Neural–Genetic Synthesis for State-Space Controllers Based on Linear Quadratic Regulator Design for Eigenstructure Assignment

Toward the synthesis of state-space controllers, a neural-genetic model based on the linear quadratic regulator design for the eigenstructure assignment of multivariable dynamic systems is presented. The neural-genetic model represents a fusion of a genetic algorithm and a recurrent neural network (RNN) to perform the selection of the weighting matrices and the algebraic Riccati equation solution, respectively. A fourth-order electric circuit model is used to evaluate the convergence of the computational intelligence paradigms and the control design method performance. The genetic search convergence evaluation is performed in terms of the fitness function statistics and the RNN convergence, which is evaluated by landscapes of the energy and norm, as a function of the parameter deviations. The control problem solution is evaluated in the time and frequency domains by the impulse response, singular values, and modal analysis.

[1]  M. Grimble,et al.  Recent trends in linear optimal quadratic multivariable control system design , 1987 .

[2]  Enrique Alba,et al.  Numerical and real time analysis of parallel distributed GAs with structured and panmictic populations , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[3]  Seul Jung,et al.  Hardware implementation of a real time neural network controller with a DSP and an FPGA , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[4]  Jun Wang,et al.  Recurrent neural networks for LU decomposition and Cholesky factorization , 1993 .

[5]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[6]  Enrique Alba,et al.  Parallelism and evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

[7]  Ignacio Rojas,et al.  Statistical analysis of the parameters of a neuro-genetic algorithm , 2002, IEEE Trans. Neural Networks.

[8]  Fabio Nogueira da Silva.  Métodos Neuronais para a Solução da EquaçãoAlgébrica de Riccati e o LQR , 2008 .

[9]  Hee-Sang Ko,et al.  An intelligent based LQR controller design to power system stabilization , 2004 .

[10]  A. Laub,et al.  Parallel algorithms for algebraic Riccati equations , 1991 .

[11]  Jun Wang,et al.  A multilayer recurrent neural network for solving continuous-time algebraic Riccati equations , 1998, Neural Networks.

[12]  Mihail M. Konstantinov,et al.  Computational methods for linear control systems , 1991 .

[13]  Rolf Isermann,et al.  Adaptive control systems , 1991 .

[14]  G. F. Bryant,et al.  Adaptive Control Systems , 1964 .

[15]  Tughrul Arslan,et al.  A parallel genetic VLSI architecture for combinatorial real-time applications-disc scheduling , 1995 .

[16]  Victor M. Becerra,et al.  Optimal control , 2008, Scholarpedia.

[17]  J. Doyle,et al.  Robust and optimal control , 1995, Proceedings of 35th IEEE Conference on Decision and Control.

[18]  Thomas Jansen,et al.  Computational complexity and evolutionary computation , 2010, GECCO '10.

[19]  Monica Carfagni,et al.  Artificial neural network software for real-time estimation of olive oil qualitative parameters during continuous extraction , 2007 .

[20]  Seul Jung,et al.  Hardware Implementation of a Real-Time Neural Network Controller With a DSP and an FPGA for Nonlinear Systems , 2007, IEEE Transactions on Industrial Electronics.

[21]  Dervis Karaboga,et al.  Genetic tracker with neural network for single and multiple target tracking , 2006, Neurocomputing.

[22]  Radoslaw Romuald Zakrzewski,et al.  Neural network control of nonlinear discrete time systems , 1994 .

[23]  Sam Kwong,et al.  A realizable architecture for genetic algorithm parallelism , 1998 .

[24]  João Viana da Fonseca Neto.  Alocação computacional inteligente de autoestruturas para controle multivariavel , 2000 .

[25]  Carlos Cesar Teixeira Ferreira.  Alocação de Auto-estrutura utilizando Controle Robusto LQG/LTR e Computação Evolutiva , 2004 .

[26]  Etsujiro Shimemura,et al.  Determining quadratic weighting matrices to locate poles in a specified region , 1983, Autom..

[27]  John N. Tsitsiklis,et al.  Parallel and distributed computation , 1989 .

[28]  Lakhmi C. Jain,et al.  Fusion of Neural Networks, Fuzzy Sets, and Genetic Algorithms: Industrial Applications , 1998 .

[29]  Andrzej Cichocki,et al.  Simplified neural networks for solving linear least squares and total least squares problems in real time , 1994, IEEE Trans. Neural Networks.

[30]  Ping Zhang,et al.  A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[31]  Gene H. Golub,et al.  Matrix computations , 1983 .

[32]  G. Stein.  Generalized quadratic weights for asymptotic regulator properties , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[33]  Jörgen Hansson,et al.  Quantifying and suppressing the measurement disturbance in feedback controlled real-time systems , 2008, Real-Time Systems.

[34]  Robert E. King.  Computational intelligence in control engineering , 1999 .

[35]  Mohsen Nasseri,et al.  Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network , 2008, Expert Syst. Appl..

[36]  Jörgen Hansson,et al.  Experimental evaluation of linear time-invariant models for feedback performance control in real-time systems , 2007, Real-Time Systems.

[37]  Arthur E. Bryson,et al.  Applied Optimal Control , 1969 .

[38]  P. Fabijanski,et al.  On-line PID controller tuning using genetic algorithm and DSP PC board , 2008, 2008 13th International Power Electronics and Motion Control Conference.

[39]  Hartmut Logemann,et al.  Multivariable feedback design : J. M. Maciejowski , 1991, Autom..

[40]  Pedro J. Zufiria,et al.  Design and comparison of adaptive power system stabilizers based on neural fuzzy networks and genetic algorithms , 2007, Neurocomputing.

[41]  Witold Pedrycz.  Genetic tolerance fuzzy neural networks: From data to fuzzy hyperboxes , 2007, Neurocomputing.

[42]  D. Gbaupe,et al.  Derivation of weighting matrices towards satisfying eigenvalue requirements , 1972 .

[43]  C.P. Bottura,et al.  An inequalities method for multivariable system's eigenstructure assignment via genetic multi-objective optimization , 2003, Proceedings of the 2003 American Control Conference, 2003..

[44]  Tim Clarke,et al.  Parallel implementation of a genetic algorithm , 1995 .

[45]  A. Laub.  A schur method for solving algebraic Riccati equations , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[46]  S. Kahne,et al.  Optimal control: An introduction to the theory and ITs applications , 1967, IEEE Transactions on Automatic Control.

[47]  J. Sarangapani.  Neural Network Control of Nonlinear Discrete-Time Systems (Public Administration and Public Policy) , 2006 .

[48]  Jih-Gau Juang,et al.  Analysis and comparison of aircraft landing control using recurrent neural networks and genetic algorithms approaches , 2008, Neurocomputing.

[49]  C. Aghanajafi,et al.  Optimization of the operational parameters in a fast axial flow CW CO2 laser using artificial neural networks and genetic algorithms , 2008 .

[50]  Preeti Bajaj,et al.  Vehicle Classification forSingle LoopDetector withNeural Genetic Controller: ADesign Approach , 2007 .

[51]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[52]  G. Runger,et al.  Performance predictions for parallel diagonal-implicitly iterated Runge-Kutta methods , 1995, Proceedings 9th Workshop on Parallel and Distributed Simulation (ACM/IEEE).

[53]  John Fulcher,et al.  Computational Intelligence: An Introduction , 2008, Computational Intelligence: A Compendium.

[54]  Okyay Kaynak,et al.  The fusion of computationally intelligent methodologies and sliding-mode control-a survey , 2001, IEEE Trans. Ind. Electron..

[55]  A. Cichocki,et al.  Neural networks for solving systems of linear equations and related problems , 1992 .

[56]  Leiba Rodman,et al.  Algebraic Riccati equations , 1995 .

[57]  F. M. Ham,et al.  A neurocomputing approach for solving the algebraic matrix Riccati equation , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[58]  Donald A. Sofge,et al.  Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches , 1992 .

[59]  J. Viana Fonseca,et al.  A Genetic Algorithm Convergence and Models for Eigenstructure Assignment via Linear Quadratic Regulator (LQR) , 2008, IEEE Latin America Transactions.

[60]  M. Ksouri,et al.  LQG/LTR control of a direct current motor , 2002, IEEE International Conference on Systems, Man and Cybernetics.