Nonlinear model predictive control based on fuzzy wavelet neural network and chaos optimization

In this paper a combined controller is proposed for nonlinear dynamical systems. The controller is constructed by a fuzzy wavelet network and nonlinear model predictive control. Chaotic optimization, which is fast and robust, is applied to generate optimized controlled input in nonlinear model predictive control. The ability of the fuzzy wavelet neural network and the proposed controller is shown by simulation. It is illustrated that the proposed method is able to increase the speed of tracking in addition to having very little steady state error. Using chaotic optimization makes the controller robust in the presence of noise.

PDF

___

[1] Kayacan E, Ramon H, Saeys W. Robust tube based decentralized nonlinear model predictive control of an au- tonomous tractor trailer system. IEEE-ASME T Mech 2015; 20: 447-456.
[2] Kaplanoglu E, Arsan T, Varsol HS. Predictive control of a constrained pressure and level system. Turk J Elec Eng & Comp Sci 2013; 23: 641-653.
[3] Hedjar R. Adaptive neural network model predictive control. Int J Innovative Comp, Inf & Cont 2013; 93: 1245-1256.
[4] Pan Y, Wang J. Model predictive control of unknown nonlinear dynamical systems based on recurrent neural network. IEEE T Indust Elec 2012; 59: 3089-3101.
[5] Wang T, Gao H, Qiu J. A combined adaptive neural network and nonlinear model predictive control for multirate networked industrial process control. IEEE T Neural Netw Learn Syst 2016; 27: 416-425.
[6] Chang YL, Tsai CC. Adaptive stable generalized predictive control using TSK fuzzy model for nonlinear discrete- time systems with time-delays. Int J Fuzzy Sys 2013; 15: 133-141.
[7] Lu CH. Wavelet fuzzy neural networks for identi cation and predictive control of dynamic systems. IEEE T Indust Elec 2011; 58: 3046-3058.
[8] Xiao H, Li Z, Yang C, Zhang L, Yuan P, Ding L, Wang T. Robust stabilization of a wheeled mobile robot using model predictive control based on neurodynamics optimization. IEEE T Indust Elec 2017; 64: 505-516.
[9] Sridhar N, Ramrao N, Singh MK. Design of PID controller with auto tuned pre lter using chaotic optimization. In: International Conference on Circuits, Communications, Control and Computing; 21{22 Nov 2014; IEEE. pp. 141-145.
[10] Xu H, Qian X, Zhang L. Study of ACO algorithm optimization based on improved tent chaotic mapping. J Inf Comp Sci 2012; 9: 1653-1660.
[11] Jahani R, Chahkandi Nejad H. Comparison of chaotic optimization algorithm and other evolutionary techniques for optimal unit commitment of power system. Australian Journal of Basic and Applied Sciences 2011; 5: 923-929.
[12] Wang L, Wei X, Shao Y, Zhu T, Zhang J. MPPT of PV array using stepped up chaos optimization algorithm. Turk J Elec Eng & Comp Sci 2015; 23: 1748-1760.
[13] Javidi MM, Emami N. A Hybrid Search Method of Wrapper Feature Selection by Chaos Particle Swarm Optimiza- tion and Local Search. Turk J Elec Eng & Comp Sci 2016; 24: 3852-3861.
[14] Li P, Xu D, Zhou Z, Lee WJ, Zhao B. Stochastic optimal operation of microgrid based on chaotic binary particle swarm optimization. IEEE T Smart Grid 2016; 7: 66-73.
[15] Camacho EF, Bordons C. Model Predictive Control. Berlin, Germany: Springer, 1999.
[16] Davanipour M, Zekri M, Sheikholeslam F. Fuzzy wavelet neural network with an accelerated hybrid learning algorithm. IEEE T Fuzzy Sys 2012; 20: 463-470.
[17] Lin FJ, Tan KH, Fang DY, Lee YD. Intelligent controlled three phase squirrel cage induction generator system using wavelet fuzzy neural network for wind power. IET Renew Pow Gener 2013; 7: 552-564.
[18] Li B, Jiang WS. Optimizing complex functions by chaos search. Cybernet Syst 1998; 24: 409-419.
[19] Engin SN, Kuvulmaz J, Omurlu VE. Fuzzy control of an ANFIS model representing a nonlinear liquid level system. Neural Comput Appl 2004; 13: 202-210.