-10, pp. 1362-1370, 2019.
Le Minh Thanh, Luong H. Thuong, Phan T. Loc, Chi-Ngon Nguyen, Delta robot control using single neuron PID algorithms based on recurrent fuzzy neural network identifiers, Inter. [15]Journal of Mechanical Engineering and Robotics Research, Vol. 9, No. 10, pp. 1411-1418, 2020.
Nguyễn Chí Ngôn và Đặng Tín, Điều khiển PID một nơron thích nghi dựa trên bộ nhận dạng mạng nơron mờ hồi qui áp dụng cho hệ thanh và bóng, Tạp chí khoa học Đại học Cần Thơ, số 20a, tr. 159-168, 2011.
Nguyễn Phùng Hưng, Phạm Kỳ Quang, Võ Hồng Hải, Bộ điều khiển PID chỉnh tham số bằng mạng nơ-ron dùng cho máy lái tự động tàu thủy, Giao thông Vận tải, số 9, tr.67-70, 2015.
Huỳnh Thế Hiển, Nguyễn Hoàng Dũng và Huỳnh Minh Vũ, Bộ điều khiển PID dựa trên mạng nơ-ron hàm cơ sở xuyên tâm, Tạp chí khoa học Đại học Cần Thơ, tập 54, số 7, tr.: 9-19, 2018.
Nguyễn Văn Đông Hải và Ngô Văn Thuyên, Xây dựng bộ điều khiển PID-neuron cho hệ con lắc ngược quay, Tạp chí Giáo dục Kỹ thuật, ĐH SPKT TP. Hồ Chí Minh, số 23, tr. 37-45, 2012.
Nguyễn Chí Ngôn và Trần Thanh Tú, Điều khiển PID thích nghi cho hệ ổn định áp suất dựa trên bộ nhận dạng dùng mạng nơ-ron hàm cơ sở xuyên tâm, Tạp chí Khoa học và Công Nghệ, ĐH Đà Nẵng, số 11(60), Quyển 1, tr. 6-12, 2012.
G.U.N.T. Gerätebau GmbH. Experiment Instructions - RT010-RT060 Principles of Control Engineering. Barsbüttel Germany, Publication-no.: 918.000 00 A 0X0 02 (A), 2004.
Labjack, U12 Datasheet, 2020.
Jinkun Liu, Radial Basis Function (RBF) Neural Network Control for Mechanical Systems – Design, Analysis and Matlab Simulation, Springer-Verlag Berlin Heidelberg, 365 pages, 2013.
Downloads
Published
How to Cite
Issue
Section
Categories
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
