Representing and Learning Unmodeled Dynamics with Neural Network Memories

A nonlinear model representation consisting of an interpolation of several local models, which are valid within certain operation regimes, is proposed. Using this representation, first principles models and black-box models like neural networks may be integrated. Only operation regimes of the plant not adequately modeled by first principles are being represented and learned by a neural network memory. The principle is illustrated by simulation examples.

[1]  T. Johansen,et al.  A NARMAX model representation for adaptive control based on local models , 1992 .

[2]  Tor Arne Johansen,et al.  Nonlinear Local Model Representation For Adaptive Systems , 1992, Singapore International Conference on Intelligent Control and Instrumentation [Proceedings 1992].

[3]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[4]  Sheng Chen,et al.  Practical identification of NARMAX models using radial basis functions , 1990 .

[5]  P. A. Minderman,et al.  INTEGRATING NEURAL NETWORKS WITH FIRST PRINCIPLES MODELS FOR DYNAMIC MODELING , 1992 .

[6]  J. van Amerongen,et al.  Neural Network Based Control of Mode-Switch Processes , 1991 .

[7]  Lennart Ljung,et al.  Construction of Composite Models from Observed Data , 1992 .

[8]  Derrick H. Nguyen,et al.  Neural networks for self-learning control systems , 1990 .

[9]  E. Sorheim,et al.  A combined network architecture using ART2 and back propagation for adaptive estimation of dynamical processes , 1991, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System Sciences.

[10]  John A. Hertz,et al.  Exploiting Neurons with Localized Receptive Fields to Learn Chaos , 1990, Complex Syst..

[11]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[12]  Anders Skeppstedt.  Construction of composite models from large data-sets , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[13]  J. van Amerongen,et al.  Intelligent adaptive control of mode-switch processes , 1991 .

[14]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[15]  Thomas J. McAvoy,et al.  Neural net based model predictive control , 1991 .

[16]  C. Jutten,et al.  Gal: Networks That Grow When They Learn and Shrink When They Forget , 1991 .

[17]  S. TarI,et al.  A Combined Pid and Neural Control Scheme for Nonlinear Dynamical Systems , 1992, Singapore International Conference on Intelligent Control and Instrumentation [Proceedings 1992].

[18]  S. Billings,et al.  Correlation based model validity tests for non-linear models , 1986 .