Adaptive model predictive process control using neural networks
Abstract
A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.
- Inventors:
-
- Los Alamos, NM
- Mazomanie, WI
- Espanola, NM
- Issue Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- OSTI Identifier:
- 871108
- Patent Number(s):
- 5659667
- Assignee:
- Regents of University of California Office of Technology Transfer (Alemeda, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- DOE Contract Number:
- W-7405-ENG-36
- Resource Type:
- Patent
- Country of Publication:
- United States
- Language:
- English
- Subject:
- adaptive; model; predictive; process; control; neural; networks; controlling; output; plant; parameter; implemented; network; improved; method; apparatus; provides; sampling; input; rate; provide; inputs; fast; mpc; provided; vector; constructed; slower; values; averaged; gapped; time; period; improvement; provision; on-line; training; difference; curvature; basis; center; adjustment; maintain; weights; centers; updated; follow; changes; operation; apart; initial; off-line; data; apparatus provides; process control; neural network; improved method; time period; neural networks; sampling rate; input control; training data; provide control; model predictive; control inputs; fast rate; neural net; plant operation; adaptive model; control input; /706/700/
Citation Formats
Buescher, Kevin L, Baum, Christopher C, and Jones, Roger D. Adaptive model predictive process control using neural networks. United States: N. p., 1997.
Web.
Buescher, Kevin L, Baum, Christopher C, & Jones, Roger D. Adaptive model predictive process control using neural networks. United States.
Buescher, Kevin L, Baum, Christopher C, and Jones, Roger D. Wed .
"Adaptive model predictive process control using neural networks". United States. https://www.osti.gov/servlets/purl/871108.
@article{osti_871108,
title = {Adaptive model predictive process control using neural networks},
author = {Buescher, Kevin L and Baum, Christopher C and Jones, Roger D},
abstractNote = {A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed Jan 01 00:00:00 EST 1997},
month = {Wed Jan 01 00:00:00 EST 1997}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Temporal difference method for multi-step prediction: application to power load forecasting
conference, August 2002
- Hwang, Jenq-Neng; Moon, Seokyong
- Proceedings of the First International Forum on Applications of Neural Networks to Power Systems
The Computational Brain
book, January 1992
- Churchland, Patricia S.; Sejnowski, Terrence J.
- MIT Press
Optimization and control of a small-angle negative ion source using an on-line adaptive controller based on the connectionist normalized local spline neural network
journal, November 1992
- Mead, W. C.; Bowling, P. S.; Brown, S. K.
- Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 72, Issue 2