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.     

A neural network study on the dynamic identification of a fermentation system

The objective of this paper is to propose neural networks for the study of dynamic identification and prediction of a fermentation system which produces mainly 2,3-butanediol (2,3-BDL). The metabolic products of the fermentation, acetic acid, acetoin, ethanol, and 2,3-BDL were measured on-line via a mass spectrometer modified by the insertion of a dimethylvinylsilicone membrane probe. The measured data at different sampling times were included as the input and output nodes, at different learning batches, of the network. A fermentation system is usually nonlinear and dynamic in nature. Measured fermentation data obtained from the complex metabolic pathways are often difficult to be entirely included in a static process model, therefore, a dynamic model was suggested instead. In this work, neural networks were provided by a dynamic learning and prediction process that moved along the time sequence batchwise. In other words, a scheme of two-dimensional moving window (number of input nodes by the number of training data) was proposed for reading in new data while forgetting part of the old data. Proper size of the network including proper number of input/output nodes were determined by trained with the real-time fermentation data. Different number of hidden nodes under the consideration of both learning performance and computation efficiency were tested. The data size for each learning batch was determined. The performance of the learning factors such as the learning coefficient η and the momentum term coefficient α were also discussed. The effect of different dynamic learning intervals, with different starting points and the same ending point, both on the learning and prediction performance were studied. On the other hand, the effect of different dynamic learning intervals, with the same starting point and different ending points, was also investigated. The size of data sampling interval was also discussed. The performance from four different types of transfer functions, x/(1+|x|), sgn(x)·x ²/(1+x ²), 2/(1+e ^{? x} )?1, and 1/(1+e ^{? x} ) was compared. A scaling factor b was added to the transfer function and the effect of this factor on the learning was also evaluated. The prediction results from the time-delayed neural networks were also studied.     

Experimental studies of network parameters and operational variables on recurrent backpropagation neural network adaptive control of penicillin acylase fermentation by Arthrobacter viscosus

This work is to investigate the on-line control of the fermentation by Arthrobacter viscosus. This species of bacteria can secrete penicillin acylase which is a key enzyme in pharmaceutical industry. The growth of more cells during the fermentation will obtain more enzyme. Both the enzyme activity and the cell growth are rather sensitive to the change of pH. Once the pH during a fermentation is not properly controlled, the decay of cells' activity will irreversibly occur. Two peristaltic pumps for supplying acidic and basic solutions, respectively, were connected for the regulation of pH. With superior ability in identification and prediction of dynamic time series, recurrent backpropagation network (RBPN), instead of conventional controllers, was used as the adaptive controller model for the fermentation with dynamic characteristics. Based on a 1-3-1 BPN, a corresponding 4-4-1 RBPN was determined. The deviation of the pH measured at current time from the set point of 7.0, denoted as ( pH(t), was chosen as the input node of the network controller. The output node of this network controller was the predicted flow rate of the peristaltic pump for next control time interval. Such a model was operated by two phases. During the first phase, the network was set as the process model and trained by a fixed set of on-line acquired data. During the second phase, the network was stopped learning and switched to become a predictor, the predicted control action was hence obtained. The optimum sampling time was determined experimentally. To enhance the effective computation of this network, the number of training data was limited. A moving-window type of supplying training data to the network was applied for the on-line learning. The window size was also determined for each learning. With properly chosen network parameters as well as operation conditions, pH of the fermentation was thus well controlled by the RBPN controller.     

Biological production of 2,3-butanediol

2,3-Butanediol (2,3-BDL), which is very important for a variety of chemical feedstocks and liquid fuels, can be derived from the bioconversion of natural resources. One of its well known applications is the formation of methyl ethyl ketone, by dehydration, which can be used as a liquid fuel additive. This article briefly reviews the basic properties of 2,3-BDL and the metabolic pathway for the microbial formation of 2,3-BDL. Both the biological production of 2,3-BDL and the variety of strains being used are introduced. Genetically improved strains for BDL production which follow either the original mechanisms or new mechanisms are also described. Studies on fermentation conditions are briefly reviewed. On-line analysis, modeling, and control of BDL fermentation are discussed. In addition, downstream recovery of 2,3-BDL and the integrated process (being important issues of BDL production) are also introduced.     

Comparative evaluation of various control schemes for fed-batch fermentation

The crucial problem associated with control of fed-batch fermentation process is its time-varying characteristics. A successful controller should be able to deal with this feature in addition to the inherent nonlinear characteristics of the process. In this work, various schemes for controlling the glucose feed rate of fed-batch baker's yeast fermentation were evaluated. The controllers evaluated are fixed-gain proportional-integral (PI), scheduled-gain PI, adaptive neural network and hybrid neural network PI. The difference between the specific carbon dioxide evolution rate and oxygen uptake rate (Q_c-Q_o) was used as the controller variable. The evaluation was carried out by observing the performance of the controllers in dealing with setpoint tracking and disturbance rejection. The results confirm the unsatisfactory performance of the conventional controller where significant oscillation and offsets exist. Among the controllers considered, the hybrid neural network PI controller shows good performance.     

An artificial neural network for biomass estimation from automatic pH control signal

This study developed an artificial neural network (ANN) to estimate the growth of microorganisms during a fermentation process. The ANN relies solely on the cumulative consumption of alkali and the buffer capacity, which were measured on-line from the on/off control signal and pH values through automatic pH control. The two input variables were monitored on-line from a series of different batch cultivations and used to train the ANN to estimate biomass. The ANN was refined by optimizing the network structure and by adopting various algorithms for its training. The software estimator successfully generated growth profiles that showed good agreement with the measured biomass of separate batch cultures carried out between at 25 and 35_C.     

On-line monitoring and control of substrate concentrations in biological processes by flow injection analysis systems

Concentrations of substrates, glucose, and ammionia in biological processes have been on-line monitored by using glucose-flow injection (FIA) and ammonia-FIA systems. Based on the on-line monitored data the concentrations of substrates have been controlled by an on-off controller, a PID controller, and a neural network (NN) based controller. A simulation program has been developed to test the control quality of each controller and to estimate the control parameters. The on-off controller often produced high oscillations at the set point due to its low robustness. The control quality of a PID controller could have been improved by a high analysis frequency and by a short residence time of sample in a FIA system. A NN-based controller with 3 layers has been developed, and a 3(input)-2(hidden)-1(output) network structure has been found to be optimal for the NN-based controller. The performance of the three controllers has been tested in a simulated process as well as in a cultivation process ofSaccharomyces cerevisiae, and the performance has also been compared to simulation results. The NN-based controller with the 3-2-1 network structure was robust and stable against some disturbances, such as a sudden injection of distilled water into a biological process.     

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.     

An on-line sampling system for fermentation monitoring using membrane inlet mass spectrometry (MIMS): application to phenoxyacetic acid monitoring in penicillin fermentation

A sampling system for on-line monitoring of organic compounds of low volatility in complex fermentation media uses membrane inlet mass spectrometry (MIMS). A Syringe pump draws a continuous flow of microfiltered broth from the reactor and circulates it after acidification through a membrane inlet, in which a membrane is the only interface between the sample and the high vacuum of a mass spectrometer. All operations run automatically, i.e., sampling, acidification measurement, and calibration. The on-stream acidification enables MIMS monitoring of carboxylic acids, as they must be undissociated in order to pass the hydrophobic membrane. The performance of the monitoring system was tested by measurements of standard solutions of phenoxyacetic acid (POAA, the sie chain precursor of penicillin-V) as well as on POAA during 200 h penicillin-V fermentation. During the entire fermentation POAA was monitored n low millimolar concentrations with high accuracy and fast response to step changes in POAA concentration. Tandem mass spectrometry (MS/MS) allowed direct identification of peaks in the mass spectrum of the broth that were not accounted for by POAA. These peaks were identified as SO(2) and SCO. (c) 1994 John Wiley & Sons, Inc.     

On-line monitoring and controlling system for fermentation processes

A personal computer-based on-line monitoring and controlling system was developed for the fermentation of microorganism. The on-line HPLC system for the analysis of glucose and ethanol in the fermentation broth was connected to the fermenter via an auto-sampling equipment, which could perform the pipetting, filtration and dilution of the sample and final injection onto the HPLC through automation based on a programmed procedure. The A/D and D/A interfaces were equipped in order to process the signals from electrodes and from the detector of HPLC, and to direct the feed pumps, the motor of stirrer and gas flow-rate controller. The software that supervised the control of the stirring speed, gas flow-rate, pH value, feed flow-rate of medium, and the on-line measurement of glucose and ethanol concentration was programmed by using Microsoft Visual Basic under Microsoft Windows. The signal for chromatographic peaks from on-line HPLC was well captured and processed using an RC filter and a smoothing algorithm. This monitoring and control system was demonstrated to be effective in the ethanol fermentation of Zymomonas mobilis operated in both batch and fed-batch modes. In addition to substrate and product concentrations determined by on-line HPLC, the biomass concentration in Z. mobilis fermentation could also be on-line estimated by using the pH control and an implemented software sensor. The substrate concentration profile in the fed-back fermentation followed well the set point profile due to the fed-back action of feed flow-rate control.     

Medium optimization and proteome analysis of (R,R)-2,3-butanediol production by Paenibacillus polymyxa ATCC 12321

Paenibacillus polymyxa can produce the (R,R)-stereoisomer of 2,3-butanediol (2,3-BDL) which is industrially very useful. Two important factors affecting (R,R)-BDL production by P. polymyxa ATCC 12321, medium composition, and addition of acetic acid to the culture were investigated in this study with accompanying comparative proteomic analysis. For this purpose, a simple control strategy of O₂ supply was applied on the basis of an optimized basal medium: after a short period of batch cultivation with relatively high O₂ supply, the culture is switched into strong O₂ limitation, thereby promoting BDL formation. Three parallel fed-batch cultures starting from the same batch culture in an early stationary phase were then comparatively studied: the first one was running as control with the only change of O₂ supply; the second was, in addition, supplemented with 0.5 g/L yeast extract; and the third one was further added with 6 g/L acetate. Proteomic analyses of the three fed-batch cultures identified more than 86 proteins involved primarily in the central carbon metabolism, amino acid biosynthesis, energy metabolism, and stress responses. The examination of expression patterns of selected proteins, especially combined with fermentation data, gave valuable insights into the metabolic regulation of P. polymyxa under the different given conditions. Based on the proteomic analysis and further medium optimization studies, methionine was identified as one major growth-limiting factor in the basal medium and explains well the effect of yeast extract. Acetic acid was found to trigger the so far less studied acetone biosynthesis pathway in this organism. The latter is suggested in turn to enhance the switch from acidogenesis to solventogenesis. Thus, these findings extended our knowledge about BDL formation in P. polymyxa and provided useful information for further strain and process optimization.     

Determination of compound aminopyrine phenacetin tablets by using artificial neural networks combined with principal components analysis

A method for simultaneous, nondestructive analysis of aminopyrine and phenacetin in compound aminopyrine phenacetin tablets with different concentrations has been developed by principal component artificial neural networks (PC-ANNs) on near-infrared (NIR) spectroscopy. In PC-ANN models, the spectral data were initially analyzed by principal component analysis. Then the scores of the principal components were chosen as input nodes for the input layer instead of the spectral data. The artificial neural network models using the spectral data as input nodes were also established and compared with the PC-ANN models. Four different preprocessing methods (first-derivative, second-derivative, standard normal variate (SNV), and multiplicative scatter correction) were applied to three sets of NIR spectra of compound aminopyrine phenacetin tablets. The PC-ANNs approach with SNV preprocessing spectra was found to provide the best results. The degree of approximation was performed as the selective criterion of the optimum network parameters.     

Software sensing for glucose concentration in industrial antibiotic fedbatch culture using fuzzy neural network

In order to control glucose concentration during fed-batch culture for antibiotic production, we applied so called “software sensor” which estimates unmeasured variable of interest from measured process variables using software. All data for analysis were collected from industrial scale cultures in a pharmaceutical company. First, we constructed an estimation model for glucose feed rate to keep glucose concentration at target value. In actual fed-batch culture, glucose concentration, was kept at relatively high and measured once a day, and the glucose feed rate until the next measurement time was determined by an expert worker based on the actual consumption rate. Fuzzy neural network (FNN) was applied to construct the estimation model. From the simulation results using this model, the average error for glucose concentration was 0.88 g/L. The FNN model was also applied for a special culture to keep glucose concentration at low level. Selecting the optimal input variables, it was possible to simulate the culture with a low glucose concentration from the data sets of relatively high glucose concentration. Next, a simulation model to estimate time course of glucose concentration during one day was constructed using the on-line measurable process variables, since glucose concentration was only measured off-line once a day. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation model. As the result of the simulation, average error of RFNN model was 0.91 g/L and this model was found to be useful to supervise the fed-batch culture.     

A prototype neural network supervised control system for Bacillus thuringiensis fermentations

This article discusses the development of a prototype neural network-based supervisory control system for Bacillus thuringiensis fermentations. The input pattern to the neural network included the type of inoculum, operation temperature, pH value, accumulated process time, optical density in fermentation medium, and change in optical density. The output from the neural network was the predicted optical density for the next sampling time. The control system has been implemented in both a computer simulation and a laboratory fermentation experiment with promising results. (c) 1994 John Wiley & Sons, Inc.     

Adaptive on-line simulation of bioreactors: Fermentation monitoring and modeling system

Summary In order to study and control fermentation processes, indirect on-line measurements and mathematical models can be used. Here an on-line model for fermentation processes is presented. The model is based on atom and partial mass balances as well as on stability equations for the protolytes. The model is given an adaptive form by including transport equations for mass transfer and expressions for the fermentation kinetics. The state of the process can be estimated on-line using the balance component of the model completed with measurement equations for the input and the output flows of the process. Adaptivity is realized by means of on-line estimation of the parameters in the transport and kinetic expressions using recursive regression analysis. On-line estimation of the kinetic and mass transfer parameters makes model-based predictions possible and enables intelligent process control while facilitating testing of the validity of the measurement variables. A practical MS-Windows 3.1 model implementation called FMMS—Fermentation Monitoring and Modeling System is shown. The system makes it easy to configure the operating conditions for a run. It uses Windows dialogs for all set-ups, model configuration parameters, elemental compositions, on-line measurement devices and signal conditioning. Advanced on-line data analysis makes it possible to plot variables against each other for easy comparison. FMMS keeps track of over 100 variables per run. These variables are either measured or estimated by the model. Assay results can also be entered and plotted during fermentation. Thus the model can be verified almost instantly. Historical fermentation runs can be re-analyzed in simulation mode. This makes it possible to examine different signal conditining filters as well as the sensitivity of the model. Combined, the data analysis and the simulation mode make it easy to test and develop model theories and new ideas.     

Pattern analysis techniques to process fermentation curves: application to discrimination of enological alcoholic fermentations

In fermentation processes, kinetic curves are generally aimed at control purposes. However, these curves could also contain information about inherent features of the product (such as origin, quality, etc.). This article presents several pattern analysis techniques used to classify fermentation curves. An application to alcoholic fermentation is presented as an illustration: it aims at retrieving the origin of a must from its fermentation curve. The fermentation kinetics of five vineyard musts, harvested over 9 years on the same parcels, were recorded. From these curves two sets of variables were generated: The first (p(1)) gathers all the kinetic curve points. The second (p(2)) contains a restrained number of variables, generated by the expert knowledge of the enologist. The set p(2) was processed by two very different techniques: a linear one (factorial discriminant analysis) and a nonlinear one (artificial neural networks). The set p(1) was processed by a new chemometric technique, the discriminant partial least-squares regression. For all the sets and the techniques used the selection of variables was studied. The interest in the latter is largely demonstrated both by theoretical and practical discussions. The discrimination results (up to 94% of good predictions) enhance the interest of the on-line measurements and their use in such pattern analysis tools.     

Optimization of temperature and initial pH and kinetic analysis of tartaric acid production by Gluconobacter suboxydans

Response surface methodology was applied for the simultaneous optimization of initial pH and temperature of fermentation for the production of tartaric acid by Gluconobacter suboxydans. A temperature of 32.8v°C and an initial pH of 6.05 was found to be most suitable. Kinetic analysis for the growth of Gluconobacter suboxydans and product formation was done and a logistic model was used to describe the growth of Gluconobacter suboxydans while the Leudeking-Piret model explained the product formation. Parameters of the model were evaluated and tartaric acid formation was found to be non-growth associated.     

Enhanced production of L-(+)-lactic acid in chemostat by Lactobacillus casei DSM 20011 using ion-exchange resins and cross-flow filtration in a fully automated pilot plant controlled via NIR

Due to the lack of suitable in-process sensors, on-line monitoring of fermentation processes is restricted almost exclusively to the measurement of physical parameters only indirectly related to key process variables, i.e., substrate, product, and biomass concentration. This obstacle can be overcome by near infrared (NIR) spectroscopy, which allows not only real-time process monitoring, but also automated process control, provided that NIR-generated information is fed to a suitable computerized bioreactor control system. Once the relevant calibrations have been obtained, substrate, biomass and product concentration can be evaluated on-line and used by the bioreactor control system to manage the fermentation. In this work, an NIR-based control system allowed the full automation of a small-scale pilot plant for lactic acid production and provided an excellent tool for process optimization. The growth-inhibiting effect of lactic acid present in the culture broth is enhanced when the growth-limiting substrate, glucose, is also present at relatively high concentrations. Both combined factors can result in a severe reduction of the performance of the lactate production process. A dedicated software enabling on-line NIR data acquisition and reduction, and automated process management through feed addition, culture removal and/or product recovery by microfiltration was developed in order to allow the implementation of continuous fermentation processes with recycling of culture medium and cell recycling. Both operation modes were tested at different dilution rates and the respective cultivation parameters observed were compared with those obtained in a conventional continuous fermentation. Steady states were obtained in both modes with high performance on lactate production. The highest lactate volumetric productivity, 138 g L(-1) h(-1), was obtained in continuous fermentation with cell recycling.     

On-line monitoring and control of acetone-butanol fermentation by membrane-sensor mass spectrometry

A mass spectrometry (MS) membrane sensor was developed and applied to on-line product measurement in acetone-butanol fermentation. The sensor facilitated the monitoring of acetone, butanol, ethanol, H₂ and CO₂, and single-compound calibration curves for both acetone and butanol showed a linear relationship between the product concentration and the MS response. However, when an actual fermentation was monitored, the product concentration calculated from the MS response was smaller than the concentration determined by gas chromatography, and the relationship between the response and the product concentration was nonlinear. It was found that large amounts of gases (H₂, CO₂) entering the MS analyzation chamber were causing a ‘space charge effect’, which resulted in an MS response ceiling. The problem could be resolved by reducing the surface area of the sensor membrane. Under some fermentation conditions, a by-product, n-butyl butyrate, was produced, and this interfered with the measurement of butanol due to a peak overlapping effect. However, it was found that this could be compensated for by using an empirical equation. Application of the MS membrane sensor in a fed batch culture of acetone-butanol fermentation resulted in successful control of the butanol concentration.     

Breath gas metabolites and bacterial metagenomes from cystic fibrosis airways indicate active pH neutral 2,3-butanedione fermentation

The airways of cystic fibrosis (CF) patients are chronically colonized by patient-specific polymicrobial communities. The conditions and nutrients available in CF lungs affect the physiology and composition of the colonizing microbes. Recent work in bioreactors has shown that the fermentation product 2,3-butanediol mediates cross-feeding between some fermenting bacteria and Pseudomonas aeruginosa, and that this mechanism increases bacterial current production. To examine bacterial fermentation in the respiratory tract, breath gas metabolites were measured and several metagenomes were sequenced from CF and non-CF volunteers. 2,3-butanedione was produced in nearly all respiratory tracts. Elevated levels in one patient decreased during antibiotic treatment, and breath concentrations varied between CF patients at the same time point. Some patients had high enough levels of 2,3-butanedione to irreversibly damage lung tissue. Antibiotic therapy likely dictates the activities of 2,3-butanedione-producing microbes, which suggests a need for further study with larger sample size. Sputum microbiomes were dominated by P. aeruginosa, Streptococcus spp. and Rothia mucilaginosa, and revealed the potential for 2,3-butanedione biosynthesis. Genes encoding 2,3-butanedione biosynthesis were disproportionately abundant in Streptococcus spp, whereas genes for consumption of butanedione pathway products were encoded by P. aeruginosa and R. mucilaginosa. We propose a model where low oxygen conditions in CF lung lead to fermentation and a decrease in pH, triggering 2,3-butanedione fermentation to avoid lethal acidification. We hypothesize that this may also increase phenazine production by P. aeruginosa, increasing reactive oxygen species and providing additional electron acceptors to CF microbes.