摘要
维生素C(又名L-抗坏血酸,L-ascorbic acid)是人体必需的一种维生素,我国维生素C生产采用的是具有自主知识产权的二步发酵法生成其重要前体—2-酮基-L-古龙酸(2-keto-L-Gulonic acid, 2-KGA),2-KGA经过烯醇化酸化生成维生素C。随着生物发酵技术的发展以及生产规模的不断扩大,工厂对发酵过程的自动化水平、安全性和可靠性要求越来越高。然而,2-KGA发酵过程不同于一般的化工过程,它涉及两种菌体的繁殖、代谢过程,两种菌体之间的生长相互影响,机理复杂,难以用准确的数学机理模型来描述。随着计算机集散控制系统的应用与发展,大量的过程数据被及时采集和存储,如何利用这些数据包含的过程状态信息提高发酵过程性能是当前过程优化控制领域的研究热点问题,也是本文的研究内容。
本文基于2-KGA发酵过程丰富的在线测量和离线分析数据,利用人工智能技术(支持向量机、智能数据库技术、模糊逻辑等)和统计分析方法,研究建立了基于数据驱动的优化2-KGA发酵过程的关键技术,首先对发酵过程关键状态变量进行超前预报,其次建立2-KGA发酵过程的评价指标—效益函数并对其进行超前预报,在预报的基础上在线评估发酵批次的创利潜力,从而对多罐并行发酵系统实施优化调度,最后在上述研究基础上开发了一套相应的软件在发酵生产车间在线运行,形成2-KGA发酵过程运行优化体系。主要研究成果包括:
1.建立2-KGA发酵过程关键状态变量的超前预报模型
2-KGA发酵过程关键状态变量(如产量、2-KGA浓度)难以在线测量,但反映了过程所处的状态,是优化发酵过程的重要依据,因此状态变量的超前预报将对发酵过程的优化有指导意义,本文建立2-KGA发酵过程产量超前预报模型,将AdaBoost回归模型与基于支持向量机滚动-学习预报技术相结合,依次训练一组基于支持向量机的滚动学习-预报器(弱预报器),每个弱预报器采用不同的参数,利用AdaBoost算法将弱SVM预报器提升为强SVM预报器,减少了调试参数的工作量,利用2-KGA工业发酵过程数据对本文建立的预报模型进行验证表明其具有较好的泛化性能和抗噪性能。在产量预报的基础上,利用统计分析对发酵液体积进行预估进而得出2-KGA浓度的预报值。另外,生产过程染菌的难以避免造成异常批次的产生,本文建立基于产量预报的异常批次早期发现方法,利用工业发酵数据进行验证表明该方法是可行的,能及时给出预警信息。
2.建立2-KGA发酵过程效益函数的在线计算与预报模型
对2-KGA发酵车间实施优化调度首先需要建立描述2-KGA发酵过程性能的评价指标,本文建立效益函数这一指标反映过程的经济行为,效益函数定义为单位时间内一个批次所创造的毛利润,通过物料衡算、能量衡算在线计算出发酵批次的效益函数,并采用基于SVM的滚动-学习预报技术对其进行超前预报,为发酵批次的在线分类、优化调度作准备。首先给出用于效益函数预报的初始训练库的建立,然后提出了历史数据库的两种在线更新方案,即分别基于分类、K-NN算法的更新策略,进而利用2-KGA工业发酵过程数据对两种方案的预报性能进行了评估,确定出预报效果较好的更新数据库方案。
3.对2-KGA发酵过程实施优化调度
本文对2-KGA工业发酵过程建立的优化调度策略主要是提供一种补料优化方法,改变传统的、各批次补料量固定(L-山梨糖资源平均分配)的生产方式,优化山梨糖在各个运行批次中的分配方案。首先根据效益函数的实际值和预报值对发酵批次在线分类,实时评估发酵过程的运行状态,获得发酵过程的创利潜力,利用状态反馈信息来确定或调节该批次的补糖量。创利潜力高的优势批次通过继续流加碳源(L-山梨糖)适当延长操作周期,挖取该批次创利潜力,而对创利能力差的劣势批次,适度减少碳源分配量,避免发酵车间的效益损失,从而使多反应器并列运行车间的经济效益最大化。此外,文中还讨论了实施优化调度方案时基于模糊逻辑技术的发酵周期的预估问题。通过对背景厂发酵车间的历史批次实施拟在线优化调度,该调度方案将给车间带来6.86%的收益增量。
4.开发了2-KGA发酵过程在线预报-优化调度软件
在上述研究的理论成果基础上,开发了一套2-KGA发酵过程在线预报-优化调度软件,该软件实时采集发酵过程各种数据(在线测量和离线分析数据),采用支持向量机、AdaBoost算法、统计分析、智能数据库、模糊逻辑等数据驱动技术,实现2-KGA发酵过程产量、产物浓度及效益函数的在线预报、发酵批次创利潜力的在线评估,以及发酵车间优化调度、发酵过程阶段辨识和异常批次的早期发现等优化控制的关键技术应用于工业发酵生产中,提高了2-KGA工业发酵过程的自动化水平。该软件已在背景厂发酵车间安装调试成功并在线运行。
L-ascorbic acid (L-AA) also known as vitamin C is an essential nutrient for human being. In the 1970s, an innovative bioconversion process was developed for the production of 2-keto-L-gulonic acid (2-KGA), a key precursor for L-ascorbic acid synthesis. With this process, 2-KGA is produced via the two-stage fermentation, and then converted to L-AA by catalytic reactions. Since then, fermentation became the dominant process in the L-AA production. In the last decades, the equipment and production scale in fermentation industries are rapidly expanded with the development of biotechnology, then the higher automation, stability and reliability of the process are required. However, it is difficult to obtain the kinetic modeling for 2-KGA fermentation processes because the complex interactions of the two involved microorganisms are not well known yet. On the other hand, a large amount of process data are collected from industrial 2-KGA cultivation and the data contain abundant information of processes. Therefore, data-driven improvement of the process performance is focused on in this dissertation.
Based on the on-line measurements and off-line assay data, key technologies are studied in this dissertation for optimizing industrial 2-KGA fermentation processes, such as on-line prediction of state variables, optimal scheduling for multi-bioreactor workshop, process monitoring and fault detection, where artificial intelligence technologies (e.g., support vector machines, intelligent database and fuzzy logic) and statistical analysis methods are applied. The main contents are as follow:
1. Prediction of state variables in industrial 2-KGA fermentation processes
The state variables such as 2-KGA formation and 2-KGA concentration could provide important information for the optimization of fermentation processes. Data-driven prediction of the state variables is presented in this paper. The 2-KGA formation is on-line predicted by integrating SVM-based rolling learning-prediction technology with the AdaBoost algorithm. The AdaBoost algorithm is used to adaptively boost the performance of SVM predictors, which is demonstrated to be beneficial to improve the prediction accuracy and the robustness. The validation results by using the data from commercial scale 2-KGA cultivation show good generalization performance and noise tolerance of the prediction approach. According to the estimation of future medium volume by statistical analysis and the prediction of total product, 2-KGA concentration is predicted.
Due to the risk of contamination and other disturbances, the abnormality of fermentation processes often arises. The on-line fault detection method based on the prediction of product formation is presented for industrial 2-KGA cultivation. The results demonstrate that the proposed method could rapidly detect abnormalities of the processes.
2. On-line computation and prediction of the profit function
The profit function is an integrated index to describe the cost-effect of the 2-KGA fermentation processes, which is defined as the gross profit of a batch over its production time. The profit function is online calculated according to the mass balance and further predicted with the SVM-based rolling learning-prediction technique, which is potentially applicable for optimal scheduling. In the dissertation, it is also discussed how to establish and update the historical training database. Two updating database methods are proposed according to the profit category and the K-NN algorithm, respectively. The prediction results using the data from industrial scale 2-KGA cultivation indicate the advantage of the K-NN algorithm-based updating method and that may be independent on the inoculation sequences.
3. Optimal scheduling for 2-KGA cultivation
An optimal scheduling approach for 2-KGA fermentation process is proposed to improve allocation of L-sorbose resource with the aim of maximizing the economic profit of the multi-bioreactor workshop. The empirical operation in 2-KGA cultivation under study is to assign the same quantity of L-sorbose to each batch regardless of the batch-to-batch variations, while the optimal scheduling approach presented will determine the L-sorbose feeding according to the evaluation of the profit-making ability of the individual batch. Each batch is on-line evaluated based on the batch classification and its scheduling function. The batches of high profit-making ability will be fed more L-sorbose to lengthen the cultivation of these batches and exploit their profit contribution, while the poorly performed batches will be decreased the quantity of fed L-sorbose and terminated earlier to avoid profit loss. As a result, the scheduling strategy will make use of the L-sorbose resource more effectively and yield higher overall profit. Pseudo-on-line scheduling is carried out by using the data of industrial 2-KGA batches. The total profit increase of ca. 7% is demonstrated in comparison with the empirical operation.
4. Developing on-line prediction and optimal scheduling software for 2-KGA fermentation processes
Finally, the software is developed for 2-KGA fermentation processes based on the theoretic researches in this dissertation. The software real-time collects data from 2-KGA industrial cultivation. It is able to realize on-line prediction of the key state variables such as total product and product concentration, computation and prediction of the profit function, on-line evaluating the profit-making potential of the current batches, and optimal scheduling for multi-bioreactor system. The software has been installed and run successfully in the 2-KGA fermentation workshop.
引文
[1] Bremus C., Herrmann U., Bringer-Meyer S. The use of microorganisms in L-ascorbic acid production. Journal of Biotechnology, 2006, 124: 196-205.
[2]耿海义,崔永涛.维生素C工艺及应用现状.中国现代应用药学杂志, 2005, 22 (7): 691-693.
[3]魏东芝,袁渭康,尹光琳,袁中一,陈敏恒.维生素C二步发酵法过程动力学模型的研究.生物工程学报, 1992, 8 (3): 277—282.
[4]谢占武,周海霞,曹爱国.维生素C的工艺发展.实用药物与临床,2005 (8): 1-2.
[5]网站信息:维生素C市场出现四大家族格局,中国投资咨询, http://www.ocn.com.cn/free/200809/weishengs%20181147.htm,2008-09-18.
[6] Reichstein T., Grüssner A. Eine ergiebige Synthese der l-Ascorbins?ure (C-Vitamin). Helvetica Chimica Acta, 1934, 17: 311-328.
[7] Ning W.Z., Tao Z.X., Wang C.H., Wang S.D., Yan Z.Z., Yin G.L. Fermentation process for producing 2-keto-L-gulonic acid. European Patent. 0278447. 1988.
[8] Hancock R.D., Viola R. Biotechnological approaches for L-ascorbic acid production. Trends in Biotechnology, 2002, 20 (7): 299-305.
[9]仪宏,张华峰,朱文众,曾远智.维生素C生产技术.中国食品添加剂, 2003, 6: 76-81.
[10]耿海义.维生素C发酵工艺的研究[学位论文].天津:天津大学. 2003.
[11]谢萍.补料分批发酵工艺在维生素C二步发酵中的应用研究[学位论文].天津:天津大学. 2004.
[12] Ji A.G., Gao P.J. Synthesis of 2-keto-L-gulonic acid from gluconic acid by co-immobilized Gluconobacter oxydans and Corynebacterium sp.. Biotechnology Letters, 1998, 20: 939–942.
[13] Macauley-Patrick S., McNeil B., Harvey L.M. By-product formation in the D-sorbitol to L-sorbose biotransformation by Gluconobacter suboxydans ATCC 621 in batch and continuous cultures. Process Biochemistry, 2005, 40: 2113–2122.
[14] Urbance J.W., Bratina B.J., Stoddard S.F. Taxonomic characterization of Ketogulonigenium vulgare gen. nov., sp. Nov. and Ketogulonigenium robustum sp. nov., which oxidize L-sorbose to 2-keto-L-gulonic acid. International Journal of Systematic and Evolutionary Microbiology, 2001, 51: 1059-1070.
[15] Xu A., Yao J., Yu L. Mutation of Gluconobacter oxydans and Bacillus megaterium in a two-step process of L-ascorbic acid manufacture by ion beam. Journal of Applied Microbiology, 2004, 96: 1317-1323.
[16]张舟,朱可丽,张海宏,冯树,张忠泽. Vc二步发酵中Na+、Ca++及pH对巨大芽孢杆菌生长作用的影响.微生物学杂志, 1998, 18 (3): 24-26.
[17]仲崇斌,张忠泽,刘延吉,张文革.环境因子对新组合菌系产生Vc前体KGA的影响.生物技术, 2003, 13 (5) : 27-28.
[18] De A., Adilson J., Rubens M., Soft sensors development for on-line bioreactor state estimation. Computers and Chemical Engineering, 2000, 24 (2): 1099 -1103.
[19] Kadlec P., Gabrys B., Strandt S. Data-driven soft sensors in the process industry. Computers and Chemical Engineering, 2009, 33: 795-814.
[20] Chen L.Z., Nguang S.K., Li X.M., Chen X.D. Soft sensors for on-line biomass measurements. Bioprocess and Biosystems Engineering, 2004, 26 (3): 191-195.
[21] Riverol C., Cooney J. Estimation of the ester formation during beer fermentation using neural networks. Journal of Food Engineering, 2007, 82: 585-588.
[22]吕淑霞,冯树,张忠泽等. Vc二步发酵中伴生菌的作用机制.微生物学通报, 2001, 28 (5):10-13.
[23]冯树,孙传宝,张忠泽,朱可丽,张海宏,高永涛.维生素C二步发酵中巨大芽孢杆菌对氧化葡萄糖酸杆菌生长和产酸的影响.微生物学杂志, 1998, 18 (1): 6-9.
[24]周彬,李义,刘耀平,张忠泽,朱可莉,廖德明,高永涛. Vc二步发酵中的微生物生态调控.应用生态学报, 2002, 13 (11): 1452-1454.
[25] Zamprogna E., Barolo M., Seborg, D.E. Estimating product composition profiles in batch distillation via partial least squares regression. Control Engineering Practice, 2004, 12 (7): 917–929.
[26] Zhao Y.H. A soft sensor based on orthogonal nonlinear principal component analysis, Developments in Chemical Engineering and Mineral Processing, 2005, 13: 233-242.
[27] Wentzell P.D., Montoto L.V. Comparison of principal components regression and partial least squares regression through generic simulations of complex mixtures. Chemometrics and Intelligent Laboratory Systems, 2003, 65: 257–279.
[28] Gunther J.C., Conner J.S., Seborg D.E. Process monitoring and quality variable prediction utilizing PLS in industrial fed-batch cell culture. Journal of Process Control, 2009, 19 (5):914-921.
[29] Li X., Chan C.W. Application of an enhanced decision tree learning approach for prediction of petroleum production. Engineering Applications of Artificial Intelligence, 2010, 23: 102-109.
[30] Wu L.C., Lee J.X., Huang H.D., Liu B.J., Horng J.T. An expert system to predict protein thermostability using decision tree. Expert Systems with Applications, 2009, 36 (5): 9007-9014.
[31] Devogelaere D., Rijckaert M., Leon O.G., Lemus G.C. Application of feedforward neural networks for soft sensors in the sugar industry. In Proceedings of the VII Brazilian symposium on neural networks, 2002: 2-6.
[32] Radhakrishnan V.R., Mohamed A.R. Neural networks for the identification and control of blast furnace hot metal quality. Journal of Process Control, 2000, 10 (6): 509-524.
[33] Fortuna L., Graziani S., Xibilia M.G. Soft sensors for product quality monitoring in debutanizer distillation columns. Control Engineering Practice, 2005, 13 (4): 499-508.
[34] Wang L., Shao C., Wang H., Wu H. Radial basis function neural networksbased modeling of the membrane separation process: Hydrogen recovery from refinery gases. Journal of Natural Gas Chemistry, 2006, 15 (3): 230-234.
[35] Su H.B., Fan L.T., Schlup J.R. Monitoring the process of curing of epoxy/graphite fiber composites with a recurrent neural network as a soft sensor. Engineering Applications of Artificial Intelligence, 1998, 11 (2): 293-306.
[36] Shene C., Diez C., Bravo S. Neural networks for the prediction of the state of Zymomonas mobilis CP4 batch fermentations. Computers and Chemical Engineering, 1999, 23: 1097-1108.
[37] Chen L.Z., Nguang S.K., Li X.M., Chen X.D. Soft sensors for on-line biomass measurements. Bioprocess and Biosystems Engineering, 2004, 26 (3): 191-195.
[38] Laursen S.?., Webb D., Ramirez W.F. Dynamic hybrid neural network model of an industrial fed-batch fermentation process to produce foreign protein. Computers and Chemical Engineering, 2007, 31: 163-170.
[39] Lawryńczuk M. Modelling and nonlinear predictive control of a yeast fermentation biochemical reactor using neural networks. Chemical Engineering Journal, 2008, 145: 290-307.
[40] Niu D., Wang F., Zhang L., He D., Jia M. Neural network ensemble modeling for nosiheptide fermentation process based on partial squares regression. Chemometrics and Intelligent Laboratory Systems, 2011, 105 (1): 125-130.
[41] Nagy Z.K. Model based control of a yeast fermentation bioreactor using optimally designed artificial neural networks. Chemical Engineering Journal, 2007, 127 (1-3): 95-109.
[42] Rosales-Colunga L.M., García R.G., Rodríguez A.D.L. Estimation of hydrogen production in genetically modified E. coli fermentations using an artificial neural network. International Journal of Hydrogen Energy, 2010, 35 (24): 13186-13192.
[43] Xiong Z., Zhang J. Modelling and optimal control of fed-batch processes using a novel control affine feedforword neural network. Neurocomputing, 2004, 61: 317-337.
[44] Araúzo-Bravo M.J., Cano-Izquierdo J.M., Gómez-Sánchez E., López-Nieto M.J., Dimitriadis Y.A., López-Coronado J. Automatization of a penicillin production process with soft sensors and an adaptive controller based on neuro fuzzy systems. Control Engineering Practice, 2004, 12 (9): 1073-1090.
[45] Khazraee S.M., Jahanmiri A.H. Composition estimation of reactive batch distillation by using adaptive neuro-fuzzy inference system. Chinese Journal of Chemical Engineering, 2010, 18 (4): 703-710.
[46] Nauck D., Klawonn F., Kruse R., Klawonn F. Foundations of neuro-fuzzy systems. New York, NY, USA: John Wiley & Sons, Inc. 1997.
[47] Feng R., Shen W., Shao H., A soft sensor modeling approach using support vector machines. Proceedings of the American Control Conference, 2003: 3702-3707.
[48] Yan W., Shao H., Wang X. Soft sensing modeling based on support vector machine and Bayesian model selection. Computers and Chemical Engineering, 2004, 28 (8): 1489–1498.
[49] Wang J.L., Yu T., Jin C.Y. On-line estimation of biomass in fermentation process using support vector machine. Chinese Journal of Chemical Engineering, 2006, 14: 383-388.
[50] Wang X., Chen J., Liu C., Pan F. Hybrid modeling of penicillin fermentation process based on least square support vector machine. Chemical Engineering Research and Design, 2010, 88: 415-420.
[51] Liu G., Zhou D., Xu H., Mei C. Model optimization of SVM for a fermentation soft sensor. Expert Systems with Applications, 2010, 37: 2708-2713.
[52] Chang P.C., Liu C.H., Lai R.K. A fuzzy case-based reasoning model for sales forecasting in print circuit board industries. Expert Systems with Applications, 2008, 34: 2049-2058.
[53] Park C.S., Han I. A case-based reasoning with the feature weights derived by analytic hierarchy process for bankruptcy prediction. Expert Systems with Applications, 2002, 23 (3): 255-264.
[54] Venkatasubramanian V., Rengaswamy R., Yin K.W., Kavuri S.N. A review of process fault detection and diagnosis Part I: Quantitative model-based methods. Computers and Chemical Engineering, 2003, 27 (3): 293-311.
[55] Venkatasubramanian V., Rengaswamy R., Yin K.W., Kavuri S.N. A review of process fault detection and diagnosis Part II: Quantitative models and search strategies. Computers and Chemical Engineering, 2003, 27 (3): 313-326.
[56] Venkatasubramanian V., Rengaswamy R., Yin K.W., Kavuri S.N. A review of process fault detection and diagnosis Part III: Process history based methods. Computers and Chemical Engineering, 2003, 27 (3): 327-346.
[57]谢磊.间歇过程统计性能监控研究[学位论文].杭州:杭州大学. 2005.
[58] Heluane H., Colombo M., Hernández M.R. Enhancing sugar cane process performance through optimal production scheduling. Chemical engineering and processing, 2007, 46: 198-209.
[59] Schügerl K. Progress in monitoring, modeling and control of bioprocesses during the last 20 years. Journal of Biotechnology, 2001; 85: 149-173.
[60] Gadkar K.G., Mahadevan R., Doyle F.J. Optimal genetic manipulations in batch bioreactor control. Automatica, 2006, 42 (10): 1723-1733.
[61] Pinto J.M., Türkay A., Bolio B., Grossmann I.E. STBS: A continuous-time MILP optimization for short-term scheduling of batch plants. Computers and Chemical Engineering, 1998, 22: 1297-1308.
[62] Floudas C.A., Lin X.X. Continuous-time versus discrete-time approaches for scheduling of chemical processes: a review. Computers and Chemical Engineering, 2004, 28: 2109–2129.
[63] Neumann K., Schwindt C., Trautmann N. Scheduling of continuous and discontinuous material flows with intermediate storage restrictions. European Journal of Operational Research, 2005, 165 (2): 495-509.
[64] Yuan J.Q., Xue Y.F., Hu K.L., Wu H.T., Jia Q. On-line application oriented optimal scheduling for penicillin fed-batch fermentation. Chemical Engineering and Processing, 2009, 48: 651-658.
[65] Akyol D.E., Bayhan G.M. A review on evolution of production scheduling with neural networks. Computers & Industrial Engineering, 2007, 53: 95-122.
[66] Honkomp S.J., Lombardo S., Rosen O., Pekny J.F. The curse of reality—why process scheduling optimization problems are difficult in practice. Computers and Chemical Engineering, 2000, 24: 323-328.
[67] Janiak A., Kozan E., Lichtenstein M. Metaheuristic approaches to the hybrid flow shop scheduling problem with a cost-related criterion. International Journal of Production Economics, 2007, 105 (2): 407-424.
[68] Méndez C.A., CerdáJ. Grossmann I.E. State-of-the-art review of optimization methods for short-term scheduling of batch processes. Computers and Chemical Engineering, 2006, 30: 913-946.
[69] Tousain R.L., Bosgra O.H. Market-oriented scheduling and economic optimization of continuous multi-grade chemical processes. Journal of Process Control, 2006, 16: 291-302.
[70] Allahverdi A., Ng C.T., Cheng T.C.E., Kovalyov M.Y. A survey of scheduling problems with setup times or costs. European Journal of Operational Research, 2008, 187: 985-1032.
[71] Lau S., Willis M.J., Montague G.A. Predictive scheduling of a bioprocess plant. IN: Proceedings of the IASTED International Conference on Modelling, Simulation and Optimatization, Banff, Alta., Canada, 2003: 296-301.
[72] Shah N. Pharmaceutical supply chains: Key issues and strategies for optimisation, Computers and Chemical Engineering, 2004, 28 (6-7): 929-941.
[73] Papageorgiou L.G. Supply chain optimisation for the process industries: Advances and opportunities. Computers and Chemical Engineering, 2009, 33 (12): 1931-1938.
[74] Lin X., Janak S.L., Floudas C.A. A new robust optimization approach for scheduling under uncertainty. I. Bounded uncertainty. Computers and Chemical Engineering, 2004, 28: 1069–1085.
[75] Jia Z., Ierapetritou M.G. Short-term scheduling under uncertainty using MILP sensitivity analysis. Industrial and Engineering Chemistry Research, 2004, 43: 3782–3791.
[76] Jia Z., Ierapetritou M.G. Generate pareto optimal solutions of scheduling problems using normal boundary intersection technique. Computers and Chemical Engineering, 2006, 31: 268–280.
[77] Jia Z., Ierapetritou M.G. Uncertainty analysis on the right-handside for MILP problems. AIChE Journal, 2006, 52 (7): 2486–2495.
[78] Li Z., Ierapetritou M.G. Process scheduling under uncertainty: Review and challenges. Computers and Chemical Engineering, 2008, 32 (4-5): 715-727.
[79] Petrovic D., Duenas A. A fuzzy logic based production scheduling/rescheduling in the presence of uncertain disruptions. Fuzzy Sets and Systems, 2006, 157: 2273-2285.
[80] Dondo R.G. A method for detection and diagnosis on batch fermentations. ISA Transactions, 2003, 42 (1): 135-147.
[81] Zhao X., Yan W., Shao H. Monitoring and fault diagnosis for batch process based on feature extract in fisher subspace. Chinese Journal of Chemical Engineering, 2006, 14 (6): 759-764.
[82] Liu Y.C., Wang F.S., Lee W.C. On-line monitoring and controlling system for fermentation processes. Biochemical Engineering Journal, 2001, 7 (1): 17-25.
[83] Hu K.L., Yuan J.Q. Bath process monitoring with tensor factorization. Journal of Process Control, 2009, 19 (2): 288-296.
[84] Zhang H., Lennox B. Integrated condition monitoring and control of fed-batch fermentation processes. Journal of Process Control, 2004, 14: 41-50.
[85] Vapnik V.N., The nature of statistical learning theory, Berlin: Springer, 1995.
[86] Burges C.J.C., A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 1998, 2 (2): 955-974.
[87] Vapnik V. N. Statistical Learning Theory. Wiley, New York, 1998.
[88] Hermes L., Frieauff D., Puzicha J. Support vector machines for land usage classification in landsat TM imagery. International Geoscience and Remote Sensing Symposium, 1999, 1: 348-350.
[89] Kim K.J. Financial time series forecasting using support vector machines. Neurocomputing, 2003,55 (1-2): 307-319.
[90] Feng R., Shen W., Shao H., A soft sensor modeling approach using support vector machines, In: Proceedings of the American Control Conference, 2003, 3702-3707.
[91] Byun H., Lee S.W., A survey on pattern recognition applications of support vector machines, International Journal of Pattern Recognition and Artificial Intelligence, 2003, 17 (3): 459-486.
[92] Li Y.F., Yuan J.Q. Prediction of key state variables using support vector machines in bioprocesses. Chemical Engineering & Technology, 2006, 29: 313-319.
[93] Gencoglu M.T., Uyar M. Prediction of flashover voltage of insulators using least squares support vector machines. Expert Systems with Applications, 2009, 36: 10789-10798.
[94] Liu G.H., Zhou D.W., Xu H.X., Mei C.L. Model optimization of SVM for a fermentation soft sensor. Expert Systems with Applications, 2010, 37: 2708-2713.
[95] Wang W.J., Men C.Q., Lu W.Z. Online prediction model based on support vector machine. Neurocomputing, 2008, 71: 550-558.
[96]范明,柴玉梅等译.统计学习基础—数据挖掘、推理与预测.北京:电子工业出版社, 2004.
[97]李国正,王猛,曾华军.支持向量机导论.北京:电子工业出版社, 2005.
[98]邓乃杨,田英杰.数据挖掘中的新方法—支持向量机.北京:科学出版社, 2005.
[99] Freund Y., Schapire R.E. A decision-theoretic generalization of on-line learning and an application to boosting. IN: Computational Learning Theory: Second European Conference, EuroCOLT, Springer-Verlag, 1995: 23-37.
[100] Freund Y., Schapire R.E. Experiment with a new boosting algorithm. Proceedings of the 13th International Conference on Machine Learning, 1996: 148-156.
[101] Freund Y., Schapire R.E. A decision-theoretic generalisation of on-line learning and an application of boosting. Journal of Computer and System Sciences, 1997, 55 (1): 119-139.
[102] Li X., Wang L., Sung E.. AdaBoost with SVM-based component classifiers. Engineering Applications of Artificial Intelligence, 2008, 21 (5): 785-795.
[103] Mathanker S.K., Weckler P.R., Bowser T.J., Wang N., Maness N.O. AdaBoost classifiers for pecan defect classification. Computers and Electronics in Agriculture, 2011, 77 (1): 60-68.
[104] Dogan H., Akay O. Using AdaBoost classifiers in a hierarchical framework for classifying surface images of marble slabs. Expert Systems with Applications, 2010, 37 (12): 8814-8821.
[105] Alfaro E., García N., Gámez M., Elizondo D. Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks. Decision Support Systems, 2008, 45 (1): 110-122.
[106] Solomatine D.P., Shrestha D.L. AdaBoost. RT: a boosting algorithm for regression problems. IEEE International Joint Conference on Neural Networks, 2004: 1163-1168.
[107] Yuan J.Q., Guo S.R., Schügerl K., Bellgardt K.H. Profit optimisation for mycelia fed-batch fermentation. Journal of Biotechnology, 1997, 54: 175-193.
[108] Cui L., Xu Y.Y., Jia Q., Wu H.T., Yuan J.Q. Prediction of the Profit Function for Industrial 2-keto-L-gulonic Acid Cultivation. Chemical Engineering & Technology, 2011, 34 (5): 751-759.
[109] Yuan J.Q., Xue Y.F., Hu K.L., Wu H.T., Jia Q. On-line application oriented optimal scheduling for penicillin fed-batch fermentation. Chemical Engineering and Processing, 2009, 48: 651-658.
[110] Dasarathy B. Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. McGraw-Hill Computer Science Series, IEEE Computer Society Press, Las Alamitos, California, 1991.
[111] Guerre E. Design adaptive nearest neighbor regression estimation. Journal of Multivariate Analysis, 2000, 75 (2): 219-244.
[112] Cheng C., Chiu M.S. A new data-based methodology for nonlinear process modeling. Chemical Engineering Science, 2004, 59 (13): 2801-2810.