Advertisement

Monitoring and Diagnosis of Fermentation Processes

From a rule-based to a model-based expert system
  • Kouamana Bousson
  • Jean-Philippe Steyer
  • Boutaib Dahhou
  • Louise Travé-Massuyès
Chapter

Abstract

This chapter deals with monitoring and diagnosing a fedbatch fermentation process by means of a real-time expert system. The first part of the chapter presents the rule-based expert system BIOTECH which, among other tasks, detects the abnormalities in the process behaviour beforehand, advises the operator about what to do to correct unwanted behaviours of the process, assesses the state of unmeasured variables and may be used as a computeraided process monitoring instruction system. Although BIOTECH assumes an underlying model of causality paths of the process, this model is not explicitly represented. To enhance robustness and generality, we have undertaken to devise a model-based approach to account for influence analysis and computation among the process variables. This approach is implemented in the model- based reasoning module CA-EN (Causal Engine).

Keywords

Expert System Fermentation Process Concentration Rate Global Constraint Process Pattern 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • Kouamana Bousson
  • Jean-Philippe Steyer
  • Boutaib Dahhou
  • Louise Travé-Massuyès

There are no affiliations available

Personalised recommendations