Adaptive Critic-based Neurofuzzy Controller for the Steam Generator Water Level

In this paper, an adaptive critic-based neurofuzzy controller is presented for water level regulation of nuclear steam generators. The problem has been of great concern for many years as the steam generator is a highly nonlinear system showing inverse response dynamics especially at low operating power levels. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the critic agent is the system feedback which is interpreted as the last action the controller has performed in the previous state. The signal produced by the critic agent is used alongside the backpropagation of error algorithm to tune online conclusion parts of the fuzzy inference rules. The critic agent here has a proportional-derivative structure and the fuzzy rule base has nine rules. The proposed controller shows satisfactory transient responses, disturbance rejection and robustness to model uncertainty. Its simple design procedure and structure, nominates it as one of the suitable controller designs for the steam generator water level control in nuclear power plant industry.

[1]  Alexander G. Parlos,et al.  Nonlinear control of U-tube steam generators via H∞ control , 2000 .

[2]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[3]  Manfred Morari,et al.  Level control in the steam generator of a nuclear power plant , 2000, IEEE Trans. Control. Syst. Technol..

[4]  Yoon Joon Lee,et al.  Design of an adaptive predictive controller for steam generators , 2003 .

[5]  Lionel Jouffe,et al.  Fuzzy inference system learning by reinforcement methods , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[6]  Alois Höld.  UTSG-2—A Theoretical Model Describing the Transient Behavior of a Pressurized Water Reactor Natural-Circulation U-Tube Steam Generator , 1990 .

[7]  Byung Hak Cho,et al.  Design of stability-guaranteed fuzzy logic controller for nuclear steam generators , 1996 .

[8]  Byung Hak Cho,et al.  Design of stability and performance robust fuzzy logic gain scheduler for nuclear steam generators , 1997 .

[9]  C. S. George Lee,et al.  Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems , 1994, IEEE Trans. Fuzzy Syst..

[10]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[11]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[12]  Paul J. Werbos,et al.  Applications of advances in nonlinear sensitivity analysis , 1982 .

[13]  Bernard Widrow,et al.  Punish/Reward: Learning with a Critic in Adaptive Threshold Systems , 1973, IEEE Trans. Syst. Man Cybern..

[14]  S Grossberg,et al.  Pavlovian pattern learning by nonlinear neural networks. , 1971, Proceedings of the National Academy of Sciences of the United States of America.

[15]  I. Pavlov.  Conditioned Reflexes: An Investigation of the Physiological Activity of the Cerebral Cortex , 1929 .

[16]  R. Godson.  Elements of intelligence , 1979 .

[17]  R. Bellman.  Dynamic programming. , 1957, Science.

[18]  John S. Edwards,et al.  The Hedonistic Neuron: A Theory of Memory, Learning and Intelligence , 1983 .

[19]  Paul J. Werbos,et al.  New directions in ACDs: keys to intelligent control and understanding the brain , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[20]  A. Parlos,et al.  Gain-Scheduled Nonlinear Control of U-Tube Steam Generator Water Level , 1992 .

[21]  Man Gyun Na,et al.  Auto-tuned PID controller using a model predictive control method for the steam generator water level , 2001 .

[22]  Chuan-Kai Lin,et al.  Adaptive critic autopilot design of Bank-to-turn missiles using fuzzy basis function networks , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[24]  Man Gyun Na.  Design of a genetic fuzzy controller for the nuclear steam generator water level control , 1998 .

[25]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[26]  Paul J. Werbos,et al.  The roots of backpropagation , 1994 .

[27]  S.R. Munasinghe,et al.  Adaptive neurofuzzy controller to regulate UTSG water level in nuclear power plants , 2005, IEEE Transactions on Nuclear Science.

[28]  Dimitri P. Bertsekas,et al.  Dynamic Programming: Deterministic and Stochastic Models , 1987 .

[29]  Hee Cheon No,et al.  Quantitative evaluation of swelling or shrinking level contributions in steam generators using spectrum analysis , 1993 .

[30]  Hamid R. Berenji,et al.  Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[31]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[32]  Peter Norvig,et al.  Artificial intelligence - a modern approach, 2nd Edition , 2003, Prentice Hall series in artificial intelligence.