Treffer: Fault Diagnosis of a Sewage Plant

In this paper we present a project whose aim is the development of an expert system managing and diagnosing a sewage plant. After a short description how the knowledge acquisition process took place we will explain why the popular model-based diagnosis approach cannot be applied to our problem domain. Instead we had to consider associative knowledge to solve the diagnostic problem. In order to adequately express knowledge about the structure of the sewage plant, knowledge about well understood subprocesses and associative knowledge for the diagnosis of the sewage plant we designed the tool MOTESDM that supports hybrid knowledge representation. MOTESDM allows us to separate associative knowledge from structural knowledge concerning the technical system. AI topic: knowledge representation, diagnosis Domain area: monitoring of sewage plants Language/Tool: Smalltalk-80, MOTESDM Status: running prototype Impact: The system will guarantee the correct behavior in small- and medium sized .