Abstract
In this paper, a new approach is investigated for adaptive dynamic neural network-based H ∞ control, which is designed for a class of non-linear systems with unknown uncertainties. Currently, non-linear systems with unknown uncertainties are commonly used to efficiently and accurately express the real practical control process. Therefore, it is of critical importance but a great challenge and still at its early age to design a stable and robust controller for such a process. In the proposed research, dynamic neural networks were constructed to precisely approximate the non-linear system with unknown uncertainties first, a non-linear state feedback H ∞ control law was designed next, then an adaptive weighting adjustment mechanism for dynamic neural networks was developed to achieve H ∞ regulation performance, and last a recurrent neural network was employed as a neuro-solver to efficiently and numerically solve the standard LMI problem so as to obtain the appropriate control gains. Finally, case studies further verify the feasibility and efficiency of the proposed research.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Abbreviations
- LMI:
-
Liner matrix inequality
- LDI:
-
Linear differential inclusion
References
Gupta MM, Rao DH (eds) (1994). Neuro control systems. IEEE Press, New York
Suykens JAK, Vanderwalle B and De Moor B (1996). Artificial neural networks for modelling and control of non-linear systems. Kluwer, Norwell
Shen Y, Hui Y and Jian G (2006). Reliable robust controller design for non-linear state-delayed systems based on neural networks. Lecture Notes Comput Sci 4234: 674–683
Suykens JAK, Vandewalle J and De Moor B (1999). Lur’s systems with multilayer perceptron and recurrent neural networks: Absolute stability and dissipativity. IEEE Trans Automat Contr 44: 770–774
Lin C-L and Lin T-Y (2001). An design approach for neural net-based control schemes. IEEE Trans Automat Contr 46(10): 1599–1605
Mukaidanif H, Ishii Y, Tanaka Y, Bu N, Tsuji T (2004) LMI based neurocontroller for guaranteed cost control of discrete-time uncertain system. IEEE Conference on Decision and Control, Atlantis, pp 800–814
Hu S and Liu Y (2004). Robust H ∞ control of multiple time-delay uncertain non-linear system using fuzzy model and adaptive neural network. Fuzzy Sets Syst 146: 403–420
Lin C-L and Lin T-Y (2002). Approach to adaptive neural net-based H ∞ control design. IEEE Proc Control Theory Appl 149(4): 331–342
Lin C-L, Lai C-C and Huang T-H (2000). A neural networks for linear matrix inequality problems. IEEE Trans Neural Networks 11(5): 1078–1092
Rovithakis GA and Christodoulou MA (1995). Direct adaptive regulation of unknown non-linear dynamical systems via dynamic neural networks. IEEE Trans Syst Man Cybernet 25(12): 1578–1594
Rovithakis GA and Christodoulou MA (1997). Neural adaptive regulation of unknown non-linear dynamical systems. IEEE Trans Syst Man Cybernet B 27(5): 810–822
Rovithakis GA (1999). Tracking control of multi-input affine non-linear dynamical systems with unknown nonlinearities using dynamical neural networks. IEEE Trans Syst Man Cybernet B 29(2): 179–189
Rovithakis GA (1999). Robust neural adaptive stabilization of unknown systems with measurement noise. IEEE Trans Syst Man Cybernet B 29(3): 453–459
Kosmatopoulos E, Polycarpou M, Christodoulou M and Ioannou P (1995). Higher-order neural networks structures for identification of dynamical systems. IEEE Trans Neural Networks 6(2): 422–431
Dempo A, Farotimi O and Kailath T (1991). Higher-order absolutely stable neural networks. IEEE Trans Circ Syst 38: 57–65
Stoorvogel A (1992) The H ∞ control problem: a state space approach. Upper Saddle River, NJ: Prentice-Hall
Boyd S, Ghaoui LE, Feron E and Balakrishnan V (1994). Linear matrix inequality in system and control theory. SIAM, Philadelphia
Steward GW (1973). Introduction to matrix computation. Academic Press, Orlando
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shen, Y., Shen, W. H ∞ Control Design Using Dynamic Neural Networks. Neural Process Lett 27, 97–113 (2008). https://doi.org/10.1007/s11063-007-9062-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-007-9062-9