Anaerobic digestion (AD) plants are highly efficient wastewater treatment processes with possible energetic valorisation. Despite these advantages, many industries are still reluctant to use them because of their instability in the face of changes in operating conditions. To the face this drawback and to enhance the industrial use of anaerobic digestion, one solution is to develop and to implement knowledge base (KB) systems that are able to detect and to assess in real-time the quality of operating conditions of the processes. Case-based techniques and heuristic approaches have been already tested and validated on AD processes but two major properties were lacking: modularity of the system (the knowledge base system should be easily tuned on a new process and should still work if one or more sensors are added or removed) and uncertainty management (the assessment of the KB system should remain relevant even in the case of too poor or conflicting information sources). This paper addresses these two points and presents a modular KB system where an uncertain reasoning formalism is used to combine partial and complementary fuzzy diagnosis modules. Demonstration of the interest of the approach is provided from real-life experiments performed on an industrial 2,000 m3 CSTR anaerobic digester.

This content is only available as a PDF.