Improved evolutionary operation based on D-optimal design and response surface method

This paper presents improved evolutionary operation based on D-optimal design and response surface method. D-optimal design and response surface method allow us to overcome the disadvantages of conventional evolutionary operation. Although evolutionary operation has been an effective alternative when fundamental models are hard to build because of the lack of the necessary information, the disadvantages in the number of experiments, experimental design and analysis and detection of the optimal point have prevented EVOP from being frequently applied to real processes. To compare the performance of the proposed method and the conventional EVOP, both of them were applied to a pulp digester process. As a result, the comparable response variable value has been clearly obtained with the proposed method while conducting much fewer numbers of experiments than the conventional evolutionary operation. In addition, the proposed method flexibly handles the constraints in the experimental design and gives more reliable experiment results than the conventional evolutionary operation. By virtue of these benefits, the proposed method can be utilized effectively for a process where prior knowledge for the process is not available.

[1]  W. DuMouchel,et al.  A simple Bayesian modification of D-optimal designs to reduce dependence on an assumed model , 1994 .

[2]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .

[3]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[4]  Jung heon Lee,et al.  Development of nonsingular optimization algorithm and its application to chemical engineering systems , 1999 .

[5]  Yeong-Koo Yeo,et al.  Optimization of the sulfolane extraction plant based on modeling and simulation , 2001 .

[6]  George E. P. Box,et al.  Evolutionary Operation: a Method for Increasing Industrial Productivity , 1957 .

[7]  M. J. D. Powell,et al.  An efficient method for finding the minimum of a function of several variables without calculating derivatives , 1964, Comput. J..

[8]  Michael H. Kutner.  Applied Linear Statistical Models , 1974 .

[9]  한종훈,et al.  Multi-period 조업을 고려한 유틸리티 플랜트의 최적화 , 1998 .

[10]  Jong Hun Han,et al.  Optimization of a Utility Plant Operation Based on a Hierarchical Method , 1998 .

[11]  Jongchul Park,et al.  Modified response surface methodology (MRSM) for phase equilibrium-theoretical background , 1996 .

[12]  Soo Hyoung Choi,et al.  Global optimization methods for chemical process design: Deterministic and stochastic approaches , 2002 .

[13]  W. G. Hunter,et al.  Evolutionary Operation: A Review , 1966 .

[14]  G. Piepel.  Programs for Generating Extreme Vertices and Centroids of Linearly Constrained Experimental Regions , 1988 .

[15]  Chonghun Han,et al.  The integration of complete replanning and rule-based repairing for optimal operation of utility plants , 2001 .

[16]  G. Box,et al.  On the Experimental Attainment of Optimum Conditions , 1951 .

[17]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[18]  B. C. Bhattacharyya,et al.  Optimization of n variable biological experiments by evolutionary operation-factorial design technique. , 1999, Journal of bioscience and bioengineering.

[19]  Toby J. Mitchell,et al.  An Algorithm for the Construction of “D-Optimal” Experimental Designs , 2000, Technometrics.

[20]  Jong Hun Han,et al.  Optimization of A Utility Plant for Multi-period Operations , 1998 .

[21]  M. E. Johnson,et al.  Some Guidelines for Constructing Exact D-Optimal Designs on Convex Design Spaces , 1983 .

[22]  J. Kiefer,et al.  Time- and Space-Saving Computer Methods, Related to Mitchell's DETMAX, for Finding D-Optimum Designs , 1980 .

[23]  B. C. Bhattacharyya,et al.  Evolutionary operation (EVOP) to optimize three‐dimensional biological experiments , 1993, Biotechnology and bioengineering.

[24]  J. Janson.  Optimization of large-scale chromatography of proteins , 2001 .