基于人工智能和代谢调控的典型好氧发酵过程在线控制和故障诊断
|
摘要
绝大多数的大宗发酵产品，如氨基酸、生物酶、生物药物蛋白等均依靠好氧发酵生产。除了选育优良菌种外，发酵过程控制技术也是提高发酵性能的重要手段。好氧发酵过程存在许多共性问题，例如：传统离线控制难以取得满意的效果，而许多重要的发酵参数又无法在线测量，实施发酵过程在线控制存在困难；发酵故障时有发生，严重影响发酵过程的稳定性和经济性；供氧压力巨大、溶解氧浓度（DO）难以控制、通纯氧发酵大大增加了发酵操作的成本和不安全因素。针对上述问题，本论文以利用两种典型的、好氧型大宗产品的发酵菌种（重组毕赤酵母和谷氨酸棒杆菌）生产药物蛋白和谷氨酸的过程为研究对象，深入研究了基于人工智能和代谢调控的发酵过程预测、在线控制和故障诊断的关键技术，旨在为好氧大宗产品发酵搭建共性平台，提高目标产物的浓度、发酵稳定性和发酵过程的整体性能。论文的主要研究内容总结如下：
（1）利用毕赤酵母生产猪α干扰素（pIFN-α）的发酵过程中，发酵性能指标、pIFN-α抗病毒活性（pIFN-α-AVA）难以测量，发酵性能无法预测。为此，以易测量的发酵参数（诱导时间/温度、DO、O2消耗速率OUR、CO2释放速率CER、甲醇消耗速率、总蛋白浓度）为输入，以pIFN-α-AVA为输出，研究比较了基于多项式回归和人工神经网络（ANN）模型（传统BP-ANN和基于遗传算法的改良型ANN）的pIFN-α-AVA的预测性能。基于遗传算法的改良型ANN模型具有最准确的预测和泛化能力。分析pIFN-α-AVA对各发酵参数的感度发现，CER、OUR和甲醇消耗速率对pIFN-α-AVA影响最大。
（2）利用MutS型毕赤酵母生产pIFN-α时，发酵性能不稳定。在甘油流加培养期，使用传统DO-Stat法流加甘油，存在乙醇生成积累的现象。如果细胞长时间地（>4h）处在高乙醇浓度（>6g L-1）的环境下，甲醇诱导无法启动。分析测定甲醇代谢途径关键酶的基因转录水平和酶活，结果发现并证实：培养期内、乙醇长时间处在高浓度下，醇氧化酶（AOX）的活性和基因转录水平不可逆转地受到抑制，这是pIFN-α发酵不稳定的最主要原因。利用商业化甲醇电极可以在线测量乙醇、并据此提出了基于乙醇在线测量的改良型自适应的DO-Stat甘油流加控制策略。该策略可以同时利用甘油和积累的乙醇、将乙醇浓度稳定在线地控制于低水平（约2g L-1），且不影响细胞生长速度。无乙醇浓度控制批次的最高pIFN-α浓度仅达到2.08g L-1，且不稳定。而只要乙醇浓度得到控制，pIFN-α浓度均可稳定在2.70~3.65g L-1的高水平，且受后续诱导条件的影响较小。pIFN-α浓度得到提高、发酵性能不稳定问题得到根本解决。
（3）使用具有强AOX启动子的Mut+表型重组毕赤酵母发酵生产猪圆环病毒Cap蛋白时，甲醇利用效率低、耗氧严重、DO难以控制、Cap蛋白表达水平低。利用DO对添加等量甲醇和山梨醇的时间响应存在差异的特征现象，提出并构建了一种基于DO在线测量和模糊推理技术的甲醇/山梨醇共混流加自动控制系统。使用该控制系统、并将DO控制于10%时，甲醇代谢途径中的几个关键酶的活性均明显提高、甲醇流加速度得到适度限制、供氧压力得到缓解、DO可以稳定控制在期望水平。此时，甲醇利用效率显著改善、胞内毒副中间产物的积累缓解；Cap蛋白浓度达到198mg·L-1，比使用甲醇诱导策略最优批次的相应值121mg·L-1明显提高；诱导可在通空气条件下进行，整体发酵性能大幅改善。
（4）利用生物素缺陷型谷氨酸棒杆菌发酵生产谷氨酸时，培养基中的生物素浓度波动严重影响发酵性能的稳定。为此，提出了基于智能型模式识别的发酵故障诊断系统。在某一时间窗口内、利用支持向量机（SVM）分类器对可在线测量的过程参数（发酵时间、搅拌转速、耗氨速率、OUR、CER）进行状态分类，并结合模糊推理技术将发酵状态划分成生物素“不足”、“适中”、“过量”的三种模式，构建了智能型的故障诊断系统。通过刻意制造“不足”、“适中”和“过量”的初始生物素浓度环境，获取大量、对应于不同发酵状态模式的数据，建立以生物素初始浓度和发酵时间为输入、其他可在线测量参数为输出的人工神经网络模型，自动生成大量数据对（datapairs），对上述故障诊断系统的有效性进行了仿真模拟研究。模拟结果表明：该故障诊断系统可以将不同初始生物素浓度下的发酵批次进行合理聚类，对发酵状态具有良好的识别判断能力。
（5）将上述故障诊断系统实用于谷氨酸发酵过程。在初始生物素含量“适中”的条件下，该在线故障诊断系统自始至终没有发出预警信号；而在初始生物素含量不当的情况下，该系统均可以在发酵初期（6~8h）准确地识别判别出故障类型，并通过补加纯生物素或吐温40、对“错误”发酵批次进行补救。通过有效的故障识别和补救，该系统对“错误”发酵批次的识别结果逐步返回到生物素含量“适中”的范围内，所有发酵批次的谷氨酸最终浓度均达到75~80g·L-1的正常水平，发酵稳定性显著改善。
Most of the bulk fermentation products, such as amino acids, enzymes, drug proteins, etc.are produced through aerobic fermentations. Besides strains breeding or screening, processcontrol technique is an alternative way for fermentation performance improvement. Aerobicfermentations suffer with many common problems, for example, off-line control has limitedpower in performance improvement, and implementing of on-line process control is difficultas many crucial fermentation parameters can not be on-line measured; the occurrence offermentation faults severely deteriorate fermentation stability and economics; extremely highoxygen supply load causes difficulty in dissolved oxygen concentration (DO) control and pureoxygen based aeration which largely increases operation cost and safety risk. Focusing onthose problems, in this thesis, drug proteins and glutamate fermentations by two typicalaerobic strains, recombinant Pichia patoris and Corynebacterium glutamicum, were used asthe prototypes, and the key techniques of intelligent and metabolic engineering based on-linestate prediction, adaptive control and fault diagnosis were investigated. The purpose ofdeveloping such key techniques is to supply a technological platform to the typical aerobicfermentation processes, to effectively improve targeted product concentrations, fermentationstabilities and performance. The major results of the dissertation were summarized as follows:
(1) In porcine interferon-α (pIFN-α) production by Pichia pastoris, fermentationperformance is hardly to predict, as pIFN-α antiviral activity (pIFN-α-AVA) was difficult tomeasure. Prediction performance of various models, including polynomial regression basedmodel and ANN models (BP-ANN and “improved” ANN optimized by genetic algorithm),were compared, with the easily measurable parameters (induction time/temperature, DO, O2uptake rate OUR, CO2evolution rate CER, methanol consumption rate, and total proteinconcentration) as the inputs and pIFN-α-AVA as the output. Among the models, the improvedANN model indicated the most accurate and universal abilities. Sensitivity analysis suggestedthat CER, OUR and methanol consumption rate were closely correlated with pIFN-α-AVA.
(2) pIFN-α production by MutSP. pastoris is unstable. Ethanol accumulation occurred iftraditional DO-Stat method was adopted for glycerol feeding during cultivation phase.Methanol induction could not be initiated if the cells were subject to high ethanolconcentration environment (>6g·L-1) for longer time (>4h). Analyzing the transcriptionallevels and activities of the key enzymes in methanol metabolism routes revealed that, thelong-term and high level accumulation of ethanol during cultivation phase irreversiblyrepressed the activity and transcriptional level of alcohol oxidase (AOX), which deterioratedpIFN-α fermentation stability in turn. Using a commercialized methanol electrode to on-linedetect ethanol, an on-line ethanol measurement based adaptive DO-Stat glycerol feedingstrategy was thus proposed. The strategy could alternatively utilize glycerol and theaccumulated ethanol to control ethanol concentrations at low level (2g L-1) without cellgrowth rate deterioration. The maximal pIFN-α concentration in runs without ethanolconcentration control was2.08g L-1, but unstable. pIFN-α concentrations in runs with low ethanol accumulation could be stabilized at higher levels of2.70~3.65g·L-1.Fermentationperformance could be successfully stabilized and enhanced.
(3) Porcine circovirus Cap protein production by Mut+P. pastoris with strong AOXpromoter suffered with the problems: inefficient methanol utilization, extensively highoxygen supply requirement, difficulty in stably controlling DO, very low Cap protein titer.Based on DO response patterns against the addition of methanol or sorbitol with equal amount,a DO on-line measurement and fuzzy logical inference based automatic methanol/sorbitolco-feeding control system was proposed. With the aid of this control system by setting DOcontrol level at10%, key enzymes in methanol metabolism route were largely activated;methanol feeding rate was restricted at a moderate level; oxygen supply load was relieved;and DO was stably controlled at the desired level. Under this condition, methanol utilizationefficiency was greatly improved and accumulation of toxic intermediate metabolites wasrelieved. Cap protein concentration reached a level of198mg·L-1, which was much higherthan the maximal value of121mg·L-1in the runs by methanol induction. Induction could beconducted by air-aeration and overall fermentation performance enhanced significantly.
(4) In glutamate fermentation by biotin-auxotroph C. glutamicum, the biotin contentvariation in culture medium severely affects fermentation stability. An intelligent patternrecognition based fault diagnosis system was thus proposed to solve the problem. A supportvector machine classifier (SVM) was firstly used to categorize the on-line measurableparameters (fermentation time, agitation rate, NH3consumption rate, OUR and CER) within amoving-window, and then the SVM was combined with fuzzy reasoning technique toconstruct an unique intelligent fault diagnosis system, which could classify the fermentationphysiological states into3catagories of biotin “in shortage”,“medium”, and “in excess”. Byexperimentally varying the initial biotin content to intently creat the three differentfermentation states and obtaining a large amount corresponding data, an artificial neuralnetwork (ANN) model was developed with initial biotin content and fermentation time as theinputs, the other on-line measurable parameters as the outputs. This ANN model couldautomatically generate a large amount of data pairs to simulate the effectiveness of the faultdiagnosis system. Simulation results indicated that the fault diagnosis system could clusterfermentation runs corresponding to different initial biotin content well and had goodfermentation states recognition ability.
(5) The fault diagnosis system was applied to glutamate fermentation process for on-linefault diagnosis. In the cases of initial biotin content “medium”, the system did not send anywarning signals throughout the fermentations; while in the cases of improper initial biotincontents, the system could accurately identify the faults and their type in the earlyfermentation stage (6~8h), and rescue those failure-likelihood fermentations by adding purebiotin or tween40. After the rescue measures were taken, outputs of the system weregradually recovered to the normal range, final glutamate concentrations in all testing runsreached to normal levels of75~80g·L-1, and fermentation stability significantly enhanced.
（1）利用毕赤酵母生产猪α干扰素（pIFN-α）的发酵过程中，发酵性能指标、pIFN-α抗病毒活性（pIFN-α-AVA）难以测量，发酵性能无法预测。为此，以易测量的发酵参数（诱导时间/温度、DO、O2消耗速率OUR、CO2释放速率CER、甲醇消耗速率、总蛋白浓度）为输入，以pIFN-α-AVA为输出，研究比较了基于多项式回归和人工神经网络（ANN）模型（传统BP-ANN和基于遗传算法的改良型ANN）的pIFN-α-AVA的预测性能。基于遗传算法的改良型ANN模型具有最准确的预测和泛化能力。分析pIFN-α-AVA对各发酵参数的感度发现，CER、OUR和甲醇消耗速率对pIFN-α-AVA影响最大。
（2）利用MutS型毕赤酵母生产pIFN-α时，发酵性能不稳定。在甘油流加培养期，使用传统DO-Stat法流加甘油，存在乙醇生成积累的现象。如果细胞长时间地（>4h）处在高乙醇浓度（>6g L-1）的环境下，甲醇诱导无法启动。分析测定甲醇代谢途径关键酶的基因转录水平和酶活，结果发现并证实：培养期内、乙醇长时间处在高浓度下，醇氧化酶（AOX）的活性和基因转录水平不可逆转地受到抑制，这是pIFN-α发酵不稳定的最主要原因。利用商业化甲醇电极可以在线测量乙醇、并据此提出了基于乙醇在线测量的改良型自适应的DO-Stat甘油流加控制策略。该策略可以同时利用甘油和积累的乙醇、将乙醇浓度稳定在线地控制于低水平（约2g L-1），且不影响细胞生长速度。无乙醇浓度控制批次的最高pIFN-α浓度仅达到2.08g L-1，且不稳定。而只要乙醇浓度得到控制，pIFN-α浓度均可稳定在2.70~3.65g L-1的高水平，且受后续诱导条件的影响较小。pIFN-α浓度得到提高、发酵性能不稳定问题得到根本解决。
（3）使用具有强AOX启动子的Mut+表型重组毕赤酵母发酵生产猪圆环病毒Cap蛋白时，甲醇利用效率低、耗氧严重、DO难以控制、Cap蛋白表达水平低。利用DO对添加等量甲醇和山梨醇的时间响应存在差异的特征现象，提出并构建了一种基于DO在线测量和模糊推理技术的甲醇/山梨醇共混流加自动控制系统。使用该控制系统、并将DO控制于10%时，甲醇代谢途径中的几个关键酶的活性均明显提高、甲醇流加速度得到适度限制、供氧压力得到缓解、DO可以稳定控制在期望水平。此时，甲醇利用效率显著改善、胞内毒副中间产物的积累缓解；Cap蛋白浓度达到198mg·L-1，比使用甲醇诱导策略最优批次的相应值121mg·L-1明显提高；诱导可在通空气条件下进行，整体发酵性能大幅改善。
（4）利用生物素缺陷型谷氨酸棒杆菌发酵生产谷氨酸时，培养基中的生物素浓度波动严重影响发酵性能的稳定。为此，提出了基于智能型模式识别的发酵故障诊断系统。在某一时间窗口内、利用支持向量机（SVM）分类器对可在线测量的过程参数（发酵时间、搅拌转速、耗氨速率、OUR、CER）进行状态分类，并结合模糊推理技术将发酵状态划分成生物素“不足”、“适中”、“过量”的三种模式，构建了智能型的故障诊断系统。通过刻意制造“不足”、“适中”和“过量”的初始生物素浓度环境，获取大量、对应于不同发酵状态模式的数据，建立以生物素初始浓度和发酵时间为输入、其他可在线测量参数为输出的人工神经网络模型，自动生成大量数据对（datapairs），对上述故障诊断系统的有效性进行了仿真模拟研究。模拟结果表明：该故障诊断系统可以将不同初始生物素浓度下的发酵批次进行合理聚类，对发酵状态具有良好的识别判断能力。
（5）将上述故障诊断系统实用于谷氨酸发酵过程。在初始生物素含量“适中”的条件下，该在线故障诊断系统自始至终没有发出预警信号；而在初始生物素含量不当的情况下，该系统均可以在发酵初期（6~8h）准确地识别判别出故障类型，并通过补加纯生物素或吐温40、对“错误”发酵批次进行补救。通过有效的故障识别和补救，该系统对“错误”发酵批次的识别结果逐步返回到生物素含量“适中”的范围内，所有发酵批次的谷氨酸最终浓度均达到75~80g·L-1的正常水平，发酵稳定性显著改善。
Most of the bulk fermentation products, such as amino acids, enzymes, drug proteins, etc.are produced through aerobic fermentations. Besides strains breeding or screening, processcontrol technique is an alternative way for fermentation performance improvement. Aerobicfermentations suffer with many common problems, for example, off-line control has limitedpower in performance improvement, and implementing of on-line process control is difficultas many crucial fermentation parameters can not be on-line measured; the occurrence offermentation faults severely deteriorate fermentation stability and economics; extremely highoxygen supply load causes difficulty in dissolved oxygen concentration (DO) control and pureoxygen based aeration which largely increases operation cost and safety risk. Focusing onthose problems, in this thesis, drug proteins and glutamate fermentations by two typicalaerobic strains, recombinant Pichia patoris and Corynebacterium glutamicum, were used asthe prototypes, and the key techniques of intelligent and metabolic engineering based on-linestate prediction, adaptive control and fault diagnosis were investigated. The purpose ofdeveloping such key techniques is to supply a technological platform to the typical aerobicfermentation processes, to effectively improve targeted product concentrations, fermentationstabilities and performance. The major results of the dissertation were summarized as follows:
(1) In porcine interferon-α (pIFN-α) production by Pichia pastoris, fermentationperformance is hardly to predict, as pIFN-α antiviral activity (pIFN-α-AVA) was difficult tomeasure. Prediction performance of various models, including polynomial regression basedmodel and ANN models (BP-ANN and “improved” ANN optimized by genetic algorithm),were compared, with the easily measurable parameters (induction time/temperature, DO, O2uptake rate OUR, CO2evolution rate CER, methanol consumption rate, and total proteinconcentration) as the inputs and pIFN-α-AVA as the output. Among the models, the improvedANN model indicated the most accurate and universal abilities. Sensitivity analysis suggestedthat CER, OUR and methanol consumption rate were closely correlated with pIFN-α-AVA.
(2) pIFN-α production by MutSP. pastoris is unstable. Ethanol accumulation occurred iftraditional DO-Stat method was adopted for glycerol feeding during cultivation phase.Methanol induction could not be initiated if the cells were subject to high ethanolconcentration environment (>6g·L-1) for longer time (>4h). Analyzing the transcriptionallevels and activities of the key enzymes in methanol metabolism routes revealed that, thelong-term and high level accumulation of ethanol during cultivation phase irreversiblyrepressed the activity and transcriptional level of alcohol oxidase (AOX), which deterioratedpIFN-α fermentation stability in turn. Using a commercialized methanol electrode to on-linedetect ethanol, an on-line ethanol measurement based adaptive DO-Stat glycerol feedingstrategy was thus proposed. The strategy could alternatively utilize glycerol and theaccumulated ethanol to control ethanol concentrations at low level (2g L-1) without cellgrowth rate deterioration. The maximal pIFN-α concentration in runs without ethanolconcentration control was2.08g L-1, but unstable. pIFN-α concentrations in runs with low ethanol accumulation could be stabilized at higher levels of2.70~3.65g·L-1.Fermentationperformance could be successfully stabilized and enhanced.
(3) Porcine circovirus Cap protein production by Mut+P. pastoris with strong AOXpromoter suffered with the problems: inefficient methanol utilization, extensively highoxygen supply requirement, difficulty in stably controlling DO, very low Cap protein titer.Based on DO response patterns against the addition of methanol or sorbitol with equal amount,a DO on-line measurement and fuzzy logical inference based automatic methanol/sorbitolco-feeding control system was proposed. With the aid of this control system by setting DOcontrol level at10%, key enzymes in methanol metabolism route were largely activated;methanol feeding rate was restricted at a moderate level; oxygen supply load was relieved;and DO was stably controlled at the desired level. Under this condition, methanol utilizationefficiency was greatly improved and accumulation of toxic intermediate metabolites wasrelieved. Cap protein concentration reached a level of198mg·L-1, which was much higherthan the maximal value of121mg·L-1in the runs by methanol induction. Induction could beconducted by air-aeration and overall fermentation performance enhanced significantly.
(4) In glutamate fermentation by biotin-auxotroph C. glutamicum, the biotin contentvariation in culture medium severely affects fermentation stability. An intelligent patternrecognition based fault diagnosis system was thus proposed to solve the problem. A supportvector machine classifier (SVM) was firstly used to categorize the on-line measurableparameters (fermentation time, agitation rate, NH3consumption rate, OUR and CER) within amoving-window, and then the SVM was combined with fuzzy reasoning technique toconstruct an unique intelligent fault diagnosis system, which could classify the fermentationphysiological states into3catagories of biotin “in shortage”,“medium”, and “in excess”. Byexperimentally varying the initial biotin content to intently creat the three differentfermentation states and obtaining a large amount corresponding data, an artificial neuralnetwork (ANN) model was developed with initial biotin content and fermentation time as theinputs, the other on-line measurable parameters as the outputs. This ANN model couldautomatically generate a large amount of data pairs to simulate the effectiveness of the faultdiagnosis system. Simulation results indicated that the fault diagnosis system could clusterfermentation runs corresponding to different initial biotin content well and had goodfermentation states recognition ability.
(5) The fault diagnosis system was applied to glutamate fermentation process for on-linefault diagnosis. In the cases of initial biotin content “medium”, the system did not send anywarning signals throughout the fermentations; while in the cases of improper initial biotincontents, the system could accurately identify the faults and their type in the earlyfermentation stage (6~8h), and rescue those failure-likelihood fermentations by adding purebiotin or tween40. After the rescue measures were taken, outputs of the system weregradually recovered to the normal range, final glutamate concentrations in all testing runsreached to normal levels of75~80g·L-1, and fermentation stability significantly enhanced.
引文
1.王镜岩,朱圣庚,徐长法.生物化学（下）[M].北京：高等教育出版社,2002.118-144.
2. Cereghino G P L, Cereghino J L, Ilgen C, et al. Production of recombinant proteins in fermenter culturesof the yeast Pichia pastoris[J]. Curr Opin Biotechnol,2002,13(4):329-332
3. Jin H, Liu G, Ye X, et al. Enhanced porcine interferon-alpha production by recombinant Pichia pastoriswith a combinational control strategy of low induction temperature and high dissolved oxygenconcentration[J]. Biochem Eng J,2010,52(1):91-98
4. Lee C Y, Lee S J, Jung K H, et al. High dissolved oxygen tension enhances heterologous proteinexpression by recombinant Pichia pastoris[J]. Process Biochem,2003,38(8):1147-1154
5.王霞,张世有.好氧发酵过程中影响溶解氧的因素及如何提高溶解氧的浓度[J].黑龙江医药,2005(4):276-277
6.王志仁.氨基酸发酵[J].发酵科技通讯,1981(2):3-14
7.胡学智.酶制剂工业概况及其应用进展[J].工业微生物,2003(4):32-41
8.王睿,刘桂超.论我国酶制剂工业的发展[J].畜牧与饲料科学,2011(1):68-69
9.崔进梅,宋磊,邓学箴等.基因工程药物的表达系统及发展状况[J].齐鲁药事,2005(2):104-105
10.蒋伯诚.基因重组药物[J].药学进展,1995(3):129-134
11. Xiao J, Shi Z P, Gao P, et al. On-line optimization of glutamate production based on balancedmetabolic control by RQ[J]. Bioprocess Biosyst Eng,2006,29(2):109-117
12. Zhang C Y, Shi Z P, Gao P, et al. On-line prediction of products concentrations in glutamatefermentation using metabolic network model and linear programming[J]. Biochem Eng J,2005,25(2):99-108
13. Lee C Y, Nakano A, Shiomi N, et al. Effects of substrate feed rates on heterologous protein expressionby Pichia pastoris in DO-stat fed-batch fermentation[J]. Enzyme Microb Technol,2003,33(4):358-365
14. Hu X, Chu J, Zhang Z, et al. Effects of different glycerol feeding strategies onS-adenosyl-L-methionine biosynthesis by P-GAP-driven Pichia pastoris overexpressing methionineadenosyltransferase[J]. J Biotechnol,2008,137(1):44-49
15. Jin H, Zheng Z, Gao M, et al. Effective induction of phytase in Pichia pastoris fed-batch culture usingan ANN pattern recognition model-based on-line adaptive control strategy[J]. Biochem Eng J,2007,37(1):26-33
16. Jia D, Liu L, Wang H, et al. Overproduction of a truncated poly (vinyl alcohol) dehydrogenase inrecombinant Pichia pastoris by low-temperature induction strategy and related mechanism analysis[J].Bioprocess Biosyst Eng,2013,36(8):1095-1103
17. Gao M, Dong S, Yu R, et al. Improvement of ATP regeneration efficiency and operation stability inporcine interferon-alpha production by Pichia pastoris under lower induction temperature[J]. Korean JChem Eng,2011,28(6):1412-1419
18. Wu D, Yu X W, Wang T C, et al. High yield rhizopus chinenisis prolipase production in Pichiapastoris: impact of methanol concentration[J]. Biotechnol Bioprocess Eng,2011,16(2):305-311
19. Minning S, Serrano A, Ferrer P, et al. Optimization of the high-level production of Rhizopus oryzaelipase in Pichia pastoris[J]. J Biotechnol,2001,86(1):59-70
20. Yamawaki S, Matsumoto T, Ohnishi Y, et al. Production of single-chain variable fragment antibody(scFv) in fed-batch and continuous culture of Pichia pastoris by two different methanol feeding methods[J].J Biosci Bioeng,2007,104(5):403-407
21. Charoenrat T, Ketudat-Cairns M, Stendahl-Andersen H, et al. Oxygen-limited fed-batch process: analternative control for Pichia pastoris recombinant protein processes[J]. Bioprocess Biosyst Eng,2005,27(6):399-406
22. Khatri N K, Hoffmann F. Oxygen-limited control of methanol uptake for improved production of asingle-chain antibody fragment with recombinant Pichia pastoris[J]. Appl Microbiol Biotechnol,2006,72(3):492-498
23. Woo S H, Park S H, Lim H K, et al. Extended operation of a pressurized75-L bioreactor for shLkn-1production by Pichia pastoris using dissolved oxygen profile control[J]. J Ind Microbiol Biotechnol,2005,32(10):474-480
24. Celik E, Calik P, Oliver S G. Metabolic flux analysis for recombinant protein production by Pichiapastoris using dual carbon sources: effects of methanol feeding rate[J]. Biotechnol Bioeng,2010,105(2):317-329
25. Gao M, Li Z, Yu R, et al. Methanol/sorbitol co-feeding induction enhanced porcine interferon-alphaproduction by P. pastoris associated with energy metabolism shift[J]. Bioprocess Biosyst Eng,2012,35(7):1125-1136
26. Jungo C, Marison I, von Stockar U. Mixed feeds of glycerol and methanol can improve theperformance of Pichia pastoris cultures: A quantitative study based on concentration gradients in transientcontinuous cultures[J]. J Biotechnol,2007,128(4):824-837
27. Wang Z, Wang Y, Zhang D, et al. Enhancement of cell viability and alkaline polygalacturonate lyaseproduction by sorbitol co-feeding with methanol in Pichia pastoris fermentation[J]. Bioresour Technol,2010,101(4):1318-1323
28. Arnau C, Ramon R, Ferrer P, et al. Sorbitol co-feeding an efficient strategy to reduce metabolic burdencaused by the overexpression of a Rhizopus oryzae lipase in Pichia pastoris[J]. J Biotechnol,2007,131(2):S76-S76
29. Yu R, Dong S, Zhu Y, et al. Effective and stable porcine interferon-alpha production by Pichia pastorisfed-batch cultivation with multi-variables clustering and analysis[J]. Bioprocess Biosyst Eng,2010,33(4):473-483
30.左莹,张萍,张惠.玉米浆在氨基酸发酵工业中的作用[J].中国酿造,2013(11):18-22
31.陈银芳. L-赖氨酸产生菌选育及其发酵条件的调控[D]:[硕士学位论文].江南大学,2009
32.袁丹丹. L-缬氨酸产生菌的选育及其发酵条件的调控[D]:[硕士学位论文].江南大学,2010
33.张佑红,王新彬,吴元欣. L-丝氨酸发酵生产菌发酵条件的优化[J].武汉工程大学学报,2007(4):11-14
34.张义萍. L-精氨酸产生菌的选育及其发酵条件优化[D]:[硕士学位论文].江南大学,2006
35.牛大鹏.诺西肽发酵过程建模与优化研究[D]:[博士学位论文].沈阳:东北大学,2010
36. Devlin J F. A simple and powerful method of parameter-estimation using simplex optimization[J].Ground Water,1994,32(2):323-327
37.徐士良.计算方法[M].北京:人民邮电出版社,2009.171-175.
38. Yao L, Sethares W A. Nonlinear parameter-estimation via the genetic algorithm[J]. IEEE Trans SignalProcess,1994,42(4):927-935
39. Dai W, Word D P, Hahn J. Modeling and dynamic optimization of fuel-grade ethanol fermentationusing fed-batch process[J]. Control Eng Practice,2014,22:231-241
40. Jang M F, Chou Y S. Modeling and optimization of bioethanol production via a simultaneoussaccharification and fermentation process using starch[J]. J Chem Technol Biotechnol,2013,88(6):1164-1174
41. Linville J L, Rodriguez M, Jr., Mielenz J R, et al. Kinetic modeling of batch fermentation for Populushydrolysate tolerant mutant and wild type strains of Clostridium thermocellum[J]. Bioresour Technol,2013,147:605-613
42. Guo W, Zhang Y, Lu J, et al. Optimization of fermentation medium for nisin production fromLactococcus lactis subsp lactis using response surface methodology (RSM) combined with artificial neuralnetwork-genetic algorithm (ANN-GA)[J]. Afr J Biotechnol,2010,9(38):6264-6272
43. Pal M P, Vaidya B K, Desai K M, et al. Media optimization for biosurfactant production byRhodococcus erythropolis MTCC2794: artificial intelligence versus a statistical approach[J]. J IndMicrobiol Biotechnol,2009,36(5):747-756
44. Singh V, Khan M, Khan S, et al. Optimization of actinomycin V production by Streptomycestriostinicus using artificial neural network and genetic algorithm[J]. Appl Microbiol Biotechnol,2009,82(2):379-385
45. Guo Y, Xu J, Zhang Y, et al. Medium optimization for ethanol production with Clostridiumautoethanogenum with carbon monoxide as sole carbon source[J]. Bioresour Technol,2010,101(22):8784-8789
46. Singh A, Majumder A, Goyal A. Artificial intelligence based optimization of exocellular glucansucraseproduction from Leuconostoc dextranicum NRRL B-1146[J]. Bioresour Technol,2008,99(17):8201-8206
47. Silva R G, Pinotti L M, Cruz A J G, et al. Artificial neural networks to infer biomass and productconcentration during the production of penicillin G acylase from Bacillus megaterium[J]. J Chem TechnolBiotechnol,2008,83(5):739-749
48. Singh A, Tatewar D, Shastri P N, et al. Application of ANN for prediction of cellulase and xylanaseproduction by Trichoderma reesei under SSF condition[J]. Indian J Chem Technol,2008,15(1):53-58
49. Hur W, Chung Y-K. An artificial neural network for biomass estimation from automatic pH controlsignal[J]. Biotechnol Bioprocess Eng,2006,11(4):351-356
50. Horiuchi J, Shimada T, Funahashi H, et al. Artificial neural network model with a culture database forprediction of acidification step in cheese production[J]. Journal of Food Engineering,2004,63(4):459-465
51. Kiran A U M, Jana A K. Control of continuous fed-batch fermentation process using neural networkbased model predictive controller[J]. Bioprocess Biosyst Eng,2009,32(6):801-808
52. Gadkar K, Mehra S, Gomes J. On-line adaptation of neural networks for bioprocess control[J]. ComputChem Eng,2005,29(5):1047-1057
53. Mészáros A, Andrá ik A, Mizsey P, et al. Computer control of pH and DO in a laboratory fermenterusing a neural network technique[J]. Bioprocess Biosyst Eng,2004,26(5):331-340
54. Nott P J K, Karim M N, Morris A J. Fault and contamination detection in a continuous bakers yeastfermentation[J]. Comput Chem Eng,1996,20: S611-S616
55. Duan S, Shi Z, Feng H, et al. An on-line adaptive control based on DO/pH measurements and ANNpattern recognition model for fed-batch cultivation[J]. Biochem Eng J,2006,30(1):88-96
56. Gao M, Zheng Z, Wu J, et al. Improvement of specific growth rate of Pichia pastoris for effectiveporcine interferon-alpha production with an on-line model-based glycerol feeding strategy[J]. ApplMicrobiol Biotechnol,2012,93(4):1437-1445
57. Shimizu H, Yasuoka H, Uchiyama K. On-Line fault diagnosis for optimal rice α-amylase productionprocess of a temperature-sensitive mutant of saccharomyces cerevisiae by an autoassociative neuralnetwork[J]. J Ferment Bioeng,1997,83(5):435-422
58. Huang J H, Shimizu H, Shioya S. Data preprocessing and output evaluation of an autoassociative neuralnetwork model for online fault detection in virginiamycin production[J]. J Biosci Bioeng,2002,94(1):70-77
59. Bai S, McLean D D, Thibault J. Autoassociative neural networks for robust dynamic datareconciliation[J]. AIChE Journal,2007,53(2):438-448
60.董传亮,潘丰,史仲平.基于自我联想神经网络的谷氨酸发酵在线故障诊断[J].中国酿造,2009(2):96-100
61. Liu G, Zhou D, Xu H, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert SystAppl,2010,37(4):2708-2713
62.陈进东.基于在线支持向量回归的建模与预测控制研究[D]:[博士学位论文].无锡:江南大学,2013
63.王鲜芳.生化过程动态建模及优化控制研究[D]:[博士学位论文].无锡:江南大学,2009
64. Horiuchi J, Kishimoto M. Fuzzy-aided estimation of biological parameters based on materialbalances[J]. J Ferment Bioeng,1998,86(1):111-117
65. Kasperski A, Miskiewicz T. An adaptive fuzzy logic controller using the respiratory quotient as anindicator of overdosage in the baker's yeast process[J]. Biotechnol Lett,2002,24(1):17-21
66. Kishimoto M, Kitta Y, Takeuchi S, et al. Computer control of glutamic-acid production based on fuzzyclusterization of culture phases[J]. J Ferment Bioeng,1991,72(2):110-114
67. Park Y S, Shi Z P, Shiba S, et al. Application of fuzzy-reasoning to control of glucose and ethanolconcentrations in bakers-yeast culture[J]. Appl Microbiol Biotechnol,1993,38(5):649-655
68.史仲平,潘丰.发酵过程解析、控制与检测技术[M].北京:化学工业出版社,2010.7-8.
69. Kleman G L, Chalmers J J, Luli G W, et al. A Predictive and Feedback-control Algorithm Maintains aConstant Glucose-concentration in Fed-batch Fermentations[J]. Appl Environ Microbiol,1991,57(4):910-917
70. Jones K, Williams D, Goodier A. Auto-tuning PID control of dissolved oxygen in a Saccharomycescerevisiae fermentation[J]. Measurement Control,1996,29(9):266-269
71. Jones K O, Williams D, Montgomery P A. On-line application of an auto-tuning PID controller fordissolved oxygen concentration in a fermentation process[J]. Trans Inst Measure Control,1997,19(5):253-262
72. Markx G H, Kell D B. The use of dielectric permittivity for the control of the biomass level duringbiotransformations of toxic substrates in continuous-culture[J]. Biotechnol Progr,1995,11(1):64-70
73. Zhang W H, Smith L A, Plantz B A, et al. Design of methanol feed control in Pichia pastorisfermentations based upon a growth model[J]. Biotechnol Progr,2002,18(6):1392-1399
74. Lee S Y. High cell-density culture of Escherichia coli[J]. Trends Biotech,1996,14(3):98-105
75. Van Duuren J, Wijte D, Karge B, et al. pH-stat fed-batch process to enhance the production of cis,cis-muconate from benzoate by Pseudomonas putida KT2440-JD1[J]. Biotechnol Progr,2012,28(1):85-92
76. Yeh K, Chen C, Chang J. pH-stat photoheterotrophic cultivation of indigenous Chlorella vulgarisESP-31for biomass and lipid production using acetic acid as the carbon source[J]. Biochem Eng J,2012,64:1-7
77. Honda H, Kobayashi T. Fuzzy control of bioprocess in Japan[J]. Biotechnol Ann Rev,2000,5:1-23
78. Honda H, Kobayashi T. Industrial application of fuzzy control in bioprocesses[J]. Adv Biochem EngBiotechnol,2004,87:151-171
79. Oishi K, Tominaga M, Kawato A, et al. Application of fuzzy control-theory to the sake brewingprocess[J]. J Ferment Bioeng,1991,72(2):115-121
80. Alfafara C G, Miura K, Shimizu H, et al. Fuzzy control of ethanol concentration and its application tomaximum glutathione production in yeast fed-batch culture[J]. Biotechnol Bioeng,1993,41(4):493-501
81. Peng Y, Ma Y, Wang S, et al. Fuzzy control of nitrogen removal in predenitrification process usingORP[J]. Water Sci Technol,2005,52(12):161-169
82. Ahioglu S, Altinten A, Ertunc S, et al. Fuzzy control with genetic algorithm in a batch bioreactor[J].Appl Biochem Biotech,2013,171(8):2201-2219
83. Meyer U, Popel H J. Fuzzy-control for improved nitrogen removal and energy saving in WWT-plantswith pre-denitrification[J]. Water Sci Technol,2003,47(11):69-76
84. Lenas P, Kitade T, Watanabe H, et al. Adaptive fuzzy control of nutrients concentration in fed-batchculture of mammalian cells[J]. Cytotechnology,1997,25(1-3):9-15
85. Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosispart I: quantitative model-based methods[J]. Comput Chem Eng,2003,27(3):293-311
86. Dondo R. Measurement processing for state estimation and fault identification in batch fermentations[J].Braz J Chem Eng,2004,21(3):367-392
87. Riverol C, Pilipovik M V. Control and fault diagnosis in bottom fermentation systems using parityspace approach[J]. Biotechnol Progr,2002,18(3):666-667
88. Venkatasubramanian V, Rengaswamy R, Kavuri S N, et al. A review of process fault detection anddiagnosis part III: process history based methods[J]. Comput Chem Eng,2003,27(3):327-346
89. Ku W F, Storer R H, Georgakis C. Disturbance detection and isolation by dynamic principal componentanalysis[J]. Chemometr Intell Lab Syst,1995,30(1):179-196
90. Lee J M, Yoo C, Lee I B. Fault detection of batch processes using multiway kernel principal componentanalysis[J]. Comput Chem Eng,2004,28(9):1837-1847
91. He N, Wang S Q, Xie L. An improved adaptive multi-way principal component analysis for monitoringstreptomycin fermentation process[J]. Chin J Chem Eng,2004,12(1):96-101
92. Agatonovic-Kustrin S, Beresford R. Basic concepts of artificial neural network (ANN) modeling and itsapplication in pharmaceutical research[J]. J Pharm Biomed Anal,2000,22(5):717-727
93. Neath M J, Swain A K, Madawala U K, et al. An optimal PID controller for a bidirectional Inductivepower transfer system using multiobjective genetic algorithm[J]. IEEE Trans Power Elect,2014,29(3):1523-1531
94. Daliri M R. A hybrid automatic system for the diagnosis of lung cancer based on genetic algorithmandfuzzy extreme learning machines[J]. J Med Syst,2012,36(2):1001-1005
95. Mathew B S, Isaac K P. Optimisation of maintenance strategy for rural road network using geneticalgorithm[J]. Int J Pavement Eng,2014,15(4):352-360
96. Acosta-Gonzalez E, Fernandez-Rodriguez F. Forecasting financial failure of firms via geneticalgorithms[J]. Comput Econ,2014,43(2):133-157
97. Jena H M, Roy G K, Mahapatra S S. Determination of optimum gas holdup conditions in a three-phasefluidized bed by genetic algorithm[J]. Comput Chem Eng,2010,34(4):476-484
98. Rao C S, Sathish T, Mahalaxmi M, et al. Modelling and optimization of fermentation factors forenhancement of alkaline protease production by isolated Bacillus circulans using feed-forward neuralnetwork and genetic algorithm[J]. J Appl Microbiol,2008,104(3):889-898
99. Beloufa F, Chikh M A. Design of fuzzy classifier for diabetes disease using Modified Artificial BeeColony algorithm[J]. Comput Method Progr Biomed,2013,112(1):92-103
100. Li Y, Tong S, Li T, et al. Adaptive fuzzy control of uncertain stochastic nonlinear systems withunknown dead zone using small-gain approach[J]. Fuzzy Set Syst,2014,235:1-24
101. Hu P, Cao G, Zhu X, et al. Coolant circuit modeling and temperature fuzzy control of proton exchangemembrane fuel cells[J]. Int J Hydrogen Energy,2010,35(17):9110-9123
102. Beccari M, Majone M. Fuzzy control of disturbances in a wastewater treatment process-Commentreply[J]. Water Res,1997,31(12):3168-3168
103. Almeida G, Vieira J, Marques A S, et al. Estimating the potential water reuse based on fuzzyreasoning[J]. J Environ Manage,2013,128:883-892
104. Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Process Lett,1999,9(3):293-300
105. Lin C F, Wang S D. Fuzzy support vector machines[J]. IEEE Trans Neural networks,2002,13(2):464-471
106. Mangasaian O L, Musicant D R. Lagrangian support vector machines[J]. J Mach Learn Res,2001,1(3):161-177
107. Zhang L, Zhou W D, Jiao L C. Wavelet support vector machine[J]. IEEE Trans Syst Man Cybern B,2004,34(1):34-39
108. Tong S, Koller D. Support vector machine active learning with applications to text classification[J]. JMach Learn Res,2002,2(1):45-66
109. Kim K I, Jung K, Kim J H. Texture-based approach for text detection in images using support vectormachines and continuously adaptive mean shift algorithm[J]. IEEE Trans Patt Anal Mach Int,2003,25(12):1631-1639
110. Zhang W, Yoshida T, Tang X. Text classification based on multi-word with support vector machine[J].Knowl-B Syst,2008,21(8):879-886
111. Meshgini S, Aghagolzadeh A, Seyedarabi H. Face recognition using Gabor-based direct lineardiscriminant analysis and support vector machine[J]. Comput Elect Eng,2013,39(3):727-745
112. Li Y M, Gong S G, Sherrah J, et al. Support vector machine based multi-view face detection andrecognition[J]. Image Vision Comput,2004,22(5):413-427
113. Kumar H, Kumar T A R, Amarnath M, et al. Fault diagnosis of antifriction bearings through soundsignals using support vector machine[J]. J Vibroeng,2012,14(4):1601-1606
114. Maglogiannis I, Loukis E, Zafiropoulos E, et al. Support vectors machine-based identification of heartvalve diseases using heart sounds[J]. Comput Method Progr Biomed,2009,95(1):47-61
115. Zhang K, Lu W, Marziliano P. Automatic knee cartilage segmentation from multi-contrast MR imagesusing support vector machine classification with spatial dependencies[J]. Magn Reson Imaging,2013,31(10):1731-1743
116. Song Q, Hu W J, Xie W F. Robust support vector machine with bullet hole image classification[J].IEEE Trans Syst Man Cybern C,2002,32(4):440-448
117. Tay F E H, Cao L J. Application of support vector machines in financial time series forecasting[J].Omega-Int J Manage SCI,2001,29(4):309-317
118. Kim K J. Financial time series forecasting using support vector machines[J]. Neurocomputing,2003,55(1-2):307-319
119. Al-Dhaifllah M, Westwick D T. Identification of auto-regressive exogenous hammerstein modelsbased on support vector machine regression[J]. IEEE Trans Control Syst Technol,2013,21(6):2083-2090
120. An S, Liu W, Venkatesh S. Fast cross-validation algorithms for least squares support vector machineand kernel ridge regression[J]. Pattern Recogn,2007,40(8):2154-2162
121. Hua Z, Wang Y, Xu X, et al. Predicting corporate financial distress based on integration of supportvector machine and logistic regression[J]. Expert Syst Appl,2007,33(2):434-440
122. Jordan L T, Derbyshire J B. Antiviral activity of interferon against transmissible gastroenteritis virusin cell culture and ligated intestinal segments in neonatal pigs[J]. Vet Microbiol,1994,38(3):263-276
123. Chinsangaram J, Koster M, Grubman M J. Inhibition of L-deleted foot-and-mouth disease virusreplication by alpha/beta interferon involves double-stranded RNA-dependent protein kinase[J]. J Virol,2001,75(12):5498-5503
124. Cao R B, Xu X Q, Zhou B, et al. Gene modification and high prokaryotic expression of porcineinterferon alpha-1[J]. Chin J Biotechnol,2004,20(2):291-294
125. Lefevre F, La Bonnardiere C. Molecular cloning and sequencing of a gene encoding biologicallyactive porcine alpha-interferon[J]. J Interferon Res,1986,6(4):349-360
126. Atici U. Prediction of the strength of mineral admixture concrete using multivariable regressionanalysis and an artificial neural network[J]. Expert Syst Appl,2011,38(8):9609-9618
127. Chelgani S C, Hower J C, Jorjani E, et al. Prediction of coal grindability based on petrography,proximate and ultimate analysis using multiple regression and artificial neural network models[J]. FuelProcess Technol,2008,89(1):13-20
128. Celekli A, Birecikligil S S, Geyik F, et al. Prediction of removal efficiency of Lanaset Red G onwalnut husk using artificial neural network model[J]. Bioresour Technol,2012,103(1):64-70
129. Shankar T J, Bandyopadhyay S. Prediction of extrudate properties using artificial neural networks[J].Food Bioprod Process,2007,85(C1):29-33
130. Sahin A S, Kilic B, Kilic U. Optimization of heat pump using fuzzy logic and genetic algorithm[J].Heat Mass Transfer,2011,47(12):1553-1560
131. Chen S, Chang P, Cheng T C E, et al. A self-guided genetic algorithm for permutation flowshopscheduling problems[J]. Comput Oper Res,2012,39(7):1450-1457
132. Nazif H, Lee L S. Optimised crossover genetic algorithm for capacitated vehicle routing problem[J].Appl Math Model,2012,36(5):2110-2117
133.金虎.毕赤酵母高效发酵生产猪α干扰素过程的优化与代谢调控[D]:[博士学位论文].无锡:江南大学,2011
134.臧荣鑫,杨具田.生物化学实验教程[M].兰州:兰州大学出版社,2010.178-180.
135. Shi H D, Shimizu K. On-line metabolic pathway analysis based on metabolic signal flow diagram[J].Biotechnol Bioeng,1998,58(2-3):139-148
136.徐士良.计算方法[M].北京:人民邮电出版社,2009.123-141.
137. Lin K H, Iijima S, Shimizu K, et al. Control of gene expression from the SUC2promoter ofSaccharomyces cerevisiae with the aid of a glucose analyser[J]. Appl Microbiol Biotechnol,1989,32(3):313-316
138. Johnston W, Cord-Ruwisch R, Cooney M J. Industrial control of recombinant E. coli fed-batch culture:new perspectives on traditional controlled variables[J]. Bioprocess Biosyst Eng,2002,25(2):111-120
139. Nawagitgul P, Morozov I, Bolin S R, et al. Open reading frame2of porcine circovirus type2encodesa major capsid protein[J]. J Gen Virol,2000,81(9):2281-2287
140. Chung J D. Design of metabolic feed controllers: Application to high-density fermentations of Pichiapastoris[J]. Biotechnol Bioeng,2000,68(3):298-307
141. Cereghino J L, Cregg J M. Heterologous protein expression in the methylotrophic yeast Pichiapastoris[J]. Fems Microbiol Rev,2000,24(1):45-66
142. Celik E, Calik P, Oliver S G. Fed-batch methanol feeding strategy for recombinant protein productionby Pichia pastoris in the presence of co-substrate sorbitol[J]. Yeast,2009,26(9):473-484
143. Eggeling L, Sahm H. L-glutamate and L-lysine: traditional products with impetuous development[J].Appl Microbiol Biotechnol,1999,52:146-153
144. Liu S, Wang W. Biotin and glutamate fermentation[J]. China feed additive,2010,2:5-8
145. Kramer M A. Nonlinear principal component analysis using auto-associative neural networks[J].AIChE Journal,1991,37:233-243
146. Webb A R. An approach to nonlinear principal component analysis using radially symmetric kernelfunctions[J]. Statics Comput,1996,6:159-168
147. Cheong S. Support vector machines with binary tree architecture for multi-class classification[J].Neural Inform Process,2004,2(3):47-51
148.曹艳,丁健,段作营等.在线推定和控制葡萄糖浓度改善谷氨酸发酵性能[J].微生物学通报,2009,36(10):1619-1624
149. Burges C J C. A tutorial on Support Vector Machines for pattern recognition[J]. Data Min KnowlDiscov,1998,2(2):121-167
150. Eggeling L, Krumbach K, Sahm H. L-glutamate efflux with Corynebacterium glutamicum: Why ispenicillin treatment or tween addition doing the same?[J]. J Mol Microb Biotech,2001,3(1):67-68
151.曹艳.利用代谢酶学和模型技术改善谷氨酸发酵的稳定性和糖酸转化率[D]:[博士学位论文].无锡:江南大学,2013
152. Takac S, Calik G, Mavituna F, et al. Metabolic flux distribution for the optimized production ofL-glutamate[J]. Enzyme Microb Technol,1998,23(5):286-300
153. Chen N, Du J, Liu H, et al. Elementary mode analysis and metabolic flux analysis of L-glutamatebiosynthesis by Corynebacterium glutamicum[J]. Ann Microbiol,2009,59(2):317-322
2. Cereghino G P L, Cereghino J L, Ilgen C, et al. Production of recombinant proteins in fermenter culturesof the yeast Pichia pastoris[J]. Curr Opin Biotechnol,2002,13(4):329-332
3. Jin H, Liu G, Ye X, et al. Enhanced porcine interferon-alpha production by recombinant Pichia pastoriswith a combinational control strategy of low induction temperature and high dissolved oxygenconcentration[J]. Biochem Eng J,2010,52(1):91-98
4. Lee C Y, Lee S J, Jung K H, et al. High dissolved oxygen tension enhances heterologous proteinexpression by recombinant Pichia pastoris[J]. Process Biochem,2003,38(8):1147-1154
5.王霞,张世有.好氧发酵过程中影响溶解氧的因素及如何提高溶解氧的浓度[J].黑龙江医药,2005(4):276-277
6.王志仁.氨基酸发酵[J].发酵科技通讯,1981(2):3-14
7.胡学智.酶制剂工业概况及其应用进展[J].工业微生物,2003(4):32-41
8.王睿,刘桂超.论我国酶制剂工业的发展[J].畜牧与饲料科学,2011(1):68-69
9.崔进梅,宋磊,邓学箴等.基因工程药物的表达系统及发展状况[J].齐鲁药事,2005(2):104-105
10.蒋伯诚.基因重组药物[J].药学进展,1995(3):129-134
11. Xiao J, Shi Z P, Gao P, et al. On-line optimization of glutamate production based on balancedmetabolic control by RQ[J]. Bioprocess Biosyst Eng,2006,29(2):109-117
12. Zhang C Y, Shi Z P, Gao P, et al. On-line prediction of products concentrations in glutamatefermentation using metabolic network model and linear programming[J]. Biochem Eng J,2005,25(2):99-108
13. Lee C Y, Nakano A, Shiomi N, et al. Effects of substrate feed rates on heterologous protein expressionby Pichia pastoris in DO-stat fed-batch fermentation[J]. Enzyme Microb Technol,2003,33(4):358-365
14. Hu X, Chu J, Zhang Z, et al. Effects of different glycerol feeding strategies onS-adenosyl-L-methionine biosynthesis by P-GAP-driven Pichia pastoris overexpressing methionineadenosyltransferase[J]. J Biotechnol,2008,137(1):44-49
15. Jin H, Zheng Z, Gao M, et al. Effective induction of phytase in Pichia pastoris fed-batch culture usingan ANN pattern recognition model-based on-line adaptive control strategy[J]. Biochem Eng J,2007,37(1):26-33
16. Jia D, Liu L, Wang H, et al. Overproduction of a truncated poly (vinyl alcohol) dehydrogenase inrecombinant Pichia pastoris by low-temperature induction strategy and related mechanism analysis[J].Bioprocess Biosyst Eng,2013,36(8):1095-1103
17. Gao M, Dong S, Yu R, et al. Improvement of ATP regeneration efficiency and operation stability inporcine interferon-alpha production by Pichia pastoris under lower induction temperature[J]. Korean JChem Eng,2011,28(6):1412-1419
18. Wu D, Yu X W, Wang T C, et al. High yield rhizopus chinenisis prolipase production in Pichiapastoris: impact of methanol concentration[J]. Biotechnol Bioprocess Eng,2011,16(2):305-311
19. Minning S, Serrano A, Ferrer P, et al. Optimization of the high-level production of Rhizopus oryzaelipase in Pichia pastoris[J]. J Biotechnol,2001,86(1):59-70
20. Yamawaki S, Matsumoto T, Ohnishi Y, et al. Production of single-chain variable fragment antibody(scFv) in fed-batch and continuous culture of Pichia pastoris by two different methanol feeding methods[J].J Biosci Bioeng,2007,104(5):403-407
21. Charoenrat T, Ketudat-Cairns M, Stendahl-Andersen H, et al. Oxygen-limited fed-batch process: analternative control for Pichia pastoris recombinant protein processes[J]. Bioprocess Biosyst Eng,2005,27(6):399-406
22. Khatri N K, Hoffmann F. Oxygen-limited control of methanol uptake for improved production of asingle-chain antibody fragment with recombinant Pichia pastoris[J]. Appl Microbiol Biotechnol,2006,72(3):492-498
23. Woo S H, Park S H, Lim H K, et al. Extended operation of a pressurized75-L bioreactor for shLkn-1production by Pichia pastoris using dissolved oxygen profile control[J]. J Ind Microbiol Biotechnol,2005,32(10):474-480
24. Celik E, Calik P, Oliver S G. Metabolic flux analysis for recombinant protein production by Pichiapastoris using dual carbon sources: effects of methanol feeding rate[J]. Biotechnol Bioeng,2010,105(2):317-329
25. Gao M, Li Z, Yu R, et al. Methanol/sorbitol co-feeding induction enhanced porcine interferon-alphaproduction by P. pastoris associated with energy metabolism shift[J]. Bioprocess Biosyst Eng,2012,35(7):1125-1136
26. Jungo C, Marison I, von Stockar U. Mixed feeds of glycerol and methanol can improve theperformance of Pichia pastoris cultures: A quantitative study based on concentration gradients in transientcontinuous cultures[J]. J Biotechnol,2007,128(4):824-837
27. Wang Z, Wang Y, Zhang D, et al. Enhancement of cell viability and alkaline polygalacturonate lyaseproduction by sorbitol co-feeding with methanol in Pichia pastoris fermentation[J]. Bioresour Technol,2010,101(4):1318-1323
28. Arnau C, Ramon R, Ferrer P, et al. Sorbitol co-feeding an efficient strategy to reduce metabolic burdencaused by the overexpression of a Rhizopus oryzae lipase in Pichia pastoris[J]. J Biotechnol,2007,131(2):S76-S76
29. Yu R, Dong S, Zhu Y, et al. Effective and stable porcine interferon-alpha production by Pichia pastorisfed-batch cultivation with multi-variables clustering and analysis[J]. Bioprocess Biosyst Eng,2010,33(4):473-483
30.左莹,张萍,张惠.玉米浆在氨基酸发酵工业中的作用[J].中国酿造,2013(11):18-22
31.陈银芳. L-赖氨酸产生菌选育及其发酵条件的调控[D]:[硕士学位论文].江南大学,2009
32.袁丹丹. L-缬氨酸产生菌的选育及其发酵条件的调控[D]:[硕士学位论文].江南大学,2010
33.张佑红,王新彬,吴元欣. L-丝氨酸发酵生产菌发酵条件的优化[J].武汉工程大学学报,2007(4):11-14
34.张义萍. L-精氨酸产生菌的选育及其发酵条件优化[D]:[硕士学位论文].江南大学,2006
35.牛大鹏.诺西肽发酵过程建模与优化研究[D]:[博士学位论文].沈阳:东北大学,2010
36. Devlin J F. A simple and powerful method of parameter-estimation using simplex optimization[J].Ground Water,1994,32(2):323-327
37.徐士良.计算方法[M].北京:人民邮电出版社,2009.171-175.
38. Yao L, Sethares W A. Nonlinear parameter-estimation via the genetic algorithm[J]. IEEE Trans SignalProcess,1994,42(4):927-935
39. Dai W, Word D P, Hahn J. Modeling and dynamic optimization of fuel-grade ethanol fermentationusing fed-batch process[J]. Control Eng Practice,2014,22:231-241
40. Jang M F, Chou Y S. Modeling and optimization of bioethanol production via a simultaneoussaccharification and fermentation process using starch[J]. J Chem Technol Biotechnol,2013,88(6):1164-1174
41. Linville J L, Rodriguez M, Jr., Mielenz J R, et al. Kinetic modeling of batch fermentation for Populushydrolysate tolerant mutant and wild type strains of Clostridium thermocellum[J]. Bioresour Technol,2013,147:605-613
42. Guo W, Zhang Y, Lu J, et al. Optimization of fermentation medium for nisin production fromLactococcus lactis subsp lactis using response surface methodology (RSM) combined with artificial neuralnetwork-genetic algorithm (ANN-GA)[J]. Afr J Biotechnol,2010,9(38):6264-6272
43. Pal M P, Vaidya B K, Desai K M, et al. Media optimization for biosurfactant production byRhodococcus erythropolis MTCC2794: artificial intelligence versus a statistical approach[J]. J IndMicrobiol Biotechnol,2009,36(5):747-756
44. Singh V, Khan M, Khan S, et al. Optimization of actinomycin V production by Streptomycestriostinicus using artificial neural network and genetic algorithm[J]. Appl Microbiol Biotechnol,2009,82(2):379-385
45. Guo Y, Xu J, Zhang Y, et al. Medium optimization for ethanol production with Clostridiumautoethanogenum with carbon monoxide as sole carbon source[J]. Bioresour Technol,2010,101(22):8784-8789
46. Singh A, Majumder A, Goyal A. Artificial intelligence based optimization of exocellular glucansucraseproduction from Leuconostoc dextranicum NRRL B-1146[J]. Bioresour Technol,2008,99(17):8201-8206
47. Silva R G, Pinotti L M, Cruz A J G, et al. Artificial neural networks to infer biomass and productconcentration during the production of penicillin G acylase from Bacillus megaterium[J]. J Chem TechnolBiotechnol,2008,83(5):739-749
48. Singh A, Tatewar D, Shastri P N, et al. Application of ANN for prediction of cellulase and xylanaseproduction by Trichoderma reesei under SSF condition[J]. Indian J Chem Technol,2008,15(1):53-58
49. Hur W, Chung Y-K. An artificial neural network for biomass estimation from automatic pH controlsignal[J]. Biotechnol Bioprocess Eng,2006,11(4):351-356
50. Horiuchi J, Shimada T, Funahashi H, et al. Artificial neural network model with a culture database forprediction of acidification step in cheese production[J]. Journal of Food Engineering,2004,63(4):459-465
51. Kiran A U M, Jana A K. Control of continuous fed-batch fermentation process using neural networkbased model predictive controller[J]. Bioprocess Biosyst Eng,2009,32(6):801-808
52. Gadkar K, Mehra S, Gomes J. On-line adaptation of neural networks for bioprocess control[J]. ComputChem Eng,2005,29(5):1047-1057
53. Mészáros A, Andrá ik A, Mizsey P, et al. Computer control of pH and DO in a laboratory fermenterusing a neural network technique[J]. Bioprocess Biosyst Eng,2004,26(5):331-340
54. Nott P J K, Karim M N, Morris A J. Fault and contamination detection in a continuous bakers yeastfermentation[J]. Comput Chem Eng,1996,20: S611-S616
55. Duan S, Shi Z, Feng H, et al. An on-line adaptive control based on DO/pH measurements and ANNpattern recognition model for fed-batch cultivation[J]. Biochem Eng J,2006,30(1):88-96
56. Gao M, Zheng Z, Wu J, et al. Improvement of specific growth rate of Pichia pastoris for effectiveporcine interferon-alpha production with an on-line model-based glycerol feeding strategy[J]. ApplMicrobiol Biotechnol,2012,93(4):1437-1445
57. Shimizu H, Yasuoka H, Uchiyama K. On-Line fault diagnosis for optimal rice α-amylase productionprocess of a temperature-sensitive mutant of saccharomyces cerevisiae by an autoassociative neuralnetwork[J]. J Ferment Bioeng,1997,83(5):435-422
58. Huang J H, Shimizu H, Shioya S. Data preprocessing and output evaluation of an autoassociative neuralnetwork model for online fault detection in virginiamycin production[J]. J Biosci Bioeng,2002,94(1):70-77
59. Bai S, McLean D D, Thibault J. Autoassociative neural networks for robust dynamic datareconciliation[J]. AIChE Journal,2007,53(2):438-448
60.董传亮,潘丰,史仲平.基于自我联想神经网络的谷氨酸发酵在线故障诊断[J].中国酿造,2009(2):96-100
61. Liu G, Zhou D, Xu H, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert SystAppl,2010,37(4):2708-2713
62.陈进东.基于在线支持向量回归的建模与预测控制研究[D]:[博士学位论文].无锡:江南大学,2013
63.王鲜芳.生化过程动态建模及优化控制研究[D]:[博士学位论文].无锡:江南大学,2009
64. Horiuchi J, Kishimoto M. Fuzzy-aided estimation of biological parameters based on materialbalances[J]. J Ferment Bioeng,1998,86(1):111-117
65. Kasperski A, Miskiewicz T. An adaptive fuzzy logic controller using the respiratory quotient as anindicator of overdosage in the baker's yeast process[J]. Biotechnol Lett,2002,24(1):17-21
66. Kishimoto M, Kitta Y, Takeuchi S, et al. Computer control of glutamic-acid production based on fuzzyclusterization of culture phases[J]. J Ferment Bioeng,1991,72(2):110-114
67. Park Y S, Shi Z P, Shiba S, et al. Application of fuzzy-reasoning to control of glucose and ethanolconcentrations in bakers-yeast culture[J]. Appl Microbiol Biotechnol,1993,38(5):649-655
68.史仲平,潘丰.发酵过程解析、控制与检测技术[M].北京:化学工业出版社,2010.7-8.
69. Kleman G L, Chalmers J J, Luli G W, et al. A Predictive and Feedback-control Algorithm Maintains aConstant Glucose-concentration in Fed-batch Fermentations[J]. Appl Environ Microbiol,1991,57(4):910-917
70. Jones K, Williams D, Goodier A. Auto-tuning PID control of dissolved oxygen in a Saccharomycescerevisiae fermentation[J]. Measurement Control,1996,29(9):266-269
71. Jones K O, Williams D, Montgomery P A. On-line application of an auto-tuning PID controller fordissolved oxygen concentration in a fermentation process[J]. Trans Inst Measure Control,1997,19(5):253-262
72. Markx G H, Kell D B. The use of dielectric permittivity for the control of the biomass level duringbiotransformations of toxic substrates in continuous-culture[J]. Biotechnol Progr,1995,11(1):64-70
73. Zhang W H, Smith L A, Plantz B A, et al. Design of methanol feed control in Pichia pastorisfermentations based upon a growth model[J]. Biotechnol Progr,2002,18(6):1392-1399
74. Lee S Y. High cell-density culture of Escherichia coli[J]. Trends Biotech,1996,14(3):98-105
75. Van Duuren J, Wijte D, Karge B, et al. pH-stat fed-batch process to enhance the production of cis,cis-muconate from benzoate by Pseudomonas putida KT2440-JD1[J]. Biotechnol Progr,2012,28(1):85-92
76. Yeh K, Chen C, Chang J. pH-stat photoheterotrophic cultivation of indigenous Chlorella vulgarisESP-31for biomass and lipid production using acetic acid as the carbon source[J]. Biochem Eng J,2012,64:1-7
77. Honda H, Kobayashi T. Fuzzy control of bioprocess in Japan[J]. Biotechnol Ann Rev,2000,5:1-23
78. Honda H, Kobayashi T. Industrial application of fuzzy control in bioprocesses[J]. Adv Biochem EngBiotechnol,2004,87:151-171
79. Oishi K, Tominaga M, Kawato A, et al. Application of fuzzy control-theory to the sake brewingprocess[J]. J Ferment Bioeng,1991,72(2):115-121
80. Alfafara C G, Miura K, Shimizu H, et al. Fuzzy control of ethanol concentration and its application tomaximum glutathione production in yeast fed-batch culture[J]. Biotechnol Bioeng,1993,41(4):493-501
81. Peng Y, Ma Y, Wang S, et al. Fuzzy control of nitrogen removal in predenitrification process usingORP[J]. Water Sci Technol,2005,52(12):161-169
82. Ahioglu S, Altinten A, Ertunc S, et al. Fuzzy control with genetic algorithm in a batch bioreactor[J].Appl Biochem Biotech,2013,171(8):2201-2219
83. Meyer U, Popel H J. Fuzzy-control for improved nitrogen removal and energy saving in WWT-plantswith pre-denitrification[J]. Water Sci Technol,2003,47(11):69-76
84. Lenas P, Kitade T, Watanabe H, et al. Adaptive fuzzy control of nutrients concentration in fed-batchculture of mammalian cells[J]. Cytotechnology,1997,25(1-3):9-15
85. Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosispart I: quantitative model-based methods[J]. Comput Chem Eng,2003,27(3):293-311
86. Dondo R. Measurement processing for state estimation and fault identification in batch fermentations[J].Braz J Chem Eng,2004,21(3):367-392
87. Riverol C, Pilipovik M V. Control and fault diagnosis in bottom fermentation systems using parityspace approach[J]. Biotechnol Progr,2002,18(3):666-667
88. Venkatasubramanian V, Rengaswamy R, Kavuri S N, et al. A review of process fault detection anddiagnosis part III: process history based methods[J]. Comput Chem Eng,2003,27(3):327-346
89. Ku W F, Storer R H, Georgakis C. Disturbance detection and isolation by dynamic principal componentanalysis[J]. Chemometr Intell Lab Syst,1995,30(1):179-196
90. Lee J M, Yoo C, Lee I B. Fault detection of batch processes using multiway kernel principal componentanalysis[J]. Comput Chem Eng,2004,28(9):1837-1847
91. He N, Wang S Q, Xie L. An improved adaptive multi-way principal component analysis for monitoringstreptomycin fermentation process[J]. Chin J Chem Eng,2004,12(1):96-101
92. Agatonovic-Kustrin S, Beresford R. Basic concepts of artificial neural network (ANN) modeling and itsapplication in pharmaceutical research[J]. J Pharm Biomed Anal,2000,22(5):717-727
93. Neath M J, Swain A K, Madawala U K, et al. An optimal PID controller for a bidirectional Inductivepower transfer system using multiobjective genetic algorithm[J]. IEEE Trans Power Elect,2014,29(3):1523-1531
94. Daliri M R. A hybrid automatic system for the diagnosis of lung cancer based on genetic algorithmandfuzzy extreme learning machines[J]. J Med Syst,2012,36(2):1001-1005
95. Mathew B S, Isaac K P. Optimisation of maintenance strategy for rural road network using geneticalgorithm[J]. Int J Pavement Eng,2014,15(4):352-360
96. Acosta-Gonzalez E, Fernandez-Rodriguez F. Forecasting financial failure of firms via geneticalgorithms[J]. Comput Econ,2014,43(2):133-157
97. Jena H M, Roy G K, Mahapatra S S. Determination of optimum gas holdup conditions in a three-phasefluidized bed by genetic algorithm[J]. Comput Chem Eng,2010,34(4):476-484
98. Rao C S, Sathish T, Mahalaxmi M, et al. Modelling and optimization of fermentation factors forenhancement of alkaline protease production by isolated Bacillus circulans using feed-forward neuralnetwork and genetic algorithm[J]. J Appl Microbiol,2008,104(3):889-898
99. Beloufa F, Chikh M A. Design of fuzzy classifier for diabetes disease using Modified Artificial BeeColony algorithm[J]. Comput Method Progr Biomed,2013,112(1):92-103
100. Li Y, Tong S, Li T, et al. Adaptive fuzzy control of uncertain stochastic nonlinear systems withunknown dead zone using small-gain approach[J]. Fuzzy Set Syst,2014,235:1-24
101. Hu P, Cao G, Zhu X, et al. Coolant circuit modeling and temperature fuzzy control of proton exchangemembrane fuel cells[J]. Int J Hydrogen Energy,2010,35(17):9110-9123
102. Beccari M, Majone M. Fuzzy control of disturbances in a wastewater treatment process-Commentreply[J]. Water Res,1997,31(12):3168-3168
103. Almeida G, Vieira J, Marques A S, et al. Estimating the potential water reuse based on fuzzyreasoning[J]. J Environ Manage,2013,128:883-892
104. Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Process Lett,1999,9(3):293-300
105. Lin C F, Wang S D. Fuzzy support vector machines[J]. IEEE Trans Neural networks,2002,13(2):464-471
106. Mangasaian O L, Musicant D R. Lagrangian support vector machines[J]. J Mach Learn Res,2001,1(3):161-177
107. Zhang L, Zhou W D, Jiao L C. Wavelet support vector machine[J]. IEEE Trans Syst Man Cybern B,2004,34(1):34-39
108. Tong S, Koller D. Support vector machine active learning with applications to text classification[J]. JMach Learn Res,2002,2(1):45-66
109. Kim K I, Jung K, Kim J H. Texture-based approach for text detection in images using support vectormachines and continuously adaptive mean shift algorithm[J]. IEEE Trans Patt Anal Mach Int,2003,25(12):1631-1639
110. Zhang W, Yoshida T, Tang X. Text classification based on multi-word with support vector machine[J].Knowl-B Syst,2008,21(8):879-886
111. Meshgini S, Aghagolzadeh A, Seyedarabi H. Face recognition using Gabor-based direct lineardiscriminant analysis and support vector machine[J]. Comput Elect Eng,2013,39(3):727-745
112. Li Y M, Gong S G, Sherrah J, et al. Support vector machine based multi-view face detection andrecognition[J]. Image Vision Comput,2004,22(5):413-427
113. Kumar H, Kumar T A R, Amarnath M, et al. Fault diagnosis of antifriction bearings through soundsignals using support vector machine[J]. J Vibroeng,2012,14(4):1601-1606
114. Maglogiannis I, Loukis E, Zafiropoulos E, et al. Support vectors machine-based identification of heartvalve diseases using heart sounds[J]. Comput Method Progr Biomed,2009,95(1):47-61
115. Zhang K, Lu W, Marziliano P. Automatic knee cartilage segmentation from multi-contrast MR imagesusing support vector machine classification with spatial dependencies[J]. Magn Reson Imaging,2013,31(10):1731-1743
116. Song Q, Hu W J, Xie W F. Robust support vector machine with bullet hole image classification[J].IEEE Trans Syst Man Cybern C,2002,32(4):440-448
117. Tay F E H, Cao L J. Application of support vector machines in financial time series forecasting[J].Omega-Int J Manage SCI,2001,29(4):309-317
118. Kim K J. Financial time series forecasting using support vector machines[J]. Neurocomputing,2003,55(1-2):307-319
119. Al-Dhaifllah M, Westwick D T. Identification of auto-regressive exogenous hammerstein modelsbased on support vector machine regression[J]. IEEE Trans Control Syst Technol,2013,21(6):2083-2090
120. An S, Liu W, Venkatesh S. Fast cross-validation algorithms for least squares support vector machineand kernel ridge regression[J]. Pattern Recogn,2007,40(8):2154-2162
121. Hua Z, Wang Y, Xu X, et al. Predicting corporate financial distress based on integration of supportvector machine and logistic regression[J]. Expert Syst Appl,2007,33(2):434-440
122. Jordan L T, Derbyshire J B. Antiviral activity of interferon against transmissible gastroenteritis virusin cell culture and ligated intestinal segments in neonatal pigs[J]. Vet Microbiol,1994,38(3):263-276
123. Chinsangaram J, Koster M, Grubman M J. Inhibition of L-deleted foot-and-mouth disease virusreplication by alpha/beta interferon involves double-stranded RNA-dependent protein kinase[J]. J Virol,2001,75(12):5498-5503
124. Cao R B, Xu X Q, Zhou B, et al. Gene modification and high prokaryotic expression of porcineinterferon alpha-1[J]. Chin J Biotechnol,2004,20(2):291-294
125. Lefevre F, La Bonnardiere C. Molecular cloning and sequencing of a gene encoding biologicallyactive porcine alpha-interferon[J]. J Interferon Res,1986,6(4):349-360
126. Atici U. Prediction of the strength of mineral admixture concrete using multivariable regressionanalysis and an artificial neural network[J]. Expert Syst Appl,2011,38(8):9609-9618
127. Chelgani S C, Hower J C, Jorjani E, et al. Prediction of coal grindability based on petrography,proximate and ultimate analysis using multiple regression and artificial neural network models[J]. FuelProcess Technol,2008,89(1):13-20
128. Celekli A, Birecikligil S S, Geyik F, et al. Prediction of removal efficiency of Lanaset Red G onwalnut husk using artificial neural network model[J]. Bioresour Technol,2012,103(1):64-70
129. Shankar T J, Bandyopadhyay S. Prediction of extrudate properties using artificial neural networks[J].Food Bioprod Process,2007,85(C1):29-33
130. Sahin A S, Kilic B, Kilic U. Optimization of heat pump using fuzzy logic and genetic algorithm[J].Heat Mass Transfer,2011,47(12):1553-1560
131. Chen S, Chang P, Cheng T C E, et al. A self-guided genetic algorithm for permutation flowshopscheduling problems[J]. Comput Oper Res,2012,39(7):1450-1457
132. Nazif H, Lee L S. Optimised crossover genetic algorithm for capacitated vehicle routing problem[J].Appl Math Model,2012,36(5):2110-2117
133.金虎.毕赤酵母高效发酵生产猪α干扰素过程的优化与代谢调控[D]:[博士学位论文].无锡:江南大学,2011
134.臧荣鑫,杨具田.生物化学实验教程[M].兰州:兰州大学出版社,2010.178-180.
135. Shi H D, Shimizu K. On-line metabolic pathway analysis based on metabolic signal flow diagram[J].Biotechnol Bioeng,1998,58(2-3):139-148
136.徐士良.计算方法[M].北京:人民邮电出版社,2009.123-141.
137. Lin K H, Iijima S, Shimizu K, et al. Control of gene expression from the SUC2promoter ofSaccharomyces cerevisiae with the aid of a glucose analyser[J]. Appl Microbiol Biotechnol,1989,32(3):313-316
138. Johnston W, Cord-Ruwisch R, Cooney M J. Industrial control of recombinant E. coli fed-batch culture:new perspectives on traditional controlled variables[J]. Bioprocess Biosyst Eng,2002,25(2):111-120
139. Nawagitgul P, Morozov I, Bolin S R, et al. Open reading frame2of porcine circovirus type2encodesa major capsid protein[J]. J Gen Virol,2000,81(9):2281-2287
140. Chung J D. Design of metabolic feed controllers: Application to high-density fermentations of Pichiapastoris[J]. Biotechnol Bioeng,2000,68(3):298-307
141. Cereghino J L, Cregg J M. Heterologous protein expression in the methylotrophic yeast Pichiapastoris[J]. Fems Microbiol Rev,2000,24(1):45-66
142. Celik E, Calik P, Oliver S G. Fed-batch methanol feeding strategy for recombinant protein productionby Pichia pastoris in the presence of co-substrate sorbitol[J]. Yeast,2009,26(9):473-484
143. Eggeling L, Sahm H. L-glutamate and L-lysine: traditional products with impetuous development[J].Appl Microbiol Biotechnol,1999,52:146-153
144. Liu S, Wang W. Biotin and glutamate fermentation[J]. China feed additive,2010,2:5-8
145. Kramer M A. Nonlinear principal component analysis using auto-associative neural networks[J].AIChE Journal,1991,37:233-243
146. Webb A R. An approach to nonlinear principal component analysis using radially symmetric kernelfunctions[J]. Statics Comput,1996,6:159-168
147. Cheong S. Support vector machines with binary tree architecture for multi-class classification[J].Neural Inform Process,2004,2(3):47-51
148.曹艳,丁健,段作营等.在线推定和控制葡萄糖浓度改善谷氨酸发酵性能[J].微生物学通报,2009,36(10):1619-1624
149. Burges C J C. A tutorial on Support Vector Machines for pattern recognition[J]. Data Min KnowlDiscov,1998,2(2):121-167
150. Eggeling L, Krumbach K, Sahm H. L-glutamate efflux with Corynebacterium glutamicum: Why ispenicillin treatment or tween addition doing the same?[J]. J Mol Microb Biotech,2001,3(1):67-68
151.曹艳.利用代谢酶学和模型技术改善谷氨酸发酵的稳定性和糖酸转化率[D]:[博士学位论文].无锡:江南大学,2013
152. Takac S, Calik G, Mavituna F, et al. Metabolic flux distribution for the optimized production ofL-glutamate[J]. Enzyme Microb Technol,1998,23(5):286-300
153. Chen N, Du J, Liu H, et al. Elementary mode analysis and metabolic flux analysis of L-glutamatebiosynthesis by Corynebacterium glutamicum[J]. Ann Microbiol,2009,59(2):317-322