Support vector regression model predictive control on a HVAC plant

Some industrial and scientific processes require simultaneous and accurate control of temperature and relative humidity. In this paper, support vector regression (SVR) is used to build the 2-by-2 nonlinear dynamic model of a HVAC system. A nonlinear model predictive controller is then designed based on this model and an optimization algorithm is used to generate online the control signals within the control constraints. Experimental results show good control performance in terms of reference command tracking ability and steady-state errors. This performance is superior to that obtained using a neural fuzzy controller.

[1]  Marzuki Khalid,et al.  Temperature regulation with neural networks and alternative control schemes , 1995, IEEE Trans. Neural Networks.

[2]  David Clarke,et al.  Advances in model-based predictive control , 1994 .

[3]  Primoz Potocnik,et al.  Nonlinear model predictive control of a cutting process , 2002, Neurocomputing.

[4]  Johan A. K. Suykens,et al.  Optimal control by least squares support vector machines , 2001, Neural Networks.

[5]  Zoltan K. Nagy,et al.  Evaluation study of an efficient output feedback nonlinear model predictive control for temperature tracking in an industrial batch reactor , 2007 .

[6]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[7]  Jay H. Lee,et al.  Model predictive control: past, present and future , 1999 .

[8]  S. Sathiya Keerthi,et al.  Evaluation of simple performance measures for tuning SVM hyperparameters , 2003, Neurocomputing.

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[10]  Miguel Velez-Reyes,et al.  Nonlinear control of a heating, ventilating, and air conditioning system with thermal load estimation , 1999, IEEE Trans. Control. Syst. Technol..

[11]  Refrigerating.  ASHRAE handbook. Heating, ventilating, and air-conditioning applications , 1991 .

[12]  Gary William Flake,et al.  Efficient SVM Regression Training with SMO , 2002, Machine Learning.

[13]  Miroslav Fikar,et al.  Receding horizon iterative dynamic programming with discrete time models , 2001 .

[14]  Arthur L. Dexter,et al.  A fuzzy decision-making approach to temperature control in air-conditioning systems , 2005 .

[15]  David Q. Mayne,et al.  Constrained model predictive control: Stability and optimality , 2000, Autom..

[16]  T.J.A. de Vries,et al.  On using a support vector machine in learning feed-forward control , 2001, AIM 2001.

[17]  Manuel A. Duarte,et al.  Control of grinding plants using predictive multivariable neural control , 2001 .

[18]  Dongbing Gu,et al.  Neural predictive control for a car-like mobile robot , 2002, Robotics Auton. Syst..

[19]  S. Sathiya Keerthi,et al.  Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[20]  Rohit Kawathekar.  Nonlinear model predictive control of a reactive distillation column , 2007 .

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Rein Luus,et al.  Iterative dynamic programming , 2019, Iterative Dynamic Programming.

[23]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[24]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[25]  Qi Miao,et al.  Nonlinear model predictive control based on support vector regression , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.