Knowledge-Based Fault Detection and Super Vision of Urban Sewer Networks

Abstract

The paper presents the development of a Real-Time Expert System for the supervision and fault detection in Urban Sewer Networks (USN). Several vital characteristics of such an expert tool, in which the project is being developed, are reminded. The main aspects of the modelling of the USN and the detection of defaults are outlined and illustrated on the case of a test urban area, north-east from Paris. Procedural knowledge about the behaviour of the USN is implemeted within formulae and procedures. Object-Oriented Representation enables the structuration and formulation of the system structure. Rule bases containing expert, heuristic knowledge are written in a structured, natural language. Knowledge formulation and implementation are illustrated on a system prototype designed with G2 (Gensym Corp.).