比例 (Proportional) ─ 積分 (Integral) ─ 微分 (Derivative) 控制器 (PIDcontroller) 是一個被廣泛使用在工業控制的方法。然而這種控制器面臨最佳化調變的問題。現存的調變法，例如著名的齊格勒－尼科爾斯
方法 (Ziegler-Nichols method)，雖然改善了人工調變的不穩定性，但是隨著控制精度需求的提高，這種方式已經不足以應付需求。對於非線性的控制系統，許多研究結合了類神經網路與 PID 控制器。由於 PID的最佳參數通常是未知的，因此許多有名的類神經網路架構並不適合用於這個問題。在本文中，我們設計一種基於雙神經網路的最佳化方法。比較起現存的最佳化法，在傳統化學工廠的實驗中，就是水壓控制與氣壓控制系統的結果顯示我們的方法可以避免局部最小值的問題。

Proportional–integral–derivative (PID) controller is wildly adopted in industry controller. Industrial controllers suffer from optimal tuning problem. Existing method driven approach like Ziegler-Nichols method is insufficient with the requirement of high accurate control. Due to the nonlinearities of PID tuning, many studies combine neural network with PID controller. Since the correct/best PID parameter are usually unavailable, makes many popular neural networks are not applicable. In this thesis, we design a duel neuron network based optimizer. Compared to existing optimizers in neural network, the experiment results of water pressure control and of steam relief control in a chemical factory show that our optimizer can avoid local minimum problem.

[1] J. Ziegler and N. Nichols, “Optimum settings for automatic controllers,” Trans.
ASME, vol. 64, no. 8, pp. 759–768, 1942.
[2] K. Chien, J. Hrones, and J. Reswick, “On the automatic control of generalized passive systems,” Trans. ASME, vol. 74, pp. 175–185, 1952.
[3] F. Cameron and D. Seborg, “A self-tuning controller with a pid structure,” Int.J. of
Control, vol. 38, pp. 401–417, 1983.
[4] A. H. P. Campos, E. d. M. Fernandes, J. J. d. Silva, and J. S. d. R. Neto, “Autotunned fuzzy based pid deformation control of a shape memory alloy actuated cantilever beam,” 2018 13th IEEE International Conference on Industry Applications
(INDUSCON), pp. 1187–1193, 2018.
[5] Y. Huang and S. Yasunobu, “A general practical design method for fuzzy pid control from conventional pid control,” Ninth IEEE International Conference on Fuzzy
Systems, vol. 2, pp. 969–972, 2000.
[6] A. Taniguchi, S. Mu, S. Shibata, and T. Yamamoto, “An intelligent pid control using
neural networks for pneumatic servo systems,” 2020 International Symposium on
Computer, Consumer and Control (IS3C), pp. 549–552, 2020.
[7] GHARGHORY, S. M. KAMAL, and H. Ahmed, “Optimal tuning of pid controller
using adaptive hybrid particle swarm optimization algorithm,” INTERNATIONAL
JOURNAL OF COMPUTERS COMMUNICATIONS and CONTROL, vol. 7, pp.
104–117, 2012.
[8] J. Lin and C.-H. Lin, “A novel fuel cell system design by using ziegler-nichols-based
intelligent fuzzy controller,” 2013 International Conference on Machine Learning
and Cybernetics, pp. 1268–1271, 2013.
[9] R. Aisuwarya and Y. Hidayati, “Implementation of ziegler-nichols pid tuning
method on stabilizing temperature of hot-water dispenser,” 2019 16th International
Conference on Quality in Research (QIR), pp. 1–5, 2019.
[10] Z. Wang, S. Qiu, R. Song, X. Wang, B. Zhu, and B. Li, “Research on pid parameter
tuning of coordinated control for ultra-supercritical units based on ziegler nichols
method,” 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), pp. 1155–1159, 2019.
[11] P. M. Meshram and R. G. Kanojiya, “Tuning of pid controller using ziegler-nichols
method for speed control of dc motor,” IEEE-International Conference On Advances
In Engineering, Science And Management (ICAESM -2012), pp. 117–122, 2012.
[12] F. Haugen, “Comparing pi tuning methods in a real benchmark temperature control
system modeling, identification and control,” no. 3, pp. 79–91, 2010.
[13] B. K. Jemie Muliadi, “Neural network control system of uav altitude dynamics and
its comparison with the pid control system,” Journal of Advanced Transportation,
p. 18, 2018.
[14] M. Chavoshian, M. Taghizadeh, and M. Mazare, “Hybrid dynamic neural network
and pid control of pneumatic artificial muscle using the pso algorithm,” International
Journal of Automation and Computing, no. 3, pp. 428–438, 2020.
[15] J. Li and A. Gómez-Espinosa, “Improving pid control based on neural network,”
2018 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE), pp. 186–191, 2018.
[16] J. Liu, X. Li, X. Zhang, and X. Chen, “Modeling and simulation of energyregenerative active suspension based on bp neural network pid control,” Shock and
Vibration, p. 8, 2019.
[17] J. Liu, M. Liu, D. Pei, and H. Sun, “Fpga implementation of family service robot
based on neural network pid motion control system,” 2019 International Conference
on Electronic Engineering and Informatics (EEI), pp. 304–308, 2019.
[18] W. Pan and Y. He, “Pid control in oil supply system of hydraulic control unit based
on bp neural network,” 2019 11th International Conference on Intelligent HumanMachine Systems and Cybernetics (IHMSC), pp. 167–170, 2019.
[19] C. Jie, “Flexible joint manipulator controlling algorithm based on neural network
improved pid,” 2021 13th International Conference on Measuring Technology and
Mechatronics Automation (ICMTMA), pp. 419–422, 2021.
[20] Y. Chen, S. Liu, C. Xiong, Y. Zhu, and J. Wang, “Research on uav flight tracking
control based on genetic algorithm optimization and improved bp neural network pid
control,” 2019 Chinese Automation Congress (CAC), pp. 726–731, 2019.
[21] Tang, Wei, L. Wang, J. Gu, , and Y. Gu, “Single neural adaptive pid control for small
uav micro-turbojet engine,” no. 2, 2020.
[22] Suzuki, M., Yamamoto, and T. Tsuji, “A design of neural-net based pid controllers
with evolutionary computation,” IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, pp. 2761–2768.
[23] F. G. Martins, “Tuning pid controllers us ing the itae criterion,” International Journal
of Engineering Education, no. 3, 2005.
[24] C. Nie and M. Z. Zewei Zheng, “Three-dimensional path-following control of a
robotic airship with reinforcement learning,” International Journal of Aerospace Engineering, 2019.
[25] S. Chattopadhyay, S. Bhattacherjee, S. Bandyopadhyay, A. Sengupta, and S. Bhaumik, “Control of single-segment continuum robots: Reinforcement learning vs. neural network based pid,” 2018 International Conference on Control, Power, Communication and Computing Technologies (ICCPCCT), pp. 222–226, 2018.
[26] Z. Guan and T. Yamamoto, “Design of a reinforcement learning pid controller,” 2020
International Joint Conference on Neural Networks (IJCNN), pp. 1–6, 2020.
[27] N. P. Lawrence, G. E. Stewart, P. D. Loewen, M. G. Forbes, J. U. Backstrom, and
R. B. Gopaluni, “Optimal pid and antiwindup control design as a reinforcement
learning problem,” IFAC-PapersOnLine, pp. 236–241, 2020.
[28] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 1998.