Data-driven model reduction-based nonlinear MPC for large-scale distributed parameter systems

Model predictive control (MPC) has been effectively applied in process industries since the 1990s. Models in the form of closed equation sets are normally needed for MPC, but it is often difficult to obtain such formulations for large nonlinear systems. To extend nonlinear MPC (NMPC) application to nonlinear distributed parameter systems (DPS) with unknown dynamics, a data-driven model reduction-based approach is followed. The proper orthogonal decomposition (POD) method is first applied off-line to compute a set of basis functions. Then a series of artificial neural networks (ANNs) are trained to effectively compute POD time coefficients. NMPC, using sequential quadratic programming is then applied. The novelty of our methodology lies in the application of POD's highly efficient linear decomposition for the consequent conversion of any distributed multi-dimensional space-state model to a reduced 1-dimensional model, dependent only on time, which can be handled effectively as a black-box through ANNs. Hence we construct a paradigm, which allows the application of NMPC to complex nonlinear high-dimensional systems, even input/output systems, handled by black-box solvers, with significant computational efficiency. This paradigm combines elements of gain scheduling, NMPC, model reduction and ANN for effective control of nonlinear DPS. The stabilization/destabilization of a tubular reactor with recycle is used as an illustrative example to demonstrate the efficiency of our methodology. Case studies with inequality constraints are also presented.

[1]  Panagiotis D. Christofides,et al.  Integrating nonlinear output feedback control and optimal actuator/sensor placement for transport-reaction processes , 2001 .

[2]  Constantinos Theodoropoulos,et al.  An off-line Model Reduction-based Technique for On-line Linear MPC Applications for Nonlinear Large-Scale Distributed Systems , 2010 .

[3]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[4]  Basil Kouvaritakis,et al.  Stochastic MPC with inequality stability constraints , 2006, Autom..

[5]  Eugene Wong,et al.  Stochastic processes in information and dynamical systems , 1979 .

[6]  Julio R. Banga,et al.  Exponential Observers for Distributed Tubular (Bio)Reactors , 2008 .

[7]  Volker Schulz,et al.  Process optimization of reactives systems by partially reduced SQP methods , 2000 .

[8]  Constantinos Theodoropoulos,et al.  Optimisation and Linear Control of Large Scale Nonlinear Systems: A Review and a Suite of Model Reduction-Based Techniques , 2011 .

[9]  Haralambos Sarimveis,et al.  Nonlinear model predictive control for distributed parameter systems using data driven artificial neural network models , 2008, Comput. Chem. Eng..

[10]  Antonio A. Alonso,et al.  Optimal sensor placement for state reconstruction of distributed process systems , 2004 .

[11]  Panagiotis D. Christofides,et al.  Optimal control of diffusion-convection-reaction processes using reduced-order models , 2008, Comput. Chem. Eng..

[12]  Constantinos Theodoropoulos,et al.  Linear MPC based on data-driven Artificial Neural Networks for large-scale nonlinear distributed parameter systems , 2012 .

[13]  Constantinos Theodoropoulos,et al.  Multiple Model Predictive Control of Dissipative PDE Systems , 2014, IEEE Transactions on Control Systems Technology.

[14]  W. Harmon Ray,et al.  The Bifurcation Behavior of Tubular Reactors. , 1982 .

[15]  P. Christofides,et al.  Finite-dimensional approximation and control of non-linear parabolic PDE systems , 2000 .

[16]  Panagiotis D. Christofides,et al.  Optimization of transport-reaction processes using nonlinear model reduction , 2000 .

[17]  Holk Cruse,et al.  Neural networks as cybernetic systems , 1996 .

[18]  S. Dubljevic,et al.  Predictive control of parabolic PDEs with state and control constraints , 2006, Proceedings of the 2004 American Control Conference.

[19]  L. Sirovich.  Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[20]  Kurt Hornik,et al.  Some new results on neural network approximation , 1993, Neural Networks.

[21]  A. Wills,et al.  THE ROBUSTNESS OF INPUT CONSTRAINED MODEL PREDICTIVE CONTROL TO INFINITY-NORM BOUND MODEL UNCERTAINTY , 2006 .

[22]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[23]  B. Foss,et al.  A new optimization algorithm with application to nonlinear MPC , 2004 .

[24]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[25]  H. Genceli,et al.  New approach to constrained predictive control with simultaneous model identification , 1996 .

[26]  Martha A. Gallivan,et al.  Optimization of a thin film deposition process using a dynamic model extracted from molecular simulations , 2008, Autom..

[27]  Constantinos Theodoropoulos,et al.  A linear model predictive control algorithm for nonlinear large‐scale distributed parameter systems , 2012 .

[28]  David D. Brengel,et al.  Multistep nonlinear predictive controller , 1989 .

[29]  Andrea Walther,et al.  An adjoint-based SQP algorithm with quasi-Newton Jacobian updates for inequality constrained optimization , 2010, Optim. Methods Softw..

[30]  P. Holmes,et al.  Turbulence, Coherent Structures, Dynamical Systems and Symmetry , 1996 .

[31]  Constantinos Theodoropoulos,et al.  Order reduction for nonlinear dynamic models of distributed reacting systems , 2000 .

[32]  Constantinos Theodoropoulos,et al.  Model reduction-based optimization using large-scale steady-state simulators , 2012 .

[33]  Constantinos Theodoropoulos,et al.  Off-line model reduction for on-line linear MPC of nonlinear large-scale distributed systems , 2011, Comput. Chem. Eng..

[34]  Hsien-Tang Tsai,et al.  The partial aliasing patterns for Taguchi’s L12 orthogonal array , 1995 .

[35]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[36]  Panagiotis D. Christofides,et al.  Integrated optimal actuator/sensor placement and robust control of uncertain transport-reaction processes , 2002 .