Control System Design via Constraint Satisfaction using Convolutional Neural Networks and Black Hole Optimization

This paper proposes a new approach to control system design through solving a Constraint Satisfaction Problem (CSP) using artificial intelligence, first using a genetic algorithm then using a Convolutional Neural Network (CNN). The genetic algorithm determines the feasible controller parameters by minimizing a cost function subject to inequality design constraints. The CNN-finds the parameters by designing a deep neural network. It is shown that the evolutionary optimization algorithm converges almost surely to the optimal solution. To demonstrate the methodologies, they are applied to the design of PID controllers for linear and nonlinear systems. Two examples are presented, an armature-controlled DC motor and Bouc-Wen nonlinear hysteresis model. Simulations results show that the proposed methods yield solutions that satisfy design

[1]  D. Banjerdpongchai,et al.  Controller design for a binary distillation column under disturbances with bounds on magnitudes and derivatives using Zakian's framework , 2004, 2004 5th Asian Control Conference (IEEE Cat. No.04EX904).

[2]  Zsófia Ruttkay,et al.  Constraint satisfaction---a survey , 1998 .

[3]  Hamed Mojallali,et al.  Modified Black Hole Algorithm with Genetic Operators , 2016, Int. J. Comput. Intell. Syst..

[4]  Xianmin Zhang,et al.  Nonlinear Hysteresis Modeling of Piezoelectric Actuators Using a Generalized Bouc–Wen Model , 2019, Micromachines.

[5]  Peter J. Fleming,et al.  Evolutionary algorithms in control systems engineering: a survey , 2002 .

[6]  G. Friedrich,et al.  Fuzzy control over constraint satisfaction problem solving in structural design , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[7]  Abbas A. Fardoun,et al.  Large scale photovoltaic array fault diagnosis for optimized solar cell parameters extracted by heuristic evolutionary algorithm , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[8]  V. Zakian.  New formulation for the method of inequalities , 1979 .

[9]  Attahiru Sule Alfa,et al.  Mixed-integer programming based techniques for resource allocation in underlay cognitive radio networks: A survey , 2016, Journal of Communications and Networks.

[10]  Wolfgang Faber.  Answer Set Programming , 2013, Reasoning Web.

[11]  Naebboon Hoonchareon,et al.  Controller design for DFIG-based wind power generation using Zakian's framework , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[12]  Lakhdar Sais,et al.  Reasoning from last conflict(s) in constraint programming , 2009, Artif. Intell..

[13]  V. Zakian,et al.  Design of dynamical and control systems by the method of inequalities , 1973 .

[14]  Peter J. Stuckey,et al.  Propagation = Lazy Clause Generation , 2007, CP.

[15]  V. Zakian,et al.  Well Matched Systems , 1991 .

[16]  I. Popescu.  Using artificial neural networks for constraint satisfaction problem , 1997 .

[17]  Peter van Beek,et al.  On Universal Restart Strategies for Backtracking Search , 2007, CP.

[18]  Walter J. Gutjahr,et al.  Convergence Analysis of Metaheuristics , 2010, Matheuristics.

[19]  Costas Papadimitriou,et al.  Multi‐objective framework for structural model identification , 2005 .

[20]  Ching-Yu Tyan,et al.  A new methodology of fuzzy constraint-based controller design via constraint-network processing , 1996, IEEE Trans. Fuzzy Syst..

[21]  Yangmin Li,et al.  Optimized PID tracking control for piezoelectric actuators based on the Bouc-Wen model , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[22]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[23]  Cesare Tinelli,et al.  Satisfiability Modulo Theories , 2021, Handbook of Satisfiability.

[24]  Andries Petrus Engelbrecht,et al.  A Convergence Proof for the Particle Swarm Optimiser , 2010, Fundam. Informaticae.

[25]  V. Zakian.  Perspectives on the principle of matching and the method of inequalities , 1996 .

[26]  V. K. Koumousis,et al.  Identification of Bouc-Wen hysteretic systems by a hybrid evolutionary algorithm , 2008 .

[27]  Vishwesh A. Vyawahare,et al.  Design of robust fractional-order controllers and prefilters for multivariable system using interval constraint satisfaction technique , 2017 .

[28]  Guobin Lin,et al.  Deep learning controller design of embedded control system for maglev train via deep belief network algorithm , 2020, Des. Autom. Embed. Syst..

[29]  Bernard Friedland,et al.  Control Systems Design , 1985 .

[30]  A. T. Bada.  Design of delayed control systems using Zakian's framework , 1985 .

[31]  Roger J.-B. Wets,et al.  Minimization by Random Search Techniques , 1981, Math. Oper. Res..

[32]  Xin-She Yang,et al.  Firefly Algorithms for Multimodal Optimization , 2009, SAGA.

[33]  Christian Bessiere,et al.  Constraint Propagation , 2006, Handbook of Constraint Programming.