Modelling of Fermentation Process Based on Hybrid Least Square Support Vector Machine

摘要：

Fermentation process has a characteristic of complexity and high non-linearity, but the modelling using least square support vector machine (LSSVM) based on structure risk minimization (SRM) can get good result. However, in the initial stages of the process the result is not so good, so its necessary to propose a hybrid LSSVM modelling method to solve the problem of bad modelling result during the initial stages. This paper builds two hybrid predicting models for biomass concentration in fermentation with serial and serialparallel approaches, through the mechanism analysis and simulation experiments, the results show that the hybrid modelling methods have higher predicting accuracy and more powerful generalization ability than the single LSSVM method.

作者: Xianfang Wang Jindong Chen Feng Pan

作者单位: School of Information and Control Engineering Southern Yangtze University Wuxi, Jiangsu, China 21412 School of Information and Control Engineering Southern Yangtze University Wuxi, Jiangsu, China 21412

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）