TOWARDS INTELLIGENT PROCESS SUPERVISION - INDUSTRIAL PENICILLIN FERMENTATION CASE-STUDY

Due to the their biological nature and inherent variability bioprocess es place significant demands on even the most advanced supervision app roaches. Sophisticated supervision software, such as G2 from Gensym (a real-time knowledge based system) is already finding wide industrial bioprocess application. However, in order to overcome the severe chall enges posed a straightforward 'coding' of operators and engineers know ledge is not sufficient. What is required is a methodology which attem pts to maximise the information available for supervision purposes. Th is paper describes the development of an application in which feature extraction and data based methodologies are integrated with sophistica ted physiological models to considerably enhance a rule-based supervis ory system. Together within the G2 real-time knowledge based system fr amework they offer the potential for bioprocess operational improvemen t.