人工神经网络在发酵工业中的应用

人工神经网络技术具有很强的非线性映射能力,用于系统的非线性建模,具有无可比拟的优势,广泛应用于发酵过程中培养基的优化和系统建模与控制方面,本主要介绍了人工神经网络的基本原理与使用方法,以及BP神经网络在非线性函数逼近的优点,详细介绍了其在发酵培养基优化,连续搅拌反应器神经网络估计,分批发酵及补料分批发酵过程建模与控制优化中的应用实例。     

Application of neural networks for controlling and predicting quality parameters in beer fermentation

The biochemical pathways involved in the production of ethyl caproate, a secondary product of the beer fermentation process, are not well established. Hence, there are no phenomenological models available to control and predict the production of this particular compound as with other related products. In this work, neural networks have been used to fit experimental results with constant and variable pH, giving a good fit of laboratory and industrial scale data. The results at constant pH were also used to predict results at variable pH. Finally, the application of neural networks obtained from laboratory experiments gave excellent predictions of results in industrial breweries and so could be used in the control of industrial operations. The input pattern to the neural network included the accumulated fermentation time, cell dry weight, consumption of sugars and aminoacids and, in some cases, the pH. The output from the neural network was an estimation of quantity of the ethyl caproate ester.     

Retrospective optimization of time-dependent fermentation control strategies using time-independent historical data

We have previously shown the usefulness of historical data for fermentation process optimization. The methodology developed includes identification of important process inputs, training of an artificial neural network (ANN) process model, and ultimately use of the ANN model with a genetic algorithm to find the optimal values of each critical process input. However, this approach ignores the time-dependent nature of the system, and therefore, does not fully utilize the available information within a database. In this work, we propose a method for incorporating time-dependent optimization into our previously developed three-step optimization routine. This is achieved by an additional step that uses a fermentation model (consisting of coupled ordinary differential equations (ODE)) to interpret important time-course features of the collected data through adjustments in model parameters. Important process variables not explicitly included in the model were then identified for each model parameter using automatic relevance determination (ARD) with Gaussian process (GP) models. The developed GP models were then combined with the fermentation model to form a hybrid neural network model that predicted the time-course activity of the cell and protein concentrations of novel fermentation conditions. A hybrid-genetic algorithm was then used in conjunction with the hybrid model to suggest optimal time-dependent control strategies. The presented method was implemented upon an E. coli fermentation database generated in our laboratory. Optimization of two different criteria (final protein yield and a simplified economic criteria) was attempted. While the overall protein yield was not increased using this methodology, we were successful in increasing a simplified economic criterion by 15% compared to what had been previously observed. These process conditions included using 35% less arabinose (the inducer) and 33% less typtone in the media and reducing the time required to reach the maximum protein concentration by 10% while producing approximately the same level of protein as the previous optimum.     

谷氨酸发酵过程的神经网络模拟预测模型

人工神经网络是八十年代迅速兴起的一门非线性科学．它力图模拟人脑的一些基本特性。如自组织性、自适应性和容错性能等,已在模式识别、数据处理和自动化控制等方面得到了初步应用,取得了很好的效果〔1〕。 本文根据上海某味精厂某发酵罐的一批批报数据,利用人工神经网络的一典型模型－“反向传播”模型,初步尝试了神经网络模拟预测方法的效果,有关这方面的研究工作尚未见报道．     

Backpropagation neural network predictive control and control scheme comparison of 2,3-butanediol fermentation by Klebsiella oxytoca

A backpropagation neural network (BPN) was applied for the control study of 2,3-butanediol fermentation (2,3-BDL) carried by Klebsiella oxytoca. The measurements of cell mass and glucose were not included in the network models, instead, only the on-line measured product concentrations from the MIMS (membrane introduction mass spectrometer) were involved. Oxygen composition was chosen to be the control variable for this fermentation system for the formation of 2,3-BDL is regulated by oxygen. Oxygen composition was directly correlated to the measured product concentrations. A two-dimensional (number of input nodes by number of data sets) moving window to supply data for on-line, dynamic learning of this fermentation system was applied. The input nodes of the networks were also properly selected. Two neural network control schemes for this 2,3-BDL fermentation were discussed and compared in this work. Fermentations often exist time delay due to the measurement and their slow reaction nature. Hence, the order of time delay for the network controller was also investigated.     

Probabilistic neural networks using Bayesian decision strategies and a modified Gompertz model for growth phase classification in the batch culture of Bacillus subtilis

Probabilistic neural networks (PNNs) were used in conjunction with the Gompertz model for bacterial growth to classify the lag, logarithmic, and stationary phases in a batch process. Using the fermentation time and the optical density of diluted cell suspensions, sampled from a culture of Bacillus subtilis, PNNs enabled a reliable determination of the growth phases. Based on a Bayesian decision strategy, the Gompertz based PNN used newly proposed definition of the lag and logarithmic phases to estimate the latent, logarithmic and stationary phases. This network topology has the potential for use with on-line turbidimeter for the automation and control of cultivation processes.     

基于自联想神经网络的谷氨酸发酵故障诊断

研究了用自联想神经网络对谷氨酸发酵进行故障诊断。自联想神经网络采用一种带有瓶颈层的特殊结构,且具有单位总增益。在经过大量样本的训练之后,各变量之间能够建立起内在联系。输入信息通过瓶颈层前的压缩及瓶颈层后的解压缩过程,信息中的精华将被提取。应用自联想神经网络对发酵过程变量进行预处理,可以准确及时的进行谷氨酸发酵故障诊断。     

Neural network predictive control by MIMS monitored 2,3-butanediol fermentation by Klebsiella oxytoca

With the aid of a membrane introduction mass spectrometer (MIMS), the major product 2,3-butanediol (2,3-BDL) as well as the other metabolites from the fermentation carried by Klebsiella oxytoca can be measured on-line simultaneously. A backpropagation neural network (BPN) being recognized with superior mapping ability was applied to this control study. This neural network adaptive control differs from those conventional controls for fermentation systems in which the measurements of cell mass and glucose are not included in the network model. It is only the measured product concentrations from the MIMS that are involved. Oxygen composition was chosen to be the control variable for this fermentation system. Oxygen composition was directly correlated to the measured product concentrations in the controller model. A two-dimensional (number of input nodes by number of data sets) moving window for on-line, dynamic learning of this fermentation system was applied. The input nodes of the network were also properly selected. Number of the training data sets for obtaining better control results was also determined empirically. Two control structures for this 2,3-BDL fermentation are discussed and compared in this work. The effect from adding time delay element to the network controller was also investigated.     

A robust soft sensor based on artificial neural network for monitoring microbial lipid fermentation processes using Yarrowia lipolytica

Microbial oils produced by Yarrowia lipolytica offer an environmentally friendly and sustainable alternative to petroleum as well as traditional lipids from animals and plants. The accurate measurement of fermentation parameters, including the substrate concentration, dry cell weight, and lipid accumulation, is the foundation of process control, which is indispensable for industrial lipid production. However, it remains a great challenge to measure the complex parameters online during the lipid fermentation process, which is nonlinear, multivariate, and characterized by strong coupling. As a type of AI technology, the artificial neural network model is a powerful tool for handling extremely complex problems, and it can be employed to develop a soft sensor to monitor the microbial lipid fermentation process of Y. lipolytica. In this study, we first analyzed and emphasized the volume of sodium hydroxide and dissolved oxygen concentration as central parameters of the fermentation process. Then, a soft sensor based on a four-input artificial neural network model was developed, in which the input variables were fermentation time, dissolved oxygen concentration, initial glucose concentration, and additional volume of sodium hydroxide. This provides the possibility of online monitoring of dry cell weight, glucose concentration, and lipid production with high accuracy, which can be extended to similar fermentation processes characterized by the addition of bases or acids, as well as changes of the dissolved oxygen concentration.     

Data and knowledge based experimental design for fermentation process optimization

A novel method for the sequential experimental design in order to optimize fed-batch fermentations was applied to a hyaluronidase fermentation by Streptococcus agalactiae. A Λ-optimal design was introduced to minimize the model parameter estimation error and to maximize the performance of the fermentation process. The method employs hybrid models that contain mechanistic, fuzzy and neural network components.     

重组巴氏毕赤酵母高密度发酵表达rHSA

对基因工程菌Pichiapastoris的摇瓶发酵条件进行了试验 ,并根据摇瓶发酵的优化结果进行了补料分批高密度发酵。在摇瓶发酵时 ,甲醇诱导基因工程菌P .pastoris表达重组人血清白蛋白的发酵周期为 96h ;甲醇的最佳诱导浓度为 1 0g L ;发酵pH范围为 5 72～ 6 5 9;在摇瓶培养时 ,随着接种量的增加 ,虽然目的蛋白表达量缓慢增加 ,但单位细胞光密度的蛋白产率却明显下降 ,符合y =1 2 941x- 0 50 59方程 (线性相关系数r=0 9789) ,其限制性因子很可能为溶氧。在分批发酵 ,接种量为 1 0 %且种子细胞光密度 (OD60 0 )为 2 0左右时 ,细胞生长的延迟期为 2 1 1h左右 ,细胞生长光密度与培养时间的关系模型为 :y =0 7841e0 .2 3 19t(线性相关系数r=0 .993 6 ) ;在补料发酵时细胞干重浓度可达到 1 1 5g L— 1 6 0g L ,在 1 2 0h重组人血清白蛋白表达量最大达到 3 6g L。     

Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation

In our previous work, partial least squares (PLSs) were employed to develop the near infrared spectroscopy (NIRs) models for at-line (fast off-line) monitoring key parameters of Lactococcus lactis subsp. fermentation. In this study, radial basis function neural network (RBFNN) as a non-linear modeling method was investigated to develop NIRs models instead of PLS. A method named moving window radial basis function neural network (MWRBFNN) was applied to select the characteristic wavelength variables by using the degree approximation (Da) as criterion. Next, the RBFNN models with selected wavelength variables were optimized by selecting a suitable constant spread. Finally, the effective spectra pretreatment methods were selected by comparing the robustness of the optimum RBFNN models developed with pretreated spectra. The results demonstrated that the robustness of the optimal RBFNN models were better than the PLS models for at-line monitoring of glucose and pH of L. lactis subsp. fermentation.     

毕赤酵母高密度发酵工艺的研究

高密度发酵是毕赤酵母提高蛋白表达量的一种重要策略,发酵工艺是高密度发酵的一个重要因素。采用下列措施均可以有效地提高表达水平：调节基础培养基,采用变pH和变温发酵,提高DO,选择最适的诱导前菌体密度和比生长速率并降低甘油初始浓度和采用分段式指数流加进行调控。选择合适的甲醇补料策略：甲醇限制补料（MLFB）、氧气限制补料（OLFB）、甲醇不限制补料（MNLFB）和温度限制补料（TLFB）。采用两种方式调控补料：诱导阶段菌体生长时,甲醇比消耗速率(qMeOH)为0.02-0.03gg-1h-1,而菌体不生长时,qMeOH采用较高值。     

L-缬氨酸发酵培养基的神经网络建模与遗传算法优化

运用神经网络对L-缬氨酸发酵培养基组成进行建模,在神经网络模型的基础上采用遗传算法对培养基组成进行优化,得到最佳发酵培养基组成.结果表明,运用神经网络并结合遗传算法是一种行之有效的优化方法.按最佳发酵培养基组成进行发酵实验64h,可在发酵液中积累L-缬氨酸28.5g/L.     

Neural network modeling in optimisation of continuous fermentation processes

The capability of self-recurrent neural networks in dynamic modeling of continuous fermentation is investigated in this simulation study. In the past, feedforward neural networks have been successfully used as one-step-ahead predictors. However, in steady-state optimisation of continuous fermentations the neural network model has to be iterated to predict many time steps ahead into the future in order to get steady-state values of the variables involved in objective cost function, and this iteration may result in increasing errors. Therefore, as an alternative to classical feedforward neural network trained by using backpropagation method, self-recurrent multilayer neural net trained by backpropagation through time method was chosen in order to improve accuracy of long-term predictions. Prediction capabilities of the resulting neural network model is tested by implementing this into the Integrated System Optimisation and Parameter Estimation (ISOPE) optimisation algorithm. Maximisation of cellular productivity of the baker's yeast continuous fermentation was used as the goal of the proposed optimising control problem. The training and prediction results of proposed neural network and performances of resulting optimisation structure are demonstrated.     

Control of continuous fed-batch fermentation process using neural network based model predictive controller

Cell growth and metabolite production greatly depend on the feeding of the nutrients in fed-batch fermentations. A strategy for controlling the glucose feed rate in fed-batch baker’s yeast fermentation and a novel controller was studied. The difference between the specific carbon dioxide evolution rate and oxygen uptake rate (Q _c − Q _o) was used as controller variable. The controller evaluated was neural network based model predictive controller and optimizer. The performance of the controller was evaluated by the set point tracking. Results showed good performance of the controller.     

Modelling and optimization of fermentation factors for enhancement of alkaline protease production by isolated Bacillus circulans using feed-forward neural network and genetic algorithm

Aim: Modelling and optimization of fermentation factors and evaluation for enhanced alkaline protease production by Bacillus circulans. Methods and Results: A hybrid system of feed‐forward neural network (FFNN) and genetic algorithm (GA) was used to optimize the fermentation conditions to enhance the alkaline protease production by B. circulans. Different microbial metabolism regulating fermentation factors (incubation temperature, medium pH, inoculum level, medium volume, carbon and nitrogen sources) were used to construct a ‘6‐13‐1’ topology of the FFNN for identifying the nonlinear relationship between fermentation factors and enzyme yield. FFNN predicted values were further optimized for alkaline protease production using GA. The overall mean absolute predictive error and the mean square errors were observed to be 0·0048, 27·9, 0·001128 and 22·45 U ml^?1 for training and testing, respectively. The goodness of the neural network prediction (coefficient of R²) was found to be 0·9993. Conclusions: Four different optimum fermentation conditions revealed maximum enzyme production out of 500 simulated data. Concentration‐dependent carbon and nitrogen sources, showed major impact on bacterial metabolism mediated alkaline protease production. Improved enzyme yield could be achieved by this microbial strain in wide nutrient concentration range and each selected factor concentration depends on rest of the factors concentration. The usage of FFNN–GA hybrid methodology has resulted in a significant improvement (>2·5‐fold) in the alkaline protease yield. Significance and Impact of the Study: The present study helps to optimize enzyme production and its regulation pattern by combinatorial influence of different fermentation factors. Further, the information obtained in this study signifies its importance during scale‐up studies.     

基因工程菌高密度发酵工艺研究进展

阐述了基因工程菌高密度发酵工艺的几个主要影响因素,包括重组菌构建、培养条件、生长抑制因子以及它们的控制技术。通过高密度发酵可以提高细胞生长密度、目的蛋白的表达含量。在高密度发酵过程中,会产生一些有害抑制代谢副产物,但通过分批补料可以降低影响。     

Using highly efficient nonlinear experimental design methods for optimization of Lactococcus lactis fermentation in chemically defined media

Optimization of fermentation media and processes is a difficult task due to the potential for high dimensionality and nonlinearity. Here we develop and evaluate variations on two novel and highly efficient methods for experimental fermentation optimization. The first approach is based on using a truncated genetic algorithm with a developing neural network model to choose the best experiments to run. The second approach uses information theory, along with Bayesian regularized neural network models, for experiment selection. To evaluate these methods experimentally, we used them to develop a new chemically defined medium for Lactococcus lactis IL1403, along with an optimal temperature and initial pH, to achieve maximum cell growth. The media consisted of 19 defined components or groups of components. The optimization results show that the maximum cell growth from the optimal process of each novel method is generally comparable to or higher than that achieved using a traditional statistical experimental design method, but these optima are reached in about half of the experiments (73–94 vs. 161, depending on the variants of methods). The optimal chemically defined media developed in this work are rich media that can support high cell density growth 3.5–4 times higher than the best reported synthetic medium and 72% higher than a commonly used complex medium (M17) at optimization scale. The best chemically defined medium found using the method was evaluated and compared with other defined or complex media at flask‐ and fermentor‐scales. © 2009 American Institute of Chemical Engineers Biotechnol. Prog., 2009