Abstract
In this paper, we present a new receding horizon neural robust control scheme for a class of nonlinear systems based on the linear differential inclusion (LDI) representation of neural networks. First, we propose a linear matrix inequality (LMI) condition on the terminal weighting matrix for a receding horizon neural robust control scheme. This condition guarantees the nonincreasing monotonicity of the saddle point value of the finite horizon dynamic game. We then propose a receding horizon neural robust control scheme for nonlinear systems, which ensures the infinite horizon robust performance and the internal stability of closed-loop systems. Since the proposed control scheme can effectively deal with input and state constraints in an optimization problem, it does not cause the instability problem or give the poor performance associated with the existing neural robust control schemes.
Similar content being viewed by others
References
Kwon, W.H., Pearson, A.E.: A modified quadratic cost problem and feedback stabilization of a linear system. IEEE Trans. Autom. Control 22, 838–842 (1977)
Kwon, W.H., Pearson, A.E.: On feedback stabilization of time-varying discrete linear systems. IEEE Trans. Autom. Control 23, 479–481 (1978)
Kwon, W.H., Bruckstein, A.M., Kailath, T.: Stabilizing state-feedback design via the moving horizon method. Int. J. Control 37, 631–643 (1983)
Lee, J.W., Kwon, W.H., Choi, J.H.: On stability of constrained receding horizon control with finite terminal weighting matrix. Automatica 34(12), 1607–1612 (1998)
Kwon, W.H., Kim, K.B.: On stabilizing receding horizon controls for linear continuous time-invariant systems. IEEE Trans. Autom. Control 45, 1329–1334 (2000)
Ahn, C.K., Han, S.H., Kwon, W.H.: \(\mathcal{H}_{\infty}\) finite memory controls for linear discrete-time state-space models. IEEE Trans. Circuits Syst. II 54(2), 97–101 (2007)
Ahn, C.K.: Robustness bound for receding horizon finite memory control: Lyapunov–Krasovskii approach. Int. J. Control 85(7), 942–949 (2012)
Ahn, C.K., Song, M.K.: New results on stability margins of nonlinear discrete-time receding horizon \(\mathcal{H}_{\infty}\) control. Int. J. Innov. Comput. Inf. Control 9(4), 1703–1714 (2013)
Ahn, C.K.: Takagi–Sugeno fuzzy receding horizon \(\mathcal{H}_{\infty}\) chaotic synchronization and its application to Lorenz system. Nonlinear Anal. Hybrid Syst. 9, 1–8 (2013)
Ahn, C.K., Lim, M.T.: Model predictive stabilizer for T–S fuzzy recurrent multilayer neural network models with general terminal weighting matrix. Neural Comput. Appl. (2013). doi:10.1007/s00521-013-1381-3
Kwon, W.H., Han, S., Ahn, C.K.: Advances in nonlinear predictive control: a survey on stability and optimality. Int. J. Control. Autom. Syst. 2(1), 15–22 (2004)
Gupta, M.M., Rao, D.H.: Neuro Control Systems. IEEE Press, New York (1994)
Ahn, C.K.: An \(\mathcal{H}_{\infty}\) approach to stability analysis of switched Hopfield neural networks with time-delay. Nonlinear Dyn. 60(4), 703–711 (2010)
Ahn, C.K.: Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay. Inf. Sci. 180(23), 4582–4594 (2010)
Chen, F.C., Liu, C.C.: Adaptively controlling nonlinear continuous-time systems using multilayer neural networks. IEEE Trans. Autom. Control 46, 1306–1310 (1994)
Feng, Z., Michel, A.N.: Robustness analysis of a class discrete-time recurrent neural networks under perturbations. IEEE Trans. Circuits Syst. I 46, 1482–1486 (1999)
Poznyak, A.S., Yu, W., Sanchez, E.N., Perez, J.P.: Stability analysis of dynamic neural control. Expert Syst. Appl. 14, 227–236 (1998)
Suykens, J.A.K., Moor, B.D., Vandewalle, J.: Robust local stability of multilayer recurrent neural networks. IEEE Trans. Neural Netw. 11, 770–774 (2000)
Ahn, C.K.: Delay-dependent state estimation for T-S fuzzy delayed Hopfield neural networks. Nonlinear Dyn. 61(3), 483–489 (2010)
Limanond, S., Si, J.: Neural-network-based control design: an LMI approach. IEEE Trans. Neural Netw. 9, 1429–1442 (1998)
Tanaka, K.: An approach to stability criteria of neural-network control systems. IEEE Trans. Neural Netw. 6, 629–642 (1996)
Suykens, J.A.K., Vandewalle, J., Moor, B.D.: Artificial Neural Networks for Modeling and Control of Non-linear Systems. Kluwer, Norwell (1996)
Suykens, J.A.K., Vandewalle, J., Moor, B.D.: Lure systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativity. IEEE Trans. Autom. Control 44, 770–774 (1999)
Ahn, C.K.: Output feedback \(\mathcal{H}_{\infty}\) synchronization for delayed chaotic neural networks. Nonlinear Dyn. 59(1–2), 319–327 (2010)
Lin, C.L., Lin, T.Y.: An \(\mathcal{H}_{\infty}\) design approach for neural net-based control schemes. IEEE Trans. Autom. Control 46, 1599–1605 (2001)
Lin, C.L., Lin, T.Y.: Approach to adaptive neural net-based \(\mathcal{H}_{\infty}\) control design. IEE Proc., Control Theory Appl. 149, 331–342 (2002)
Lin, C.L., Lin, T.Y.: Neural net-based \(\mathcal{H}_{\infty}\) control for a class of nonlinear systems. Neural Process. Lett. 15, 157–177 (2002)
Boyd, S., Ghaoui, L.E., Feron, E., Balakrishnan, V.: Linear Matrix Inequalities in System and Control Theory vol. 15. SIAM, Philadelphia (1994)
Passino, K.M., Yurkovich, S.: Fuzzy Control. Addison Wesley/Longman, New York (1995)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Jyh-Horng Chou.
Rights and permissions
About this article
Cite this article
Ahn, C.K. Receding Horizon Robust Control for Nonlinear Systems Based on Linear Differential Inclusion of Neural Networks. J Optim Theory Appl 160, 659–678 (2014). https://doi.org/10.1007/s10957-013-0328-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-013-0328-2