Call for Paper

CAE solicits original research papers for the July 2018 Edition. Last date of manuscript submission is June 30, 2018.

Read More

An Adaptive Controller using Radial Basis Function Neural Network with Reinforcement Learning

Niusha Shafiabady, M. A. Nima Vakilian, Dino Isa Published in Artificial Intelligence

Communications on Applied Electronics
Year of Publication: 2015
© 2015 by CAE Journal
10.5120/cae-1581

Niusha Shafiabady, Nima M a Vakilian and Dino Isa. Article: An Adaptive Controller using Radial Basis Function Neural Network with Reinforcement Learning. Communications on Applied Electronics 1(7):7-13, May 2015. Published by Foundation of Computer Science, New York, USA. BibTeX

@article{key:article,
	author = {Niusha Shafiabady and M.a. Nima Vakilian and Dino Isa},
	title = {Article: An Adaptive Controller using Radial Basis Function Neural Network with Reinforcement Learning},
	journal = {Communications on Applied Electronics},
	year = {2015},
	volume = {1},
	number = {7},
	pages = {7-13},
	month = {May},
	note = {Published by Foundation of Computer Science, New York, USA}
}

Abstract

A self-tuning PID control strategy using reinforcement learning is given to deal with conventional tracking control problems. Actor-Critic learning is used to tune PID parameters in an adaptive way to take advantage of the reinforcement learning properties. This policy is model-free and RBF neural network is used to approximate the parameters of PID controller. The critic part is designed to evaluate the actor part's efficiency and compensate its disabilities producing TD error that is calculated by the temporal difference of the value function between successive states in the state transition. The inputs of RBF network are system error, as well as the first and the second order differences of error. Both PSO and gradient descent are used to train the network's parameters and the controller has had a good performance being applied on the four plants.

Reference

  1. Cheng Y H, Yi J Q, Zhao D B. Application of Actor-Critic Learning to Adaptive State Space Construction. Proceeding of the Third International Conference on Machine Learning and Cybernetics. Shanghai, Institute of Electrical and Electronics Engineers Inc. Press, 2004, 26-29.
  2. Kondo T, Ito K. , A Reinforcement Learning with Evolutionary State Recruitment Strategy for Autonomous Mobile Robots Control, Robotics and Autonomous Systems, 2004,46(2), 111-124.
  3. Zhou KT, Zhen L X, Optimal Design of PID Parameters Using Evolutionary Algorithms, Journal of Huaquiao University (Natural Science), 2010, 26(1), 85-88.
  4. Wang X S, Cheng Y H, Sun W Q, Learning Based on Self Organizing Fuzzy Radial Basis Function Network, Lecture Notes in Computer Science, 2006, 3971, 607-615.
  5. Wang Xue-song, Cheng Yu-hu, Sun Wei, A Proposal of Adaptive PID controller, China Univ Mining & Technology, 2007, 17(1), 40-44.
  6. Barto A G, Sutton R S, Anderson C W, Neuronlike Adaptive Elements that can Solve Difficult Learning Control Problems, IEEE transactions on Systems, Man and Cybernetics, 13(5), 834-846.
  7. Teng Fong Chwee, H. R. Siresena, Self-Tuning PID Controllers for Dead Time Processes, IEEE Transaction on Industrial Electronics, VOL. 35, NO. 1.
  8. Niusha Shafiabady, M. Teshnehlab, M. Aliyari, A Comparison of PSO and Backpropagation Combined with LS and RLS in Identification Using Fuzzy Neural Networks, 2006 IEEE International Conference on Industrial Technology.
  9. You-tong, F. , Cheng-zhi, F. , Single neuron network PI control of high reliability linear induction motor for Maglev. Journal of Zhejiang University SCIENCE A, 2010, 8(3):408-411.
  10. Gwo-Ruey Yu and Lun-Wei Huang , "Design of LMI-Based Fuzzy Controller for Two-link Robot Arm using Genetic Algorithms," Proceedings of 2008 CACS International Automatic Control Conference National Cheng Kung University, Tainan, Taiwan, Nov, 21-23, 2008.
  11. A. Oonsivilai and P. Pao-La-Or, "Application of adaptive tabu search for optimum PID controller tuning AVR system," WSEAS Transactions on Power Systems, vol. 3, no. 6, pp. 495–506, 2008.
  12. C. Cao, X. Guo, and Y. Liu, "Research on ant colony neural network PID controller and application," inProceedings of the 8th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD '07), pp. 253–258, 2007.
  13. A. Bagis, "Determination of the PID controller parameters by modified genetic algorithm for improved performance," Journal of Information Science and Engineering, vol. 23, no. 5, pp. 1469–1480, 2007.
  14. K. Sansal, Y. ildiz, Biao Huang, J. Fraser Forbes, Dynamics and variance control of hot mill loopers, Control Engineering Practice, vol. 12, no. 16, 89-100, 2008.
  15. Bin-hu Yang, Wei-dong Yang, Lian-gui Chen, Lei Qu, Dynamic optimization of feed forward automatic gauge control based on extend Kalam Filter, International Journal of Iron and Steel, vol. 15, no. 2, 39-42, 2008.
  16. S. I. Han, K. S. Lee, M. G. Park, and J. M. Lee, "Robust adaptive deadzone and friction compensation of robot manipulator using RWCMAC network," Journal of Mechanical Science and Technology, vol. 25, no. 6, pp. 1583–1594, 2011.
  17. M. M. Fateh and S. Khorashadizadeh, "Robust control of electrically driven robots by adaptive fuzzy estimation of uncertainty," Nonlinear Dynamics, vol. 69, no. 3, pp. 1465–1477, 2012.
  18. Hou, G. l. , Zhang, J. F. , Liu, J. J. , and Zhang, J. H. , "Multiple-Model Predictive Control Based on Fuzzy Adaptive Weights and Its Application to Main-Steam Temperature in Power Plant," IEEE Conference on Industrial Electronics and Applications , pp. 668–673, 2010.
  19. Du, H. P. , and Zhang, N. , "Static Output Feedback Control for Electrohydraulic Active Suspensions via T–S Fuzzy Model Approach," ASME J. Dyn. Syst. , Meas. , Control, 131 (5), p. 051004, 2009.
  20. Daogang Peng, Hao Zhang, Hui Li, and Fei Xia, "Research of Networked Control System Based on Fuzzy Adaptive PID Controller," Journal of Advances in Computer Networks vol. 2, no. 1, pp. 44-47, 2014.
  21. Niusha Shafiabady, Dino Isa, MA Nima Vakilian, (2014). The Proposal of Two New Recurrent Radial Basis Function Neural Networks, International Journal of Computer Applications, 92 (3), 32-39

Keywords

Reinforcement learning, Particle Swarm Optimization, Gradient Descent, Adaptive controller, Radial Basis Function, Fuzzy Neural Network