| 生物反应过程的在线支持向量机建模优化 |
| |
| 引用本文： | 郑蓉建,周林成,潘丰.生物反应过程的在线支持向量机建模优化[J].化工学报,2012,63(9):2812-2817. |
| |
| 作者姓名： | 郑蓉建 周林成 潘丰 |
| |
| 作者单位： | 1. 江南大学轻工过程先进控制教育部重点实验室,江苏无锡214122;淮阴工学院电气工程学院,江苏淮安223003
2. 江南大学轻工过程先进控制教育部重点实验室,江苏无锡,214122 |
| |
| 基金项目： | 高等学校学科创新引智计划，江苏省普通高校研究生科研创新计划，中央高校基本科研业务费专项资金 |
| |
| 摘 要： | 针对生物反应过程具有较强的非线性、时变性,建立准确的机理模型较为困难,并且复杂的机理模型也无法用于在线控制和优化。将在线支持向量机和机理模型结合,提出串并联在线自校正混合建模方法。通过对典型生化过程谷氨酸的生产过程分析,找到影响谷氨酸浓度的关键参数;从现场历史数据中选取样本,建立基于在线向量机的软测量模型。实验结果表明该模型对谷氨酸浓度预测效果较好。
|
| 关 键 词： | 生化反应 在线支持向量机 自校正混合建模优化 软测量 谷氨酸预测 过程参数 |
Bioprocess modeling optimization based on online support vector machine |
| |
| ZHENG Rongjian
,
ZHOU Lincheng
,
PAN Feng.Bioprocess modeling optimization based on online support vector machine[J].Journal of Chemical Industry and Engineering(China),2012,63(9):2812-2817. |
| |
| Authors: | ZHENG Rongjian ZHOU Lincheng PAN Feng |
| |
| Affiliation: | 1(1Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education),Jiangnan University,Wuxi 214122,Jiangsu,China; 2Faculty of Electrical Engineering,Huaiyin Institute of Technology,Huai’an 223003,Jiangsu,China) |
| |
| Abstract: | Comparing with other industrial processes,biological reaction process has complicated mechanism,high nonlinear and uncertainty issues.It is difficult to build mechanism model,and complex mechanism model is not able to online control and optimize.Aiming to solve these issues,bioprocess modeling and optimization strategies based on online support vector machine(online SVM)are studied,combining online support vector machine and mechanism model,online self-tuning hybrid model of series-parallel connection is proposed.By analyzing the producing process of glutamic acid in bioprocess,the key process parameters,which affect the glutamic acid concentration,are found,and samples are selected from field history data,then the soft sensor model based on online support vector machine is built.The experimental results show that the model based on online method has a well performance and it is effective to predict glutamic acid concentration. |
| |
| Keywords: | bioprocess reaction online support vector machine self-tuning hybrid modeling optimization soft sensor glutamic acid concentration prediction process parameter |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
