Application of Q Learning-Based Self-Tuning PID with DRNN in the Strip Flatness and Gauge System

Yu Lian Jiang; Jian Chang Liu; Shu Bin Tan

doi:10.4028/www.scientific.net/AMM.494-495.1377

Paper Titles

Robust Speed Control Algorithm of Welding Wire Feed System Based on the State Space Model
p.1358

Control Point Optimization and Simulation of Dental Arch Generator
p.1364

Study on Six-DOF Electric Platform Adaptive Control
p.1368

Research and Design of Embedded CNC System Based on CAN Bus Technology
p.1373

Application of Q Learning-Based Self-Tuning PID with DRNN in the Strip Flatness and Gauge System
p.1377

The Design of the Intelligent Robot Wireless Communication Based on the Network Control System
p.1381

Simulations on the Stability and Stabilization Method for Random Long Delay Network Control
p.1385

Design of FPGA Image Acquisition System for Search-Rescue Robot Navigation
p.1389

Torque Ripple Reduction of Switched Reluctance Motor by Optimizing Stator Pole Type
p.1395

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 494-495Application of Q Learning-Based Self-Tuning PID...

Application of Q Learning-Based Self-Tuning PID with DRNN in the Strip Flatness and Gauge System

Abstract:

In view of the process of automatic flatness control and automatic gauge control that is a nonlinear system with multi-dimensions, multi-variables, strong coupling and time variation, a novel control method called self-tuning PID with diagonal recurrent neural network (DRNN-PID) based on Q learning is proposed. It is able to coordinate the coupling of flatness control and gauge control agents to get the satisfactory control requirements without decoupling directly and amend output control laws by DRNN-PID adaptively. Decomposition-coordination is utilized to establish a novel multi-agent system for coordination control including flatness agent, gauge agent and Q learning agent. Simulation result demonstrates the validity of our proposed method.

You might also be interested in these eBooks

Current Development of Mechanical Engineering and Energy

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 494-495)

Pages:

1377-1380

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.494-495.1377

Citation:

Cite this paper

Online since:

February 2014

Authors:

Yu Lian Jiang*, Jian Chang Liu, Shu Bin Tan

Keywords:

Coordinated Control, Diagonal Recurrent Neural Network, Gauge Control, Multi-Agent (MA), Q Learning, Strip Flatness

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] S. Kapetanakis, D. Kudenko, M. Strens. Reinforcement learning approaches to coordination multi-agent systems [C]. Lecture Notes in Computer Science, 2003: 18-32.

DOI: 10.1007/3-540-44826-8_2

Google Scholar

[2] Kyriakos G. Vamvoudakis, Frank L. Lewis, Greg R. Hudas. Multi-agent differential graphical games: online adaptive learning solution for synchronization with optimality [J]. Automatica, 2012 48 (8) 1598-1611.

DOI: 10.1016/j.automatica.2012.05.074

Google Scholar

[3] Rajneesh Sharma, M. Gopal. Synergizing reinforcement learning and game theory–a new direction for control [J]. Applied Soft Computing, 2010 10 (3) 675-688.

DOI: 10.1016/j.asoc.2009.10.020

Google Scholar

[4] Xianghua Liu. Prospects for variable gauge rolling: technology, theory and application [J]. Journal of Iron and Steel Research International, 2011 18 (1) 01-07.

Google Scholar

[5] Gang Wu, Yikang Sun. Application of multivariable fuzzy predictive control in AGC-AFC [J]. Journal of University of Science and Technology Beijing, 1999 21 (4) 403-405.

Google Scholar

[6] Chao-Chee Ku, Kwang Y. Lee, R.M. Edwards. Improved nuclear reactor temperature control using diagonal recurrent neural networks [J]. IEEE Transactions on Nuclear Science, 1992 39 (6) 2298-2308.

DOI: 10.1109/23.211440

Google Scholar

[7] Tom M. Mitchell. Machine Learning [M]. China Machine Press, (2003).

Google Scholar

[8] Lucian Busoniu, Robert Babuska, Bart D. Schutter. A comprehensive survey of multiagent reinforcement learning [J]. IEEE Transactions on Systems, Man and Cybernetics, 2008 38 (2) 156-172.

DOI: 10.1109/tsmcc.2007.913919

Google Scholar