基于分阶段的LSSVM发酵过程建模

doi:10.3969/j.issn.0438-1157.2013.09.026

化工学报 ›› 2013, Vol. 64 ›› Issue (9): 3262-3269.DOI: 10.3969/j.issn.0438-1157.2013.09.026

基于分阶段的LSSVM发酵过程建模

杨小梅, 刘文琦, 杨俊

大连理工大学电子信息与电气工程学部, 辽宁大连 116024

收稿日期:2013-01-21 修回日期:2013-03-07 出版日期:2013-09-05 发布日期:2013-09-05
通讯作者: 刘文琦
作者简介:杨小梅(1986- ),女,硕士研究生。
基金资助:
国家重大科技专项(2009ZX09306-004,2011ZX09101-008-09)。

LSSVM modeling for fermentation process based on dividing stages

YANG Xiaomei, LIU Wenqi, YANG Jun

School of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024, Liaoning, China

Received:2013-01-21 Revised:2013-03-07 Online:2013-09-05 Published:2013-09-05
Supported by:
supported by the Important National Science & Technology Specific Projects(2009ZX09306-004,2011ZX09101-008-09).

摘要/Abstract

摘要： 发酵过程建模是研究微生物发酵的重要课题,基于模型可实现被测参量的软测量、系统的优化控制。鉴于引入混合核函数的最小二乘支持向量机在过程建模中具有优良表现,采用基于混合核函数的最小二乘支持向量机建模。但由于发酵过程周期较长,最小二乘支持向量机的全局模型预测精度难以保证,算法复杂度很高,因此提出一种分阶段建模方法。首先,选择表征阶段特性的辅助变量,利用模糊C均值聚类算法对样本数据聚类,将发酵过程分成不同的阶段,然后为各个阶段分别建立最优混合核最小二乘支持向量机局部模型,最后将局部模型合成构成过程的完整模型。将此方法应用于青霉素发酵过程和重组大肠杆菌发酵过程中,验证了该方法的有效性。

关键词: 发酵过程建模, 最小二乘支持向量机, 分阶段建模, 混合核函数

Abstract: The modeling for fermentation process is an important issue in studying microbial fermentation. A precise mathematics model lays the foundation for the subsequent soft measurement and optimization work.The least squares support vector machine(LSSVM)with mixtures of kernels was used for its good performance in the modeling for fermentation process.Global modeling treats entire fermentation process as a study object.It is difficult to guarantee the prediction accuracy.Moreover,it brings about high computing complexity.To solve these problems,a staged modeling method based on LSSVM with optimal mixtures of kernels was proposed.Firstly,secondary variables which presented the characteristics of each stage were selected and modeling samples were classified according to the disparate stages by FCM clustering algorithm.Secondly,local models of stages were built using LSSVM while each local model used the optimal mixtures of kernels.Lastly,the integral process model was constituted with these local models.This method was applied to modeling the penicillin fermentation process based on Pensim and the recombinant E.coli fermentation process in the interleukin-2 production.Simulation results showed that local models of stages were superior to global model both in prediction accuracy and time complexity.The effectiveness of the proposed approach was validated.

Key words: modeling for fermentation process, LSSVM, staged modeling, mixtures of kernels

中图分类号:

TP29

杨小梅, 刘文琦, 杨俊. 基于分阶段的LSSVM发酵过程建模[J]. 化工学报, 2013, 64(9): 3262-3269.

YANG Xiaomei, LIU Wenqi, YANG Jun. LSSVM modeling for fermentation process based on dividing stages[J]. CIESC Journal, 2013, 64(9): 3262-3269.

参考文献 21

[1]	Cinar A,Palazoglu A,Kayihan F.Chemical Process Performance Evaluation[M].New York:CRC Press,2007:73-85
[2]	Craninx M,Fievez V,Vlaeminck B,de Baets B.Artificial neural network models of the rumen fermentation pattern in dairy cattle[J].Computers and Electronics in Agriculture,2008,60(2):226-238
[3]	Xiong Z H,Zhang J.Neural network model-based on-line re-optimisation control of fed-batch processes using a modified iterative dynamic programming algorithm[J].Chemical Engineering and Processing:Process Intensification,2005,44(4):477-484
[4]	Gao X J,Wang P,Qi Y S,Zhang Y T,Zhang H Q,Yan A J.An optimal control strategy combining SVM with RGA for improving fermentation titer[J].Chinese Journal of Chemical Engineering,2010,18(1):95-101
[5]	Liu G H,Zhou D W,Xu H X,Mei C L.Model optimization of SVM for a fermentation soft sensor[J].Expert Systems with Application,2010,37(4):2708-2713
[6]	Vapnik V.The Nature of Statistical Learning Theory[M].New York:Springer Verlag,1995:123-180
[7]	Suykens J,Vandewalle J,de Moor B.Optimal control by least squares support vector machines[J].Neural Networks,2001,14(1):23-35
[8]	Smits G F,Jordaan E M.Improved SVM regression using mixtures of kernels//Proceedings of the 2002 International Joint Conference on Neural Networks[C].Hawaii,2002:2785-2790
[9]	Zheng S,Liu J,Tian J W.An efficient star acquisition method based on SVM with mixtures of kernels[J].Pattern Recognition Letters,2005,26(2):147-165
[10]	John J,Vinodhini B,Karthik S.Estimating missing values using mixture kernel regression[J].International Journal of Computer Applications in Engineering Sciences,2012,2(2):83-88
[11]	Wu C H,Tzeng G H,Lin R H.A novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J].Expert Systems with Applications,2009,36(3):4725-4735
[12]	Doan X T,Srinivasan R,Bapat P M,Wangikar P P. Detection of phase shifts in batch fermentation via statistical analysis of the on line measurements:a case study with rifamycin B fermentation[J].Journal of Biotechnology,2007,132(2):156-166
[13]	Yang Qiangda(杨强大),Hou Xinyu(侯新宇).Staged soft-sensor modeling for Nosiheptide fermentation process[J].CIESC Journal(化工学报),2011,62(6):1612-1619
[14]	Gao Xuejin(高学金),Wang Pu(王普),Sun Chongzheng(孙崇正).Research and application of method on modeling by dividing phases for fermentation process[J].Journal of System Simulation(系统仿真学报)2007,19(11):2574-2577
[15]	Camacho J,Pico J.Multi-phase principal component analysis for batch processes modeling[J].Chemometrics and Intelligent Laboratory Systems,2006,81(2):127-136
[16]	Lu N Y,Gao F N,Wang F L.Sub-PCA modeling and on-line monitoring strategy for batch processes[J].AIChE Journal,2004,50(1):255-259
[17]	Xiong Weili(熊伟丽),Wang Xiao(王肖),Chen Minfang(陈敏芳),Xu Baoguo(徐保国).Modeling for penicillin fermentation process based on weighted LS-SVM[J].CIESC Journal(化工学报),2012,63(9):2913-2919
[18]	Zhao C H,Wang F L,Lu N Y,Jia M X.Stage-based soft-transition multiple PCA modeling and online monitoring strategy for batch process[J].Journal of Process Control,2007,17(9):728-741
[19]	Sun W,Meng Y,Palazoglu A,Zhao J,Zhang H,Zhang J.A method for multiphase batch process monitoring based on auto phase identification[J].Journal of Process Control,2011,21(4):627-638
[20]	Liu Yi(刘毅),Wang Haiqing(王海清).Pensim simulator and its application in penicillin fermentation process[J].Journal of System Simulation(系统仿真学报),2006,12(12):3524-3527
[21]	Birol G,Undey C,Cinar A.A modular simulation package for fed-batch fermentation:penicillin production[J].Computer and Chemical Engineering,2002,26(11):1553-1565

基于分阶段的LSSVM发酵过程建模

LSSVM modeling for fermentation process based on dividing stages

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	穆瑞, 乐高杨, 杨慧中. 基于O₃/UV法在线COD检测的气体溶解量估计方法[J]. 化工学报, 2019, 70(2): 730-735.
[2]	朱建勇, 张旭乾, 杨辉, 陆荣秀. 单光照条件变化的镨/钕元素组分含量软测量[J]. 化工学报, 2019, 70(2): 780-788.
[3]	牛大鹏, 刘元清. 基于改进即时学习算法的湿法冶金浸出过程建模[J]. 化工学报, 2017, 68(7): 2873-2879.
[4]	赵敏华, 胡毅, 李金, 王羽笙, 吴蕊, 宋乐. 使用博弈差分算法的电站锅炉高效低污染燃烧均衡优化[J]. 化工学报, 2017, 68(6): 2455-2464.
[5]	赵朋程, 刘彬, 高伟, 赵志彪, 王美琪. 用于水泥熟料fCaO预测的多核最小二乘支持向量机模型[J]. 化工学报, 2016, 67(6): 2480-2487.
[6]	刘瑞兰, 徐艳, 戎舟. 基于稀疏最小二乘支持向量机的软测量建模[J]. 化工学报, 2015, 66(4): 1402-1406.
[7]	冯凯, 卢建刚, 陈金水. 基于最小二乘支持向量机的MIMO线性参数变化模型辨识及预测控制[J]. 化工学报, 2015, 66(1): 197-205.
[8]	王通, 高宪文, 刘文芳. 自适应软测量方法在动液面预测中的研究与应用[J]. 化工学报, 2014, 65(12): 4898-4904.
[9]	靳文博，敬加强，田震，孙娜娜，伍鸿飞. 基于最小二乘支持向量机的蜡沉积速率预测[J]. 化工进展, 2014, 33(10): 2565-2569.
[10]	赵斐, 陆宁云, 杨毅. 基于工况识别的注塑过程产品质量预测方法[J]. 化工学报, 2013, 64(7): 2526-2534.
[11]	钱晓山, 阳春华, 徐丽莎. 基于改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量[J]. 化工学报, 2013, 64(5): 1704-1709.
[12]	徐龙, 卢建刚, 杨秦敏, 陈金水, 施英姿. 一种新的近红外光谱信息区间选择方法[J]. 化工学报, 2013, 64(12): 4410-4415.
[13]	郭烁, 袁德成, 郭娲. 基于GMM核的LS-SVM真核启动子模型[J]. 化工学报, 2013, 64(12): 4662-4666.
[14]	熊伟丽, 姚乐, 徐保国. 混沌最小二乘支持向量机及其在发酵过程建模中的应用[J]. 化工学报, 2013, 64(12): 4585-4591.
[15]	周云龙，张全厚，邓艳秋. 基于PSO优化LS-SVM的气液两相流干度软测量[J]. 化工进展, 2013, 32(02): 295-298.