Modeling based on MOGA and the dynamic Ε -SVM for fermentation process - Details

Author：

Indexed by：

EI Scopus

Abstract：

To　found　the　suitable　models　to　describe　the　behavior　of　biochemistry　systems,　the　dynamic　Ε　-SVM　method　was　proposed　on　the　basis　of　SVM.　Each　training　sample　uses　different　error.　The　existed　methods　for　selecting　the　parameters　of　SVM　not　only　consume　time,　but　also　are　difficult　to　find　the　optimal　parameters.　The　optimal　parameters　were　automatically　decided　by　using　multi-object　Genetic　Algorithm　(MOGA).　A　new　modeling　method　that　combined　MOGA　with　the　dynamic　Ε　-SVM　was　presented.　The　model　for　penicillin　titer　preestimate　was　developed　by　it　in　Matlab6.5　with　data　collected　from　real　plant.　The　model　possesses　the　strong　capability　of　fitting　and　generalization.　Experiments　show　that　the　dynamic　Ε　-SVM　is　superior　to　the　standard　SVM　modeling　method.　MOGA　is　very　feasible　and　efficient　too.　©2006　IEEE.

Keyword：

Antibiotics Parameter estimation Optimal control systems Fermentation Biochemistry Support vector machines Error analysis Genetic algorithms

Author Community：

[ 1 ] [Xuejin, Gao]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 2 ] [Pu, Wang]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 3 ] [Chongzheng, Sun]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 4 ] [Yating, Zhang]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 5 ] [Huiqing, Zhang]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 6 ] [Yi, Jianqiang]Key Laboratory of Complex System and Intelligence Science, Chinese Academy of Sciences, Beijing 100033, China