skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Adaptive, predictive controller for optimal process control

Abstract

One can derive a model for use in a Model Predictive Controller (MPC) from first principles or from experimental data. Until recently, both methods failed for all but the simplest processes. First principles are almost always incomplete and fitting to experimental data fails for dimensions greater than one as well as for non-linear cases. Several authors have suggested the use of a neural network to fit the experimental data to a multi-dimensional and/or non-linear model. Most networks, however, use simple sigmoid functions and backpropagation for fitting. Training of these networks generally requires large amounts of data and, consequently, very long training times. In 1993 we reported on the tuning and optimization of a negative ion source using a special neural network[2]. One of the properties of this network (CNLSnet), a modified radial basis function network, is that it is able to fit data with few basis functions. Another is that its training is linear resulting in guaranteed convergence and rapid training. We found the training to be rapid enough to support real-time control. This work has been extended to incorporate this network into an MPC using the model built by the network for predictive control. This controller has shown somemore » remarkable capabilities in such non-linear applications as continuous stirred exothermic tank reactors and high-purity fractional distillation columns[3]. The controller is able not only to build an appropriate model from operating data but also to thin the network continuously so that the model adapts to changing plant conditions. The controller is discussed as well as its possible use in various of the difficult control problems that face this community.« less

Authors:
; ; ; ; ; ; ;
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE, Washington, DC (United States)
OSTI Identifier:
150955
Report Number(s):
LA-UR-95-3627; CONF-951036-2
ON: DE96002590
DOE Contract Number:  
W-7405-ENG-36
Resource Type:
Conference
Resource Relation:
Conference: International conference on accelerator and large experimental physics control systems, Chicago, IL (United States), 30 Oct - 3 Nov 1995; Other Information: PBD: [1995]
Country of Publication:
United States
Language:
English
Subject:
99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; NEURAL NETWORKS; ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTERIZED CONTROL SYSTEMS; MATHEMATICAL MODELS; PARTIAL DIFFERENTIAL EQUATIONS; NONLINEAR PROBLEMS

Citation Formats

Brown, S K, Baum, C C, Bowling, P S, Buescher, K L, Hanagandi, V M, Hinde, Jr, R F, Jones, R D, and Parkinson, W J. Adaptive, predictive controller for optimal process control. United States: N. p., 1995. Web.
Brown, S K, Baum, C C, Bowling, P S, Buescher, K L, Hanagandi, V M, Hinde, Jr, R F, Jones, R D, & Parkinson, W J. Adaptive, predictive controller for optimal process control. United States.
Brown, S K, Baum, C C, Bowling, P S, Buescher, K L, Hanagandi, V M, Hinde, Jr, R F, Jones, R D, and Parkinson, W J. 1995. "Adaptive, predictive controller for optimal process control". United States. https://www.osti.gov/servlets/purl/150955.
@article{osti_150955,
title = {Adaptive, predictive controller for optimal process control},
author = {Brown, S K and Baum, C C and Bowling, P S and Buescher, K L and Hanagandi, V M and Hinde, Jr, R F and Jones, R D and Parkinson, W J},
abstractNote = {One can derive a model for use in a Model Predictive Controller (MPC) from first principles or from experimental data. Until recently, both methods failed for all but the simplest processes. First principles are almost always incomplete and fitting to experimental data fails for dimensions greater than one as well as for non-linear cases. Several authors have suggested the use of a neural network to fit the experimental data to a multi-dimensional and/or non-linear model. Most networks, however, use simple sigmoid functions and backpropagation for fitting. Training of these networks generally requires large amounts of data and, consequently, very long training times. In 1993 we reported on the tuning and optimization of a negative ion source using a special neural network[2]. One of the properties of this network (CNLSnet), a modified radial basis function network, is that it is able to fit data with few basis functions. Another is that its training is linear resulting in guaranteed convergence and rapid training. We found the training to be rapid enough to support real-time control. This work has been extended to incorporate this network into an MPC using the model built by the network for predictive control. This controller has shown some remarkable capabilities in such non-linear applications as continuous stirred exothermic tank reactors and high-purity fractional distillation columns[3]. The controller is able not only to build an appropriate model from operating data but also to thin the network continuously so that the model adapts to changing plant conditions. The controller is discussed as well as its possible use in various of the difficult control problems that face this community.},
doi = {},
url = {https://www.osti.gov/biblio/150955}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Dec 01 00:00:00 EST 1995},
month = {Fri Dec 01 00:00:00 EST 1995}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: