Ann-based Prediction of the Profit Function for Industrial 2-Keto-L-Gulonic Acid Production

被引：0

作者：

Cui, Lei ^{[1
]}

Song, Haihui ^{[1
]}

Hu, Zhihua ^{[1
]}

Wang, Zhifeng ^{[1
]}

机构：

[1] Shanghai Second Polytech Univ, Coll Engn, Shanghai 201209, Peoples R China

来源：

INTERNATIONAL CONFERENCE ON ELECTRICAL AND CONTROL ENGINEERING (ICECE 2015) | 2015年

关键词：

fed-batch fermentation; profit function; ANN; data-driven prediction; FED-BATCH FERMENTATION; NEURAL-NETWORKS; OPTIMIZATION;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The profit function for 2-keto-L-gulonic acid (2-KGA) cultivation, generic criterion for describing the cost-effect of the processes, is predicted with the rolling learning-prediction (RLP) approach based on artificial neural networks (ANN) in this study. The historical database of the ANN is updated with statistical analysis of the profit function after the termination of a batch. To satisfy the online application demand, pseudo-on-line prediction is carried out using the data from commercial scale 2-KGA cultivation. The results indicate that the prediction approach has good generalization performance and noise tolerance.

引用

页码：396 / 401

页数：6

共 16 条

[1] Dynamic neural networks as a tool for the online optimization of industrial fermentation [J].

Becker, T ;

Enders, T ;

Delgado, A .

BIOPROCESS AND BIOSYSTEMS ENGINEERING, 2002, 24 (06) :347-354

[2] The use of microorganisms in L-ascorbic acid production [J].

Bremus, Christoph ;

Herrmann, Ute ;

Bringer-Meyer, Stephanie ;

Sahm, Hermann .

JOURNAL OF BIOTECHNOLOGY, 2006, 124 (01) :196-205

[3] Online monitoring of batch processes using multi-phase principal component analysis [J].

Camacho, Jose ;

Pico, Jesus .

JOURNAL OF PROCESS CONTROL, 2006, 16 (10) :1021-1035

[4] Least-squares parameter estimation for systems with irregularly missing data [J].

Ding, Feng ;

Ding, Jie .

INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2010, 24 (07) :540-553

[5] Multiinnovation Least-Squares Identification for System Modeling [J].

Ding, Feng ;

Liu, Peter X. ;

Liu, Guangjun .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2010, 40 (03) :767-778

[6] Continuous-time versus discrete-time approaches for scheduling of chemical processes: a review [J].

Floudas, CA ;

Lin, XX .

COMPUTERS & CHEMICAL ENGINEERING, 2004, 28 (11) :2109-2129

[7] Enhancing sugar cane process performance through optimal production scheduling [J].

Heluane, H. ;

Colombo, M. ;

Hernandez, M. R. ;

Graells, M. ;

Puigjaner, L. .

CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION, 2007, 46 (03) :198-209

[8] Metaheuristic approaches to the hybrid flow shop scheduling problem with a cost-related criterion [J].

Janiak, Adam ;

Kozan, Erhan ;

Lichtenstein, Maciej ;

Oguz, Ceyda .

INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2007, 105 (02) :407-424

[9] Dynamic hybrid neural network model of an industrial fed-batch fermentation process to produce foreign protein [J].

Laursen, Siris O. ;

Webb, Daniel ;

Ramirez, W. Fred .

COMPUTERS & CHEMICAL ENGINEERING, 2007, 31 (03) :163-170

[10]

Ning W.Z., 1988, NING WZ, Patent No. 0278447

← 1 2 →