Fed-Batch Dynamic Optimization using Generalized Dual Heuristic Programming

Donald C. Wunsch; M. S. Iyer

doi:10.1109/IJCNN.1999.836190

Fed-Batch Dynamic Optimization using Generalized Dual Heuristic Programming

Donald C. Wunsch
, M. S. Iyer

Research output: Contribution to journal › Article › peer-review

Abstract

Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer

Original language	American English
Journal	Proceedings of the International Joint Conference on Neural Networks, 1999. IJCNN '99
DOIs	https://doi.org/10.1109/IJCNN.1999.836190
State	Published - Jan 1 1999

Keywords

Action Learning
Adaptive Critic Design
Batch Processing (Industrial)
Dual Heuristic Programming
Dynamic Optimization
Fed-Batch Biochemical Process
Feedforward Neural Nets
Feedforward Neural Networks
Fermentation
Learning (Artificial Intelligence)
Neurocontrollers
Optimization
Phenomenological Model
Process Control
Real-Time Systems

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/IJCNN.1999.836190License: Unspecified

Fed-Batch Dynamic Optimization using Generalized Dual Heuristic PFinal published version, 480 KBLicense: Unspecified

Cite this

@article{653a31df32ac40b3a6543a5e725a3a17,

title = "Fed-Batch Dynamic Optimization using Generalized Dual Heuristic Programming",

abstract = " Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer",

keywords = "Action Learning, Adaptive Critic Design, Batch Processing (Industrial), Dual Heuristic Programming, Dynamic Optimization, Fed-Batch Biochemical Process, Feedforward Neural Nets, Feedforward Neural Networks, Fermentation, Learning (Artificial Intelligence), Neurocontrollers, Optimization, Phenomenological Model, Process Control, Real-Time Systems",

author = "Wunsch, \{Donald C.\} and Iyer, \{M. S.\}",

year = "1999",

month = jan,

day = "1",

doi = "10.1109/IJCNN.1999.836190",

language = "American English",

journal = "Proceedings of the International Joint Conference on Neural Networks, 1999. IJCNN '99",

issn = "2161-4407",

}

TY - JOUR

T1 - Fed-Batch Dynamic Optimization using Generalized Dual Heuristic Programming

AU - Wunsch, Donald C.

AU - Iyer, M. S.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer

AB - Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer

KW - Action Learning

KW - Adaptive Critic Design

KW - Batch Processing (Industrial)

KW - Dual Heuristic Programming

KW - Dynamic Optimization

KW - Fed-Batch Biochemical Process

KW - Feedforward Neural Nets

KW - Feedforward Neural Networks

KW - Fermentation

KW - Learning (Artificial Intelligence)

KW - Neurocontrollers

KW - Optimization

KW - Phenomenological Model

KW - Process Control

KW - Real-Time Systems

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/1635

U2 - 10.1109/IJCNN.1999.836190

DO - 10.1109/IJCNN.1999.836190

M3 - Article

SN - 2161-4407

JO - Proceedings of the International Joint Conference on Neural Networks, 1999. IJCNN '99

JF - Proceedings of the International Joint Conference on Neural Networks, 1999. IJCNN '99

ER -

Fed-Batch Dynamic Optimization using Generalized Dual Heuristic Programming

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this