Real-time fuzzy-knowledge-based control of Baker's yeast production

A real-time fuzzy-knowledge-based system for fault diagnosis and control of bioprocesses was constructed using the object-oriented programming environment Small-talk/V Mac. The basic system was implemented in a Macintosh Quadra 900 computer and built to function connected on line to the process computer. Fuzzy logic was employed in handling uncertainties both in the knowledge and in measurements. The fuzzy sets defined for the process variables could be changed on-line according to process dynamics. Process knowledge was implemented in a graphical two-level hierachical knowledge base. In on-line process control the system first recognizes the current process phase on the basis of top-level rules in the knowledge-base. Then, according to the results of process diagnosis based on measurement data, the appropriate control strategy is subsequently inferred making use of the lower level rules describing the process during the phase in question. (c) 1995 John Wiley & Sons, Inc.     

Object-oriented fuzzy expert system for on-line diagnosing and control of bioprocesses

Summary An object-oriented fuzzy expert system to support on-line control of an automated fermentation plant is described. The major elements of the system consist of a fuzzy inference engine, a database, a knowledge base, and an expression evaluater. The expression evaluater calculates specific rates for growth, and substrate and product formation at different physiological states during the cultivation from the measured data. The specific rates are then compared with the standard target rates stored in the database. If differences outside the set tolerances were observed, the inference engine analyses the reasons for the faults on the basis of the knowledge represented in the form of a knowledge network and fuzzy membership functions of the process variables. The fuzzy expert system was developed on the basis of a shell constructed by using the object oriented Smalltalk/V Mac programming environment, with Lactobacillus casei lactic acid fermentation as the example of process application.Visiting scientist from Helsinki University of Technology at RIKEN Correspondence to: P. Linko or I. Endo     

Fuzzy reasoning system for fault diagnosis of physiological activities in a cultivating process.

Aiming at development of a system which supports cultivating operations, a method to diagnose physiological activities in a cultivating process is presented, and a fuzzy expert system for diagnosing Lactobacillus casei cultivating process is implemented in this paper. This system can calculate specific rates of cell growth, substrate consumption, and product formation with measuring cell mass concentration, substrate concentration, and product concentration by using a turbidity sensor and HPLC. A database is implemented, where standard curves on specific rates representing characteristics of microorganisms are stored according to normalized substrate consumption. Comparing the calculated specific rates with standard values derived from the database, the system diagnoses physiological activities of the microorganisms. As a case study, a knowledge base for diagnosing lactic acid production process is implemented. The use of fault diagnosis on pH malfunctions by the expert system proves its reasonable performance.     

A knowledge based system for diagnosing microbial activities during a fermentation process

A knowledge based system, LAexpert, was developed to diagnose microbial activities during a fermentation process on the basis of specific rates determined on-line. The LAexpert is a supervisor for a process control system and assists operators in fault diagnosis. The LAexpert was implemented using a fuzzy expert system shell based on the object oriented programming tool Smalltalk V/Mac running in a Macintosh II computer. The shell can handle uncertainties both in the measurements and knowledge by fuzzy reasoning.List of Symbols X g/l biomass dry weight (g/l) - S g/l substrate concentration (g/l) - P g/l product concentration (g/l) - _c, _c, _c 1/h specific rates calculated from on-line measured data of X, S and P (1/h) - _d, _d, _d 1/h specific rates read from database of BIOACS (1/h)     

Incorporation of negative rules and evolution of a fuzzy controller for yeast fermentation process

The control of bioprocesses can be very challenging due to the fact that these kinds of processes are highly affected by various sources of uncertainty like the intrinsic behavior of the used microorganisms. Due to the reason that these kinds of process uncertainties are not directly measureable in most cases, the overall control is either done manually because of the experience of the operator or intelligent expert systems are applied, e.g., on the basis of fuzzy logic theory. In the latter case, however, the control concept is mainly represented by using merely positive rules, e.g., “If A then do B”. As this is not straightforward with respect to the semantics of the human decision-making process that also includes negative experience in form of constraints or prohibitions, the incorporation of negative rules for process control based on fuzzy logic is emphasized. In this work, an approach of fuzzy logic control of the yeast propagation process based on a combination of positive and negative rules is presented. The process is guided along a reference trajectory for yeast cell concentration by alternating the process temperature. The incorporation of negative rules leads to a much more stable and accurate control of the process as the root mean squared error of reference trajectory and system response could be reduced by an average of 62.8 % compared to the controller using only positive rules.     

On‐line yeast propagation process monitoring and control using an intelligent automatic control system

The monitoring and control of bioprocesses is a challenging task. This applies particularly if the actions to the process have to be carried out in real‐time. This work presents a system for on‐line monitoring and control of batch yeast propagation under limiting conditions based on a virtual plant operator, which uses the concept of intelligent control algorithms by means of fuzzy logic theory. Process information is provided on‐line using a sensor array comprising the measurement of OD, operating temperature, pressure, density, dissolved oxygen, and pH value. In this context practical problems arising through on‐line sensing and signal processing are addressed. The preprocessed sensor data are fed to a neural network for on‐line biomass estimation. The root mean squared error of prediction is 4 × 10⁶ cells/mL. The proposed system then triggers temperature and aeration by usage of a temperature dependent metabolic growth model and sensor data. The deviation of the predicted biomass from that of the reference trajectory as modeled by the metabolic growth model and its temporal derivative are used as inputs for the fuzzy temperature controller. The inputs used by the fuzzy aeration controller are the deviation of measured extract from that of the reference trajectory, the predicted cell count, and the dissolved oxygen concentration. The fuzzy‐based expert system allows to provide the desired yeast cell concentration of 100–120 × 10⁶ cells/mL at a minimum residual extract limit of 6.0 g/100 g at the required point of time. Thus, a dynamic adjustment of the propagation process to the overall production schedule is possible in order to produce the required amount of biomass at the right time.     

Constructing a fuzzy rule-based system using the ILFN network and Genetic Algorithm.

In this paper, a method for automatic construction of a fuzzy rule-based system from numerical data using the Incremental Learning Fuzzy Neural (ILFN) network and the Genetic Algorithm is presented. The ILFN network was developed for pattern classification applications. The ILFN network, which employed fuzzy sets and neural network theory, equips with a fast, one-pass, on-line, and incremental learning algorithm. After trained, the ILFN network stored numerical knowledge in hidden units, which can then be directly interpreted into if then rule bases. However, the rules extracted from the ILFN network are not in an optimized fuzzy linguistic form. In this paper, a knowledge base for fuzzy expert system is extracted from the hidden units of the ILFN classifier. A genetic algorithm is then invoked, in an iterative manner, to reduce number of rules and select only discriminate features from input patterns needed to provide a fuzzy rule-based system. Three computer simulations using a simulated 2-D 3-class data, the well-known Fisher's Iris data set, and the Wisconsin breast cancer data set were performed. The fuzzy rule-based system derived from the proposed method achieved 100% and 97.33% correct classification on the 75 patterns for training set and 75 patterns for test set, respectively. For the Wisconsin breast cancer data set, using 400 patterns for training and 299 patterns for testing, the derived fuzzy rule-based system achieved 99.5% and 98.33% correct classification on the training set and the test set, respectively.     

An object-oriented modelling framework for the arterial wall

An object-oriented modelling framework for the arterial wall is presented. The novelty of the framework is the possibility to generate customisable artery models, taking advantage of imaging technology. In our knowledge, this is the first object-oriented modelling framework for the arterial wall. Existing models do not allow close structural mapping with arterial microstructure as in the object-oriented framework. In the implemented model, passive behaviour of the arterial wall was considered and the tunica adventitia was the objective system. As verification, a model of an arterial segment was generated. In order to simulate its deformation, a matrix structural mechanics simulator was implemented. Two simulations were conducted, one for an axial loading test and other for a pressure–volume test. Each simulation began with a sensitivity analysis in order to determinate the best parameter combination and to compare the results with analogue controls. In both cases, the simulated results closely reproduced qualitatively and quantitatively the analogue control plots.     

Fuzzy knowledge- and data-based models of damage to reeds by grazing of Greylag Geese

This paper describes a fuzzy and neuro-fuzzy approach to modelling feeding intensity of Greylag Geese on reed. As a consequence of the presence of some non-measurable or random factors and the heterogeneity of reed and goose behaviour, the relationships between the model variables are often not well known and the data collected have a high degree of uncertainty. A fuzzy approach was selected which can be applied with vague knowledge and data of high uncertainty. Fuzzy logic can be used to handle inexact reasoning in knowledge-based models with fuzzy rules and fuzzy sets to handle uncertainty in data. The neural network technique was applied to develop the fuzzy data-based models. For training, several dataset combinations of three lakes in North Germany were used. The generalisation capability of these models was checked for other lakes. The performance of these models was compared with the results of the fuzzy knowledge-based model developed in the next step. The knowledge base of this model contains the Mamdani-type rules formulated by a domain expert. All models were implemented using the Fuzzy Logic Toolbox of MATLAB^®.     

Fuzzy rule‐based decision support system for evaluation of long‐established forest restoration projects

Although the importance of monitoring and evaluation of restoration actions is increasingly acknowledged, availability of accurate, quantitative monitoring data is very rare for most restoration areas, particularly for long‐established restoration projects. We propose using fuzzy rule‐based expert systems to evaluate the degree of success of restoration actions when available information on project results and impacts largely relies on expert‐based qualitative assessments and rough estimates of quantitative values. These systems use fuzzy logic to manage the uncertainty present in the data and to integrate qualitative and quantitative information. To illustrate and demonstrate the potential of fuzzy rule‐based systems for restoration evaluation, we applied this approach to seven forest restoration projects implemented in Spain between 1897 and 1952, using information compiled in the REACTION database on Mediterranean forest restoration projects. The information available includes both quantitative and expert‐based qualitative data, and covers a wide variety of indicators grouped into technical, structural, functional, and socioeconomic criteria. The fuzzy rule‐based system translates expert knowledge of restoration specialists and forest managers into a set of simple logic rules that integrate information on individual indicators into more general evaluation criteria. The rule‐based approach proposed here can be readily applicable to any kind of restoration project, provided that some information, even if vague and uncertain, is available for a variety of assessment indicators. The evaluation of long‐established forest restoration projects implemented in Spain revealed important asymmetries in the degree of restoration success between technical, structural, functional, and socioeconomic criteria.     

Knowledge based diagnosis of inoculum properties and sterilization time in lactic acid fermentation

Summary A knowledge based system has been shown to be a powerful tool for diagnosing microbial activities during a fermentation process. Knowledge about lactic acid fermentation was collected by an experimental study ofLactobacillus casei. The effects of the inoculum properties and sterilization time on the cultivation were expressed in a form of a fuzzy rule-based knowledge network. The system was able to detect abnormal inoculum or sterilization conditions which caused malfunctions in the cultivations.     

F-IND: A framework to design fuzzy indices of environmental conditions

Multivariable indices of environmental conditions summarize the information provided by several biotic or abiotic variables into a single value of immediate interpretability. Thus they are important instruments for monitoring. Developing new indices that combine different variables is not a trivial task: variables may be qualitative, or measured in different units, and the relationship between primitive components and quality may be ambiguous. Fuzzy logic has been repeatedly proposed as an effective technique to cope with such problems; however, the variety of choices that exist at each stage of the development of fuzzy models may present a problem for the index designer. In this paper we present F-IND, a framework to create fuzzy indices by means of a simplified and intuitive procedure. It allows to capture the expert knowledge of the system under study (air, soil, water) to easily generate a multivariable index of environmental conditions. F-IND is implemented in Java, to achieve an optimal portability on any operating system.     

基于HIS模型建立肝病知识库对军队医院的作用及意义

目的:通过整合302医院丰富的肝病病例、肝病专家诊疗经验和临床科研数据,建立肝病知识库,提高基础资源辅助临床诊疗和科研的能力。方法:对肝病智能知识模型进行分析,获取知识库中结构化知识,并以知识库模型的形式建立知识库,形成一套独立、可重复的智能化的辅助诊疗和科研信息系统,实现知识库辅助临床诊疗、知识科学研究,最大程度发挥知识库的意义,真正为临床服务。结果:建立的基于HIS的肝病知识库主要编配于医疗单位,适用于临床医护人员、临床科研人员以及所有从事医疗行业的工作人员。医护工作者可通过程序访问知识库,对知识库中的肝病知识进行检索、分析、推理,辅助临床医护工作者提高临床诊疗能力,提升临床科研水平。结论:建立的肝病知识库系统为用户提供横向及纵向医疗基础信息的检索、分析及推理方法。推理出的合适的知识模型,为肝病的临床诊疗和临床科研提供前沿、实用、高效的智能辅助信息支持。     

Classification of antituberculosis herbs for remedial purposes by using fuzzy sets

Using fuzzy set theory, we created a system, that assesses a herb's usefulness for the treatment of tuberculosis, based on ethnobotanical data. We analysed two systems which contain different amount of inputs. The first system contains four inputs, the second one contains six inputs. We used the Takagi–Sugeno–Kanga model. Mamdani model is poor at representation as it needs more fuzzy rules than that of TSK to model a real world system where accuracy is demanded.It has been employed a fuzzy controller, and a fuzzy model, in successfully solving difficult control and modelling problems in practice. It is implemented in the Fuzzy Logic Toolbox in Matlab.The data for inputs are gathered in the database named SOPAT (selection of plants against tuberculosis), which is part of a project coordinated by the Oxford International Biomedical Centre. In this database there could be up to one millon plant species. It would be cumbersome to select a remedy from one (or some) of these species looking at the data base one-by-one. By means of the fuzzy set theory this remedy can be chosen very quickly.     

Inline noninvasive Raman monitoring and feedback control of glucose concentration during ethanol fermentation

Raman spectroscopy as a process analytical technology tool was implemented for the monitoring and control of ethanol fermentation carried out with Saccharomyces cerevisiae. The need for the optimization of bioprocesses such as ethanol production, to increase product yield, enhanced the development of control strategies. The control system developed by the authors utilized noninvasive Raman measurements to avoid possible sterilization problems. Real-time data analysis was applied using partial least squares regression (PLS) method. With the aid of spectral pretreatment and multivariate data analysis, the monitoring of glucose and ethanol concentration was successful during yeast fermentation with the prediction error of 4.42 g/L for glucose and 2.40 g/L for ethanol. By Raman spectroscopy-based feedback control, the glucose concentration was maintained at 100 g/L by the automatic feeding of concentrated glucose solution. The control of glucose concentration during fed-batch fermentation resulted in increased ethanol production. Ethanol yield of 86% was achieved compared to the batch fermentation when 75 % yield was obtained. The results show that the use of Raman spectroscopy for the monitoring and control of yeast fermentation is a promising way to enhance process understanding and achieve consistently high production yield.     

中国生态农业模式管理信息及决策支持系统的建立

根据全国生态农业试点县建设和典型生态农业模式研究的经验,利用Access数据库技术建立了全国首批生态农业县有关自然资源背景、农业生产水平、生态环境与工程技术等各种基础信息数据库和所推广应用的生态农业模式信息数据库,可快速方便地提供各生态农业县相关信息或知识的查询或编辑．在此基础上,采用了面向对象的推理方法建立了生态农业模式区域决策的知识库体系模型,并利用Visual C^++语言初步开发出生态农业模式的区域决策支持系统,基本上实现了区域生态农业模式的决策推荐．     

A simple method to monitor and control methanol feeding of Pichia pastoris fermentations using mid-IR spectroscopy

Mid-infrared FTIR spectroscopy is an efficient tool for the monitoring of bioprocesses, since it is fast and able to detect many compounds simultaneously. However, complex and time-consuming calibration procedures are still required, and have inhibited the spreading of these instruments. A simple and quick method to calibrate a FTIR instrument was developed for the control of fed-batch fermentations of the methylotrophic yeast Pichia pastoris. Based on the assumptions that (1) only substrate concentration may change significantly during a fed-batch process and (2) absorbance can be considered as proportional to concentration, a linear two-point calibration was implemented. Long-term instability of the instrument had to be addressed in order to get accurate results: two fixed points, on both sides of substrate absorbance peak, were used to perform on-line a linear correction of the signal drift. Fed-batch experiments at constant methanol (substrate) concentration ranging from 0.8 to 15gl(-1) were carried out. Off-line HPLC control analysis showed a good agreement with on-line FTIR data, with standard error of prediction values < 0.12gl(-1). Even though methanol acts both as carbon source and inducer of protein expression, no significant effect was observed on the level of protein expression in the recombinant strain used.     

Colonic lesion expert system. Evaluation of sensitivity

In a previous study, an expert system using visually assessed diagnostic clues for diagnosing colonic tissue as normal, adenoma or adenocarcinoma arrived at diagnoses agreeing with the evaluation by pathologists ("correct diagnoses") for all 49 cases of normal colon, for 49 of 50 cases of adenoma and for 48 of 49 cases of adenocarcinoma. The present study examined the robustness and sensitivity of the expert system to changes in the knowledge base, to changes in criteria specified by the user and to missing information. Alternative rules for combining certainty factors are discussed.     

Investigation of the potential of biocalorimetry as a process analytical technology (PAT) tool for monitoring and control of Crabtree-negative yeast cultures

Biological reaction calorimetry, also known as biocalorimetry, has led to extensive applications in monitoring and control of different bioprocesses. A simple real-time estimator for biomass and growth rate was formulated, based on in-line measured metabolic heat flow values. The performance of the estimator was tested in a unique bench-scale calorimeter (BioRC1), improved to a sensitivity range of 8 mW l^− 1 in order to facilitate the monitoring of even weakly exothermic biochemical reactions. A proportional–integral feedback control strategy based on these estimators was designed and implemented to control the growth rate of Candida utilis, Kluyveromyces marxianus and Pichia pastoris by regulating an exponential substrate feed. Maintaining a particular specific growth rate throughout a culture is essential for reproducible product quality in industrial bioprocesses and therefore a key sequence for the step from quality by analysis to quality by design. The potential of biocalorimetry as a reliable biomass monitoring tool and as a key part of a robust control strategy for aerobic fed-batch cultures of Crabtree-negative yeast cells in defined growth medium was investigated. Presenting controller errors of less than 4% in the best cases, the approach paves the way for the development of a generally applicable process analytical technology platform for monitoring and control of microbial fed-batch cultures.