基于LS-SVM的红霉素发酵过程软测量方法研究
|
摘要
随着生物技术的发展,微生物发酵工程在国民经济和社会生活中的地位越来越重要。为提高发酵过程的产品得率和产品质量,获得更好的经济效益,需要对发酵过程进行优化控制。但是由于发酵过程复杂的生化特性,发酵过程的许多重要特征参数不能实现实时测量,这使得先进的控制策略和算法难以在发酵工业现场获得应用。本文以红霉素发酵过程为研究对象,采用最小二乘支持向量机回归算法建立软测量模型,对发酵过程中的三个关键变量进行拟合和预估,为发酵过程优化控制提供了前提条件。具体研究如下:
1.在大量阅读文献和分析红霉素发酵机理的基础上,建立了红霉素发酵过程菌丝浓度、总糖浓度和化学效价三个关键变量的最小二乘支持向量机软测量模型,并与标准支持向量机软测量模型进行了对比研究。
2.分析了模型参数对模型精度的影响,研究了网格搜索和交叉验证相结合的最小二乘支持向量机软测量模型的参数优化方法。
3.针对发酵过程辅助变量测量与优化控制的需要,设计了温度、pH值、溶氧等主要参量的数据采集系统,并设计了红霉素发酵过程控制系统的结构。
With the development of biotechnology,microbial fermentation engineering is playing more and more important role in the national economy and social life.For the purpose of improving product output,quality and cost reduction,it is a necessity to optimize the fermentation process control.However,due to the complexity of the biochemical process,many important parameters can not be measured in real-time. Therefore,advanced control algorithm and strategy can't be applied efficiently in the fermentation industry.With the fermenting process of erythromycin as the object,this research adopted regress algorithm of Least Squares Support Vector Machine (LS-SVM) to set up the soft sensor models to predict three important parameters in the fermenting process.The detailed work is as follows.
Firstly,on the basis of reading literatures and studying the fermentation mechanism of erythromycin,the soft sensor models of LS-SVM are established respectively to predict the parameters in the erythromycin fermenting process,such as mycelium concentration,sugar concentration and production concentration,these models are compared and studied with soft sensor models of Support Vector Machine(SVM).
Secondly,analyze the impact of the model parameters to the model accuracy, research the method of grid search with cross-validation and to determine the LS-SVM model parameters.
Finally,in order to meet the requirement of variable measurement and optimal control in the fermenting process,design the data acquisition system to collect data of key parameters such as temperature,pH value,dissolved oxygen,and design the erythromycin fermentation process control system structure.
1.在大量阅读文献和分析红霉素发酵机理的基础上,建立了红霉素发酵过程菌丝浓度、总糖浓度和化学效价三个关键变量的最小二乘支持向量机软测量模型,并与标准支持向量机软测量模型进行了对比研究。
2.分析了模型参数对模型精度的影响,研究了网格搜索和交叉验证相结合的最小二乘支持向量机软测量模型的参数优化方法。
3.针对发酵过程辅助变量测量与优化控制的需要,设计了温度、pH值、溶氧等主要参量的数据采集系统,并设计了红霉素发酵过程控制系统的结构。
With the development of biotechnology,microbial fermentation engineering is playing more and more important role in the national economy and social life.For the purpose of improving product output,quality and cost reduction,it is a necessity to optimize the fermentation process control.However,due to the complexity of the biochemical process,many important parameters can not be measured in real-time. Therefore,advanced control algorithm and strategy can't be applied efficiently in the fermentation industry.With the fermenting process of erythromycin as the object,this research adopted regress algorithm of Least Squares Support Vector Machine (LS-SVM) to set up the soft sensor models to predict three important parameters in the fermenting process.The detailed work is as follows.
Firstly,on the basis of reading literatures and studying the fermentation mechanism of erythromycin,the soft sensor models of LS-SVM are established respectively to predict the parameters in the erythromycin fermenting process,such as mycelium concentration,sugar concentration and production concentration,these models are compared and studied with soft sensor models of Support Vector Machine(SVM).
Secondly,analyze the impact of the model parameters to the model accuracy, research the method of grid search with cross-validation and to determine the LS-SVM model parameters.
Finally,in order to meet the requirement of variable measurement and optimal control in the fermenting process,design the data acquisition system to collect data of key parameters such as temperature,pH value,dissolved oxygen,and design the erythromycin fermentation process control system structure.
引文
[1]李海清,黄志尧.特种检测技术及应用[M].杭州:浙江大学出版社,2000.
[2]克理斯特安尼等著,李国正等译.支持向量机导论[M].电子工业出版社,2003.
[3]翁佩芳.固态发酵生物反应动力学理论及反应器研究进展[J].中国酿造,200l,2:6-8.
[4]王树青.发酵过程控制的新进展.化工自动化及仪表,1995,22(4):3-10
[5]李艳.发酵工业概论[M].北京:中国轻工业出版社,1999
[6]张伦.红霉素市场现状与发展趋势[J].中国药房,2003(12):713-715
[7]郑琦,卢红卫,辛平等.生物传感器在环境监测和发酵工业中的应用[[J].仪器仪表学报,2006,27(12):1746-1748.
[8]张广.生物传感器在生物工程研究中的应用[J].太原师范学院学报,2005,4(3):82-84.
[9]黄显,粟大超,徐可欣等.基于微型面的等离子共振生物传感器的葡萄糖溶液测量技术[J].传感技术学报,2006,90(5):20722076.
[10]佘俐莹,张认诚.生物传感器概述[[J].仪器仪表,2007,14(1):2-3.
[11]覃柳,浏仲明.电化学生物传感器研究进度[J].中国医学物理学杂志,2007,124(1):60-62.
[12]黄风良.软测量思想与软测量技术[J].计量学报,2004,25(3):284-288.
[13]胡长松,贾延刚,夏伯楷.软测量技术现状与发展[J].石油仪器,2003,(3):4-7.
[14]荣冈,金晓民,王树青.先进控制技术及应用(第三讲):软测量技术及其应用[J],化工自动化及仪表,1999,26(4):70-72.
[15]Gonzalez,CzD.Soft Sensors for Processing Plants[C].IEEE Proceedings of the Second International Conference on IPMM,1999,(1):59-69.
[16]Peife Yu,Jiangang Lu.Soft sensor based on kernel principal componment analysis and radial basis function neural network for microbiological fermentation [C].IEEE the Sixth World Congress on WCICA,2006,(1):4851-4858.
[17]D.Beluhan,D.Gosak,N.Pavlovic,M.Vampola.Biomass estimation and optimal control of the baker's yeast fermentation process[J].Computers and Chemical Engineering.1995,19,387-392.
[18]Zhao Y.Studies on modeling and control of continuous biotechnical processes,Norway[J],Norwegian University of Science and Technology,1996,125-128.
[19]Pinchuk RJ,Brown WA,Hughes SM.Modeling of biological processes using self-cycling fermentation and genetic algorithms[J].Biotechnology and Bioengineering,2000,67(1),19-24.
[20]Feng M,Glassey J.Physiological state-specific models in estimation of recombinant Escherichia coil fermentation performance[J],Biotechnology and Bioengineering.2000,69(5):495-503.
[21]Lubenova V.On-line estimation of biomass concentration and non stationary parameters for aerobic bioprocess[J],Journal of Biotechnology.1996,46.197-207.
[22]方柏山,谢晓兰,S.Sirisansaneeyakul,胡宗定.木糖醇发酵过程参数的在线软测量[J],天津大学学报,2000,33(5),607-609.
[23]Glassey J,Ignova M.Ward A C.Bioprocess supervision:neural networks and knowledge based systems[J].Journal of Biotechnology,1997,52,201-205
[24]Cimander C,Cadsson M.Mandenius C F.Sensor fusion for on-line monitoring of yoghurt fermentation[J],Journal of Biotechnology,2002,99,237-248
[25]Ronen M,Shabtai Y.Hybrid model building methodology using unsupervised fuzzy clustering and supervised neural networks[J],Biotechnoiogy and Bioengineering,2002,77(4),420-429.
[26]方千山,王永初.软测量技术在发酵过程中的应用研究[J],厦门大学学报(自然科学版),2001,40(6):1324-1328.
[27]Shene C,Diez C,Bravo S.Neural networks for the prediction of the state of Zymomonas mobilis CP4 batch fermentations[J],Computers and Chemical Engineering,1999,23:1097-1108
[28]Zorzetto L F M,Maciel F R,Wolf-Maciel M R.Process modeling development through artificial neural networks and hybrid models[J],Computers and Chemical Engineering,2000,24:1355-1360
[29]隋青美,王正欧.发酵过程混合神经网络模型及其仿真[J],系统仿真学报,2002,14(4):415-417.
[30]Liangyu Lei,Zonghai Sun.Soft sensor based on generalized support vector machines for microBiological fermentation[C].IEEE Proceedings of the Fourth International Conference on Machine Leaning and Cybernetics,2005,4305-4309
[31]罗荣富,邵惠鹤.软测量方法及其工业应用[M].工业过程模型化与控制,上海交大出版社,1994,253-260.
[32]陈坚,堵国成,李寅.发酵工程实验技术[M].北京:化学工业出版社,2005.
[33]李海清,黄志尧.软测量技术原理及应用[M].北京:化学工业出版社,2000.
[34]Weimin Zhong,Daoying Pi,Youxian Sun.SVM based soft sensor for antibiotic fermentation process[J].IEEE,2003,160-164.
[35]Mejdell T,Skogestod S.Estimation of distillation composition from multiple-temperature measurements using partial-least-square regression,Ind.Eng.Chen Res,1991,30(12),2543-2565.
[36]Kreisselmeier G..Adaptive observer with exponential convergence,IEEE Trans Conts AC,1977,22(1):2-8.
[37]Tham M.T,Montague C.A,Morris A.J,et al.Soft-sensors for process estimation and inferential control,J of Proc Cont,1991,1(1):3-14.
[38]L.Zhou,et al.Modeling and control for nonlinear time-delay System via pattern recognition,IEEE Trans.Neural Networks,1992,3(6),991-997.
[39]王武,杨海麟.超声波在生物发酵工程中的应用[J].无锡轻工业大学学报,2002,2 1(3):322-326.
[40]褚蕾蕾.计算智能的数学基础[M].北京:科学出版社,2002.
[41]Vapnik V N.The Nature of Statistical Leaming Theory[M].New York:Springer Verlag,1995.
[42]Suykens J A K,Vandewalle J.Least squares support vector machine classifiers.Neural Processing Letters,1999,9(3):293-300.
[43]Suykens J A K,Lukas L,Van Dooren P,De Moor B,Vandewalle J.Least square support vector machine classifiers:a large scale algorithm.Proceedings of the European Conference on Circuit Theory and Design(ECCTD'99),Stresa,Italy,1999,(9):839-842
[44]刘毅,王海青.采用最小二乘支持向最机的青霉素发酵过程[J].生物工程学报,2006,22(1):144-149.
[45]邬正义,施健.基于鲁棒最小二乘支持向量机的聚丙烯熔融指数预报[[J].华东理工大学学报,2006,32(7):889-892.
[46]杨琳.基于支持向量机的微生物发酵过程生物量软测量方法研究[D].北京: 北京化工大学,2005.
[47]陈渭泉,刘瑞兰等.基于贝叶斯方法的4-CBA含量的软测量研究[[J].化工自动化及仪表,2003,30(5):49-51.
[48]虎仿超.高压溶出过程苛性比值与溶出率软测量计算机系统开发[D].长沙:中南大学,2004.
[49]李勇.一种新的灰关联分析算法在软测量中的应用[J].自动化学报,2006,32(2):311-317.
[50]刘瑞兰.软测量技术若干问题的研究及工业应用[D].杭州:浙江大学,2004.
[51]于静江,周春晖.过程控制中的软测量技术.控制理论与应用,1996,13(2):137-144.
[52]Hsuan-Tien Lin,Chih-Jen Lin.A study on sigmoid kernels for SVM and training of non-PSD kernels by SMO-type Methods.www.csie.ntu.edu.tw/-cjlin/papers/tanh.pdf.
[53]Chih-Wei Hsu,Chih-Chung Chang,Chih-Jen Lin.A practical guide to support vector classification,www.csie.ntu.edu.tw/-cilin/iibsvm/.
[54]Chapeile O,Vapnik V,Bousquet O,Mukherjee S.Choosing multiple parameters for support machines.Machine Learning,2002,(46):131-159.
[55]Michael W Browne.Cross-validation method.Joumal of Mathematical Psychology,2000,(44):108-132.
[56]席少霖,赵风治.最优化计算方法.上海科学技术出版社,1983
[57]余龙江.发酵工程原理与技术应用.北京.化学工业出版社,2006
[2]克理斯特安尼等著,李国正等译.支持向量机导论[M].电子工业出版社,2003.
[3]翁佩芳.固态发酵生物反应动力学理论及反应器研究进展[J].中国酿造,200l,2:6-8.
[4]王树青.发酵过程控制的新进展.化工自动化及仪表,1995,22(4):3-10
[5]李艳.发酵工业概论[M].北京:中国轻工业出版社,1999
[6]张伦.红霉素市场现状与发展趋势[J].中国药房,2003(12):713-715
[7]郑琦,卢红卫,辛平等.生物传感器在环境监测和发酵工业中的应用[[J].仪器仪表学报,2006,27(12):1746-1748.
[8]张广.生物传感器在生物工程研究中的应用[J].太原师范学院学报,2005,4(3):82-84.
[9]黄显,粟大超,徐可欣等.基于微型面的等离子共振生物传感器的葡萄糖溶液测量技术[J].传感技术学报,2006,90(5):20722076.
[10]佘俐莹,张认诚.生物传感器概述[[J].仪器仪表,2007,14(1):2-3.
[11]覃柳,浏仲明.电化学生物传感器研究进度[J].中国医学物理学杂志,2007,124(1):60-62.
[12]黄风良.软测量思想与软测量技术[J].计量学报,2004,25(3):284-288.
[13]胡长松,贾延刚,夏伯楷.软测量技术现状与发展[J].石油仪器,2003,(3):4-7.
[14]荣冈,金晓民,王树青.先进控制技术及应用(第三讲):软测量技术及其应用[J],化工自动化及仪表,1999,26(4):70-72.
[15]Gonzalez,CzD.Soft Sensors for Processing Plants[C].IEEE Proceedings of the Second International Conference on IPMM,1999,(1):59-69.
[16]Peife Yu,Jiangang Lu.Soft sensor based on kernel principal componment analysis and radial basis function neural network for microbiological fermentation [C].IEEE the Sixth World Congress on WCICA,2006,(1):4851-4858.
[17]D.Beluhan,D.Gosak,N.Pavlovic,M.Vampola.Biomass estimation and optimal control of the baker's yeast fermentation process[J].Computers and Chemical Engineering.1995,19,387-392.
[18]Zhao Y.Studies on modeling and control of continuous biotechnical processes,Norway[J],Norwegian University of Science and Technology,1996,125-128.
[19]Pinchuk RJ,Brown WA,Hughes SM.Modeling of biological processes using self-cycling fermentation and genetic algorithms[J].Biotechnology and Bioengineering,2000,67(1),19-24.
[20]Feng M,Glassey J.Physiological state-specific models in estimation of recombinant Escherichia coil fermentation performance[J],Biotechnology and Bioengineering.2000,69(5):495-503.
[21]Lubenova V.On-line estimation of biomass concentration and non stationary parameters for aerobic bioprocess[J],Journal of Biotechnology.1996,46.197-207.
[22]方柏山,谢晓兰,S.Sirisansaneeyakul,胡宗定.木糖醇发酵过程参数的在线软测量[J],天津大学学报,2000,33(5),607-609.
[23]Glassey J,Ignova M.Ward A C.Bioprocess supervision:neural networks and knowledge based systems[J].Journal of Biotechnology,1997,52,201-205
[24]Cimander C,Cadsson M.Mandenius C F.Sensor fusion for on-line monitoring of yoghurt fermentation[J],Journal of Biotechnology,2002,99,237-248
[25]Ronen M,Shabtai Y.Hybrid model building methodology using unsupervised fuzzy clustering and supervised neural networks[J],Biotechnoiogy and Bioengineering,2002,77(4),420-429.
[26]方千山,王永初.软测量技术在发酵过程中的应用研究[J],厦门大学学报(自然科学版),2001,40(6):1324-1328.
[27]Shene C,Diez C,Bravo S.Neural networks for the prediction of the state of Zymomonas mobilis CP4 batch fermentations[J],Computers and Chemical Engineering,1999,23:1097-1108
[28]Zorzetto L F M,Maciel F R,Wolf-Maciel M R.Process modeling development through artificial neural networks and hybrid models[J],Computers and Chemical Engineering,2000,24:1355-1360
[29]隋青美,王正欧.发酵过程混合神经网络模型及其仿真[J],系统仿真学报,2002,14(4):415-417.
[30]Liangyu Lei,Zonghai Sun.Soft sensor based on generalized support vector machines for microBiological fermentation[C].IEEE Proceedings of the Fourth International Conference on Machine Leaning and Cybernetics,2005,4305-4309
[31]罗荣富,邵惠鹤.软测量方法及其工业应用[M].工业过程模型化与控制,上海交大出版社,1994,253-260.
[32]陈坚,堵国成,李寅.发酵工程实验技术[M].北京:化学工业出版社,2005.
[33]李海清,黄志尧.软测量技术原理及应用[M].北京:化学工业出版社,2000.
[34]Weimin Zhong,Daoying Pi,Youxian Sun.SVM based soft sensor for antibiotic fermentation process[J].IEEE,2003,160-164.
[35]Mejdell T,Skogestod S.Estimation of distillation composition from multiple-temperature measurements using partial-least-square regression,Ind.Eng.Chen Res,1991,30(12),2543-2565.
[36]Kreisselmeier G..Adaptive observer with exponential convergence,IEEE Trans Conts AC,1977,22(1):2-8.
[37]Tham M.T,Montague C.A,Morris A.J,et al.Soft-sensors for process estimation and inferential control,J of Proc Cont,1991,1(1):3-14.
[38]L.Zhou,et al.Modeling and control for nonlinear time-delay System via pattern recognition,IEEE Trans.Neural Networks,1992,3(6),991-997.
[39]王武,杨海麟.超声波在生物发酵工程中的应用[J].无锡轻工业大学学报,2002,2 1(3):322-326.
[40]褚蕾蕾.计算智能的数学基础[M].北京:科学出版社,2002.
[41]Vapnik V N.The Nature of Statistical Leaming Theory[M].New York:Springer Verlag,1995.
[42]Suykens J A K,Vandewalle J.Least squares support vector machine classifiers.Neural Processing Letters,1999,9(3):293-300.
[43]Suykens J A K,Lukas L,Van Dooren P,De Moor B,Vandewalle J.Least square support vector machine classifiers:a large scale algorithm.Proceedings of the European Conference on Circuit Theory and Design(ECCTD'99),Stresa,Italy,1999,(9):839-842
[44]刘毅,王海青.采用最小二乘支持向最机的青霉素发酵过程[J].生物工程学报,2006,22(1):144-149.
[45]邬正义,施健.基于鲁棒最小二乘支持向量机的聚丙烯熔融指数预报[[J].华东理工大学学报,2006,32(7):889-892.
[46]杨琳.基于支持向量机的微生物发酵过程生物量软测量方法研究[D].北京: 北京化工大学,2005.
[47]陈渭泉,刘瑞兰等.基于贝叶斯方法的4-CBA含量的软测量研究[[J].化工自动化及仪表,2003,30(5):49-51.
[48]虎仿超.高压溶出过程苛性比值与溶出率软测量计算机系统开发[D].长沙:中南大学,2004.
[49]李勇.一种新的灰关联分析算法在软测量中的应用[J].自动化学报,2006,32(2):311-317.
[50]刘瑞兰.软测量技术若干问题的研究及工业应用[D].杭州:浙江大学,2004.
[51]于静江,周春晖.过程控制中的软测量技术.控制理论与应用,1996,13(2):137-144.
[52]Hsuan-Tien Lin,Chih-Jen Lin.A study on sigmoid kernels for SVM and training of non-PSD kernels by SMO-type Methods.www.csie.ntu.edu.tw/-cjlin/papers/tanh.pdf.
[53]Chih-Wei Hsu,Chih-Chung Chang,Chih-Jen Lin.A practical guide to support vector classification,www.csie.ntu.edu.tw/-cilin/iibsvm/.
[54]Chapeile O,Vapnik V,Bousquet O,Mukherjee S.Choosing multiple parameters for support machines.Machine Learning,2002,(46):131-159.
[55]Michael W Browne.Cross-validation method.Joumal of Mathematical Psychology,2000,(44):108-132.
[56]席少霖,赵风治.最优化计算方法.上海科学技术出版社,1983
[57]余龙江.发酵工程原理与技术应用.北京.化学工业出版社,2006