Terhi Siimes

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

SummaryAn 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.

A knowledge based system using fuzzy inference for supervisory control of bioprocesses

Abstract In this paper, a rule-based, real-time knowledge based system for bioprocess fault diagnosis and control is described. The system was designed to generate on-line advice for the operators and to supervise automatic control of bioprocesses, using biotechnical production of lactic acid as an example process. It consists of a real-time data acquisition and data processing system linked to a fuzzy expert system written in Smalltalk V/Mac. The expert knowledge was expressed in the form of a rule-based knowledge network, fuzzy membership functions and control strategies. The fuzzy expert system carries out on-line fault diagnosing on the basis of filtered specific rates calculated from process variable measurements, and provides suitable countermeasures to recover the process. Fault diagnosis was realized both by backward and forward chaining procedures. The system was constructed to allow three different control strategies (given here in Smalltalk syntax), change of Setpoint, FuzzyAnswer for each discovered fault, employing the fuzzy mean defuzzification method, and linguistic Advice to the operator. The system was successfully tested on-line with a laboratory scale process.

Fuzzy supervisory control of fed-batch baker's yeast process

A fuzzy supervisory system for bioprocess control was developed, and applied to bakers yeast fermentation. The system was based on hierarchical bioprocess control with fuzzy phase recognition and separate fuzzy control of each process phase. A two-level knowledge base included rules both for the phase recognition and control. The system was tested by using experimental data of fed-batch bakers yeast cultivations and by process simulations.

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

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.

Knowledge Based Diagnosis in Lactic Acid Fermentation

Abstract A knowledge based diagnosis system for lactic acid fermentation was developed using a fuzzy expert system. The performance of the system was tested using experimental data obtained under abnormal culture conditions. The results showed that the system developed could diagnose faults and malfunctions of the lactic acid fermentations very well.

Flexible computer-aided design, monitoring and data management system for biocatalyst production

With an increasing need for computer-aided bioprocess research and development techniques a novel software package BioBOSS was constructed, and applied in experimental design, monitoring, and data analysis of glucoamylase fermentation. The new tool allowed all the information management and data processing to be carried out with a single program package. Data transfer, and analysis and storing of experimental results could be carried out conveniently and with ease. The BioBOSS software package markedly simplified research planning and execution, resulting in a greater efficiency and considerable savings in time.

Multivariate Process Modelling Applied to Lysine Production

Abstract A multivariate technique (projection to latent structures, PLS) was used for modelling the production of an amino acid, lysine. Lysine fermentations were divided into three growth phases. Separate PLS-models were constructed for each of these phases. We demonstrate that sequential PLS-models can be used for fed-batch fermentation modelling.

On-line Diagnosing System for Fed-Batch Fermentation

An on-line diagnosing system for a fed-batch fermentation process has been developed. The system is based on the physiological activities of a micro-organism which are represented by specific rates like cellular growth, substrate consumption and production of an aiming substance. These process variables can be measured by an on-line system named Bio Advanced Control System (BIOACS) which we developed in 1985.