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

Numers, Camilla von; Nakajima, M.; Siimes, T.; Asama, Hajime; Linko, P.; Endo, Itaru

doi:10.1016/0168-1656(94)90081-7

Cited by 22 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially for rule‐based expert systems, many successful applications were reported. Most applications are based on fuzzy logic ; modeling based on fuzzy logic uses a procedure to represent uncertainty for the implementation of knowledge about the process under consideration. Here rules from the experience of a process operator can be represented in a computer using imprecise linguistic variables and utilizing them to calculate control actions.…”

Section: Modeling Methodologiesmentioning

confidence: 99%

Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation

Solle

Hitzmann

Herwig

et al. 2017

Chemie Ingenieur Technik

View full text Add to dashboard Cite

The best method for process control is the use of model‐based solutions, based on process analytical technology for online monitoring of critical process variables, product quality attributes, or a holistic process state estimation. Mechanistic models as well as data‐driven techniques are essential for real‐time process monitoring. Their main characteristics, advantages and disadvantages, and the link between both are discussed as well as the synergetic effects, benefits, and drawbacks resulting from their combination. Aspects and differences of the computational model life cycle management are highlighted.

show abstract

Section: Modeling Methodologiesmentioning

confidence: 99%

Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation

Solle

Hitzmann

Herwig

et al. 2017

Chemie Ingenieur Technik

View full text Add to dashboard Cite

show abstract

“…Knowledge-based systems can be used to couple quantitative information with qualitative symbolic expressions (heuristics) of skilled, experienced operators to provide computer-based supervision (Konstantinov and Yoshida, 1992) for input-data validation, for fault diagnosis (Von Numers et al, 1994), and for plant scheduling.…”

Section: Bioprocess Diagnosis and Automationmentioning

confidence: 99%

Monitoring of Submerged Bioprocesses

Vaidyanathan

Macaloney

Vaughan

et al. 1999

Critical Reviews in Biotechnology

View full text Add to dashboard Cite

Monitoring is an important exercise in the operation of submerged bioprocesses and is a subject that has attracted intense research activity in recent years. In order to achieve optimal production or conversion, the factors that influence the performance of a bioprocess should be measured, preferably on-line, so that the process can be monitored in real-time and appropriate control or remedial action implemented. Such measurements can be achieved either in situ or ex situ. Ideally, in situ approaches are desirable. Where such an option is difficult to implement, ex situ approaches with appropriate sample handling techniques can be employed. In cases where direct analytical information is not available, inferential approaches can be adopted. In addition, analytical information not yet accessible on-line can be obtained off-line. Computational techniques have enabled the compilation of measurement data before utilizing the information for process diagnosis. Current developments in the different measurement technologies are presented with a critical assessment of their potential application in industrial production or process development.

show abstract

“…rules describing the process. The InferenceNet was constructed of different types of NetNodes along the lines described by von Numers et al 34 The different nodes are responsible for the functions of the knowledge net, hierarchically organized to phase recognition network, and separate subnetworks to control each phase, schematically illustrated in Figure 2. The NetNode subclass RuleNode had itself several subclasses, such as AndNodes, OrNodes, and RunNodes.…”

Section: Fuzzyvariable (Do E F Rq S X)mentioning

confidence: 99%

“…mation and prediction of key state variable^^^'^.^^^^^ and implementing subjective expert's knowledge into intelligent process control systems. 15930,31, 34 Further, the division of the process into different phases can markedly simplify estimation and c0ntr01. '2~22~'5 B y employing a fuzzy phase recognition method in bioprocess control, sudden changes in culture state which often are detrimental in a fermentation process may be avoided, and process models used for control are considerably simplified when they represent only a part of the process at a…”

Section: Introductionmentioning

confidence: 99%

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

Siimes¹,

Linko²,

Numers

et al. 1995

Biotech & Bioengineering

Self Cite

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 22 publications

References 6 publications

Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation

Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation

Monitoring of Submerged Bioprocesses

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

Contact Info

Product

Resources

About