[1]熊伟丽,徐保国.基于PSO-SVR的发酵过程状态预估模型[J].南京理工大学学报(自然科学版),2008,(04):517-521.
 XIONG Wei-li,XU Bao-guo.State Estimation Model of Fermentation Process Based on PSO-SVR[J].Journal of Nanjing University of Science and Technology,2008,(04):517-521.
点击复制

基于PSO-SVR的发酵过程状态预估模型
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2008年04期
页码:
517-521
栏目:
出版日期:
2008-08-30

文章信息/Info

Title:
State Estimation Model of Fermentation Process Based on PSO-SVR
作者:
熊伟丽;徐保国;
江南大学通信与控制工程学院, 江苏无锡214122
Author(s):
XIONG Wei-liXU Bao-guo
School of Communication and Control Engineering,Southern Yangtze University,Wuxi 214122,China
关键词:
支持向量回归 状态预估 粒子群优化 发酵过程 β-甘露聚糖酶
Keywords:
support vector regression state estimation particle swarm optimization fermentation process beta-mannanase
分类号:
TQ920.1
摘要:
针对发酵过程中生物参数难以实时在线测量的问题,建立了用于生物参数状态预估的支持向量机软测量模型。考虑到该支持向量回归(SVR)模型的复杂性和冷化特征取决于其三个参数,εc,γ能否取到最优值,采用粒子群优化(PSO)算法实现对参数,εc,γ的同时寻优。在此基础上,以饲料用β-甘露聚糖酶为对象,建立了基于PSO-SVR的发酵过程产物浓度状态预估模型。发酵罐控制结果表明:该模型具有很好的学习精度和泛化能力,可实现对β-甘露聚糖酶产物浓度的实时在线预估。
Abstract:
In view of the hardship to get real-time and on-line biological parameters in fermentation process,a soft sensor model based on support vector machines is established for estimating the biological parameters.The complexity and generalization performance of the support vector regression(SVR) model depend on a good setting of the three parameters ε,c,γ.An algorithm called particle swarm optimization(PSO) is applied to optimize the three parameters synchronously.Based on the proposed method,a PSO-SVR model is developed to estimate the products concentration of beta-mannanase for feedstuff.The control results of fermenter show that the state estimation model based on PSO-SVR has good learning accuracy and generalization performance so as to obtain the real-time and on-line estimation for products concentration of beta-mannanase.

参考文献/References:

[1] 冯兴杰, 魏新, 黄亚楼. 基于支持向量机回归的旅 客吞吐量预测研究[ J]. 计算机工程, 2005, 31 ( 14): 172- 173.
[2] U stun B, M e lssen W J, Oudenhu ijzenM, et a.l Determ ination o f optim a l support vector reg ression parameters by genetic a lgo rithm s and simp lex optim iza tion [ J]. Ana ly tica Ch im ica Ac ta, 2005, 544 ( 1 - 2 ): 292- 305.
[3] Vapn ik V N. Statistica l learning theory [M ]. New York: JohnW iley & Sons, Inc. , 1998.
[4] Cherkassky V S, M ulier F M. Learning from data: Concepts, theory, and m ethods [M ]. New York: John W iley& Sons, 1998.
[5] Cherkassky V, M a Y Q. Practica l se lection of SVM param eters and noise estim ation fo r SVM regress ion [ J]. Neu ra lNe tw orks, 2004, 17 ( 1): 113- 126.
[6] 熊伟丽, 徐保国. 基于PSO的SVR参数优化选择方 法研究[ J]. 系统仿真学报, 2006, 18 ( 9): 2 442 - 2 446.
[7] Feng Y, H e Z. Optim ization o f ag itation, aeration, and tem perature conditions for m ax im um B-m annanase production [ J]. Enzyme and M icrobia,l 2003, 32 ( 2): 282- 289.
[8] 潘丰. 生化过程智能控制研究[ D] . 无锡: 江南大 学通信与控制工程学院, 2001. 521

备注/Memo

备注/Memo:
基金项目: 国家/ 8630计划( 2003AA241160); 江苏省自然科学基金( BK2005012) 作者简介: 熊伟丽( 1978- ), 女, 河南洛阳人, 博士, 副教授, 主要研究方向: 智能控制、优化算法, E-mail: w lx iong @ jiangnan. edu. cn。
更新日期/Last Update: 2012-12-19