基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模

doi:10.11949/j.issn.0438-1157.20161533

化工学报 ›› 2017, Vol. 68 ›› Issue (3): 976-983.DOI: 10.11949/j.issn.0438-1157.20161533

基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模

郑蓉建^1,2, 潘丰¹

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;
2 淮阴工学院自动化学院, 江苏淮安 223003

收稿日期:2016-10-31 修回日期:2016-11-07 出版日期:2017-03-05 发布日期:2017-03-05
通讯作者: 郑蓉建,rjmzheng@163.com
基金资助:
国家自然科学基金项目（61273131）；江苏省普通高校研究生科研创新计划项目（CXZZ12_0741）；中央高校基本科研业务费专项资金（JUDCF12034）。

Prediction of product concentration in glutamate fermentation process using partial least squares and least square support vector machine

ZHENG Rongjian^1,2, PAN Feng¹

1 Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, Jiangsu, China;
2 Faculty of Automation, Huaiyin Institute of Technology, Huai'an 223003, Jiangsu, China

Received:2016-10-31 Revised:2016-11-07 Online:2017-03-05 Published:2017-03-05
Contact: 10.11949/j.issn.0438-1157.20161533
Supported by:
supported by the National Natural Science Foundation of China (61273131),the Graduate Innovation of Jiangsu Province (CXZZ12_0741) and the Fundamental Research Funds for Central Universities (JUDCF12034).

摘要/Abstract

摘要：

针对谷氨酸发酵过程关键生化参数难以在线检测给发酵优化控制带来困难问题，基于谷氨酸5 L发酵罐发酵过程，建立基于偏最小二乘（PLS）和最小二乘向量机（LSSVM）相结合的谷氨酸浓度预测模型；利用PLS对输入变量进行特征提取降低维数和消除相关性，以简化模型和提高模型精度。为确定谷氨酸发酵最佳预测模型，简化后的预测模型与发酵动力学模型进行比较；实验结果表明，简化后的耦合模拟退火（coupled simulated annealing，CSA）对参数进行优化的LSSVM模型具有最好预测性能，相对PLS预测模型和发酵动力学模型具有明显优势，均方根误差分别为1.597、8.49和2.934，可以为谷氨酸发酵过程操作及时调整及优化控制提供有效指导。

关键词: 谷氨酸, 发酵, 预测, 偏最小二乘, 最小二乘向量机, 反应动力学, 模型简化

Abstract:

Considered that key variables in glutamate fermentation process could not be measured inline, which would make it difficult to control and optimize the fermentation process, a model for glutamate concentration prediction in a 5 L fermentation tank was established on the basis of partial least squares (PLS) and least square support vector machine (LSSVM). PLS was applied first to extract features of input variables, to reduce number of variable dimensions, and to eliminate correlations such that model complexity was simplified and performance was improved. Coupled simulated annealing (CSA) arithmetic was later combined with grid search to determine model parameter values of LSSVM for improved prediction accuracy. Further model simplification was completed by deleting parameters with weak correlation to glutamate concentration. The simplified model was compared to kinetic model in order to select the best model of glutamate fermentation. Experimental results showed that the simplified LSSVM model equipped with CSA parameter optimization outperformed both PLS and kinetic models,which root mean square errors (RMSE) were 1.597, 8.49 and 2.934 respectively. The LSSVM prediction model had excellent performance with high accuracy, so it would be more suitable for online prediction of glutamate concentration and offer an effective guidance for control and optimization of the glutamate fermentation process.

Key words: glutamate, fermentation, prediction, partial least squares, least squares support vector machine, reaction kinetics, model simplification

中图分类号:

TP274

郑蓉建, 潘丰. 基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模[J]. 化工学报, 2017, 68(3): 976-983.

ZHENG Rongjian, PAN Feng. Prediction of product concentration in glutamate fermentation process using partial least squares and least square support vector machine[J]. CIESC Journal, 2017, 68(3): 976-983.

参考文献 30

[1]	KHAN N S, MISHRA I M, SINGH R P, et al. Modeling the growth of corynebacterium glutamicum under product inhibition in L-glutamic acid fermentation[J]. Biochemical Engineering Journal, 2005, 25(2):173-178.
[2]	CAO Y, MPOFU E, SHI Z P. A novel metabolic model incorporating directed signal flow diagram with enzymatic activities data for evaluating glutamate yield in glutamate fermentation[J]. Biochemical Engineering Journal, 2013, 77(8):136-146.
[3]	VELOSO A C A, ROCHA I, FERREIRA E C. Monitoring of fed-batch E. coli fermentations with software sensors[J]. Bioprocess Biosyst. Eng., 2009, 32:381-388.
[4]	贺彦林, 王晓, 朱群雄. 基于主成分分析改进的极限学习机方法的精对苯二甲酸醋酸含量软测量[J]. 控制理论与应用, 2015, 32(1):80-85. HE Y L, WANG X, ZHU Q X. Modeling of acetic acid content in purified terephthalic acid solvent column using principal component analysis based improved extreme learning machine[J]. Control Theory & Applications, 2015, 32(1):80-85.
[5]	KANEKO H, FUNATSU K. Ensemble locally weighted partial least squares as a just-in-time modeling method[J]. AIChE Journal, 2016, 62(3):717-725.
[6]	袁小锋, 葛志强, 宋执环. 基于时间差分和局部加权偏最小二乘算法的过程自适应软测量建模[J].化工学报, 2016, 67(3):724-728. YUAN X F, GE Z Q, SONG Z H. Adaptive soft sensor based on time difference model and locally weighted partial least squares regression[J]. CIESC Journal, 2016, 67(3):724-728.
[7]	黄永红, 孙丽娜, 孙玉坤, 等. 海洋蛋白酶发酵过程生物参数的软测量建模[J]. 信息与控制, 2013, 42(4):506-510. HUANG Y H, SUN L N, SUN Y K, et al. Soft sensor modeling based on biological variables of marine protease fermentation process[J]. Information and Control, 2013, 42(4):506-510.
[8]	WANG T, SUN J W, ZHANG W D, et al. Prediction of product formation in 2-keto-l-gulonic acid fermentation through Bayesian combination of multiple neural networks[J]. Process Biochemistry, 2014, 49:188-194.
[9]	陈进东, 潘丰. 基于在线支持向量回归的非线性模型预测控制方法[J]. 控制与决策, 2014, 29(3):460-464. CHEN J D, PAN F. Online support vector regression-based nonlinear model predictive control[J]. Control and Decision, 2014, 29(3):460-464.
[10]	LIU G H, ZHOU D W, XU H X, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert Systems with Applications, 2010, 37(4):2708-2713.
[11]	ACUNA G, RAMIREZ C, CURILEM M. Software sensors for biomass concentration in a SSC process using artificial neural networks and support vector machine[J]. Bioprocess Biosyst. Eng., 2014, 37(1):27-36.
[12]	SUYKENS J A K, VANDEWALLE J. Least squares support machine classifiers[J]. Neural Processing Letters, 1999, 9(3):293-300.
[13]	WANG X F, CHEN J D, LIU C B, et al. Hybrid modeling of penicillin fermentation process based on least square support vector machine[J]. Chemical Engineering Research and Design, 2010, 88:415-420.
[14]	NIU D P, JIA M X, WANG F L, et al. Optimization of Nosiheptide fed-batch fermentation process based on hybrid model[J]. Industrial & Engineering Chemistry Research, 2013, 52:3373-3380.
[15]	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. XIONG W L, YAO L, XU B G. Chaos least squares support vector machine and its application on fermentation process modeling[J]. CIESC Journal, 2013, 64(12):4585-4591.
[16]	陶劲松, 杨亚帆, 李远华. 基于PLS和SVM的纸张抗张强度建模比较[J].华南理工大学学报(自然科学版), 2014, 42(7):132-137. TAO J S, YANG Y F, LI Y H. Comparison of paper tensile strength prediction models based on PLS and SVM methods[J]. Journal of South China University of Technology (Natural Science Edition), 2014, 42(7):132-137.
[17]	TAE C P, TAE Y K, YEONG K Y. Prediction of the melt flow index using partial least squares and support vector regression in high-density polyethylene (HDPE) process[J]. Korean J. Chem. Eng., 2010, 27(6):1662-1668.
[18]	FACCO P, DOPLICHER F, BEZZO F, et al. Moving average PLS soft sensor for online product quality estimation in an industrial batch polymerization process[J]. J. Process Control, 2009, 19(3):520-529.
[19]	KANEKO H, ARAKAWA M, FUNATSU K. Development of a new soft sensor method using independent component analysis and partial least squares[J]. AIChE J., 2009, 55(1):87-98.
[20]	汤伟, 于东伟, 张怡真. 基于递推PLS的置换蒸煮终点软测量建模研究[J]. 中国造纸学报, 2015, 30(3):47-50. TANG W, YU D W, ZHANG Y Z. Research on cooking end point modeling based on recursive PLS for displacement cooking[J]. Transactions of China Pulp and Paper, 2015, 30(3):47-50.
[21]	FUJIWARA K, SAWADA H, KANO M. Input variable selection for PLS modeling using nearest correlation spectral clustering[J]. Chemometrics and Intelligent Laboratory Systems, 2012, 118:109-119.
[22]	赵朋程, 刘彬, 高伟, 等. 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. ZHAO P C, LIU B, GAO W, et al. Multiple kernel least square support vector machine model for prediction of cement clinker lime content[J]. CIESC Journal, 2016, 67(6):2480-2487.
[23]	XIAO J, SHI Z P, GAO P, et al. On-line optimization of glutamate production based on balanced metabolic control by RQ[J]. Bioprocess Biosyst. Eng., 2006, 29(2):109-117.
[24]	董传亮. 谷氨酸发酵过程的故障诊断研究[D]. 无锡:江南大学, 2008. DONG C L. Study on fault diagnosis for glutamic acid fermentation process[D]. Wuxi:Jiangnan Univercity, 2008.
[25]	ZHENG X W, SUN T, SUN Z Y, et al. Time-dependent kinetic models for glutamic acid fermentation[J]. Enzyme and Microbial Technology, 1998, 22:205-209.
[26]	蔡煜东, 陈常庆.用遗传算法辨识发酵动力学模型参数[J].化工学报, 1995, 46(3):338-342. CAI Y D, CHEN C Q. Recognition of parameters in fermentation dynamics model by genetic algorithm[J]. Journal of Chemical Industry and Engineering(China), 1995, 46(3):338-342.
[27]	肖玲玲, 黄瑞, 郭金玲, 等. 木聚糖酶的发酵动力学研究与分批补料控制[J]. 可再生能源, 2015, 33(11):1700-1705. XIAO L L, HUANG R, GUO J L, et al. Study on the dynamics of xylanase fermentation and control of fed-batch[J]. Renewable Energy Resources, 2015, 33(11):1700-1705.
[28]	BAFFI G, MARTIN E B, MORRIS A J. Non-linear projection to latent structures revisited:the quadratic PLS algorithm[J]. Computers & Chemical Engineering, 1999, 23(3):395-411.
[29]	吕游, 刘吉臻, 杨婷婷, 等. 基于PLS特征提取和LS-SVM结合的NOx排放特性建模[J]. 仪器仪表学报, 2013, 34(11):2418-2424. LÜ Y, LIU J Z, YANG T T, et al. NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM[J]. Chinese Journal of Scientific Instrument, 2013, 34(11):2418-2424.
[30]	熊富强, 桂卫华, 阳春华, 等. 基于PLS-LSSVM方法的湿法炼锌过程预测建模[J].仪器仪表学报, 2011, 32(4):941-948. XIONG F Q, GUI W H, YANG C H, et al. Forecasting modeling of zinc hydrometallurgy process based on PLS-LSSVM approach[J]. Chinese Journal of Scientific Instrument, 2011, 32(4):941-948.ve soft sensor based on time difference model and locally weighted partial least squares regression[J]. CIESC Journal,2016,67(6):2480-2487.
[7]	黄永红,孙丽娜,孙玉坤,等.海洋蛋白酶发酵过程生物参数的软测量建模[J]. 信息与控制, 2013,32(4):506-510. HUANG Y H, SUN L N, SUN Y K, et al. Soft sensor modeling based on biological variables of marine protease fermentation process[J]. Information and Control, 2013,42(4): 506-510.
[8]	WANG T, SUN J W, ZHANG W D, et al. Prediction of product formation in 2-keto-l-gulonic acid fermentation through Bayesian combination of multiple neural networks[J]. Process Biochemistry, 2014,49:188-194.
[9]	陈进东,潘丰.基于在线支持向量回归的非线性模型预测控制方法[J]. 控制与决策, 2014,29(3):460-464. CHEN J D, PAN F. Online support vector regression-based nonlinear model predictive control[J]. Control and Decision, 2014,29(3): 460-464.
[10]	LIU G H, ZHOU D W, XU H X, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert Systems with Applications,2010,37(4): 2708-2713.
[11]	ACUNA G, RAMIREZ C, CURILEM M. Software sensors for biomass concentration in a SSC process using artificial neural networks and support vector machine[J]. Bioprocess Biosyst. Eng., 2014,37(1): 27-36.
[12]	SUYKENS J A K, VANDEWALLE J. Least squares support machine classifiers[J]. Neural Processing Letters,1999,9(3): 293-300.
[13]	WANG X F, CHEN J D, LIU C B, et al. Hybrid modeling of penicillin fermentation process based on least square support vector machine[J]. Chemical Engineering Research and Design, 2010,88: 415-420.
[14]	NIU D P, JIA M X, WANG F L, et al. Optimization of Nosiheptide fed-batch fermentation process based on hybrid model[J]. Industrial & Engineering Chemistry Research,2013,52:3373-3380.
[15]	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. XIONG W L, YAO L, XU B G. Chaos least squares support vector machine and its application on fermentation process modeling[J]. CIESC Journal,2013,64(12): 4585-4591.
[16]	陶劲松,杨亚帆,李远华.基于PLS和SVM的纸张抗张强度建模比较[J].华南理工大学学报(自然科学版), 2014,42(7):132-137. TAO J S, YANG Y F, LI Y H. Comparison of paper tensile strength prediction models based on PLS and SVM methods[J]. Journal of South China University of Technology (Natural Science Edition) ,2014,42(7):132-137.
[17]	TAE C P, TAE Y K, YEONG K Y. Prediction of the melt flow index using partial least squares and support vector regression in high-density polyethylene (HDPE) process[J]. Korean J. Chem. Eng.,2010,27(6):1662-1668.
[18]	FACCO P, DOPLICHER F, BEZZO F, et al. Moving average PLS soft sensor for online product quality estimation in an industrial batch polymerization process[J]. J. Process Control, 2009,19(3): 520-529.
[19]	KANEKO H, ARAKAWA M, FUNATSU K. Development of a new soft sensor method using independent component analysis and partial least squares[J]. AIChE J.,2009,55(1):87-98.
[20]	汤伟,于东伟,张怡真. 基于递推PLS的置换蒸煮终点软测量建模研究[J]. 中国造纸学报,2015,30(3) :47-50. TANG W,YU D W, ZHANG Y Z. Research on cooking end point modeling based on recursive PLS for displacement cooking[J]. Transactions of China Pulp and Paper,2015,30(3): 47-50.
[21]	FUJIWARA K, SAWADA H, KANO M. Input variable selection for PLS modeling using nearest correlation spectral clustering[J]. Chemometrics and Intelligent Laboratory Systems,2012,118:109-119.
[22]	赵朋程,刘彬,高伟,等.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. ZHAO P C, LIU B, GAO W, et al. Multiple kernel least square support vector machine model for prediction of cement clinker lime content[J]. CIESC Journal,2016,67(6):2480-2487.
[23]	XIAO J, SHI Z P, GAO P, et al. On-line optimization of glutamate production based on balanced metabolic control by RQ[J]. Bioprocess Biosyst. Eng., 2006,29(2):109-117.
[24]	董传亮. 谷氨酸发酵过程的故障诊断研究[D]. 无锡: 江南大学,2008. DONG C L. Study on fault diagnosis for glutamic acid fermentation process[D]. Wuxi: Jiangnan Univercity, 2008.
[25]	ZHENG X W, SUN T, SUN Z Y, et al. Time-dependent kinetic models for glutamic acid fermentation[J]. Enzyme and Microbial Technology,1998,22:205-209.
[26]	蔡煜东,陈常庆.用遗传算法辨识发酵动力学模型参数[J].化工学报,1995,46(3): 338-342. CAI Y D, CHEN C Q. Recognition of parameters in fermentation dynamics model by genetic algorithm[J]. CIESC Journal,1995,46(3):338-342.
[27]	肖玲玲,黄瑞,郭金玲,等. 木聚糖酶的发酵动力学研究与分批补料控制[J]. 可再生能源, 2015,33(11):1700-1705. XIAO L L, HUANG R, GUO J L, et al. Study on the dynamics of Xylanase fermentation and control of fed-batch[J]. Renewable Energy Resources, 2015,33(11):1700-1705.
[28]	BAFFI G, MARTIN E B, MORRIS A J. Non-linear projection to latent structures revisited: the quadratic PLS algorithm[J]. Computers & Chemical Engineering, 1999,23(3):395-411.
[29]	吕游,刘吉臻,杨婷婷,等. 基于PLS特征提取和LS-SVM结合的NOx排放特性建模[J]. 仪器仪表学报, 2013,34(11):2418-2424. LV Y, LIU J Z, YANG T T, et al. NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM[J]. Chinese Journal of Scientific Instrument, 2013,34(11):2418-2424.
[30]	熊富强,桂卫华,阳春华,等. 基于PLS-LSSVM方法的湿法炼锌过程预测建模[J].仪器仪表学报, 2011, 32(4):941-948. XIONG F Q, GUI W H, YANG C H, et al. Forecasting modeling of zinc hydrometallurgy process based on PLS-LSSVM approach[J]. Chinese Journal of Scientific Instrument, 2011, 32(4):941-948.

基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模

Prediction of product concentration in glutamate fermentation process using partial least squares and least square support vector machine

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价

[1]	程成, 段钟弟, 孙浩然, 胡海涛, 薛鸿祥. 表面微结构对析晶沉积特性影响的格子Boltzmann模拟[J]. 化工学报, 2023, 74(S1): 74-86.
[2]	王浩, 王振雷. 基于自适应谱方法的裂解炉烧焦模型化简策略[J]. 化工学报, 2023, 74(9): 3855-3864.
[3]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[4]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[5]	汪林正, 陆俞冰, 张睿智, 罗永浩. 基于分子动力学模拟的VOCs热氧化特性分析[J]. 化工学报, 2023, 74(8): 3242-3255.
[6]	张蒙蒙, 颜冬, 沈永峰, 李文翠. 电解液类型对双离子电池阴阳离子储存行为的影响[J]. 化工学报, 2023, 74(7): 3116-3126.
[7]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[8]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[9]	高学金, 姚玉卓, 韩华云, 齐咏生. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521.
[10]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[11]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[12]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[13]	禹进, 余彬彬, 蒋新生. 一种基于虚拟组分的燃烧调控化学作用量化及分析方法研究[J]. 化工学报, 2023, 74(3): 1303-1312.
[14]	史克年, 郑景元, 钱宇, 杨思宇. 基于马尔可夫链的蒸汽动力系统两阶段随机规划[J]. 化工学报, 2023, 74(2): 807-817.
[15]	陈家辉, 杨鑫泽, 陈顾中, 宋震, 漆志文. 以离子液体密度为例的分子性质预测模型建模方法探讨[J]. 化工学报, 2023, 74(2): 630-641.