Operator guidance system for coal washing

Abstract

In this paper we present the analysis, design and implementation of the Ash Control Model (AshMod), a real-time knowledge-based operator guidance system (OGS) in the coal washing domain. The complexity of coal washing is such that a knowledge modelling methodology was needed for the development of this operator guidance system. The Knowledge Acquisition and Design Structuring (KADS) methodology guided us in the development of these knowledge models. We present an integration of the KADS methodology with the G2 real time implementation environment. AshMod assists the operator in monitoring the plant, performing fault diagnosis, and in plant optimisation. Furthermore, it assists the operator in maximising clean coal yield while keeping ash (impurity) content within acceptable limits. AshMod performs deep reasoning through the use of KADS-inspired knowledge models that capture purpose, function, structure, behaviour and heuristics. Knowledge validation and maintenance are facilitated through the use of graphical object-oriented knowledge models, implemented in G2. AshMod has been developed for the B and C coal washing plants operated by Broken Hill Proprietary Limited (BHP) at Port Kembla, Australia. 1,2 Owing to our focus on generality and reuse during the development of this operator guidance system, we expect that much of AshMod can be reused in future OGS developments in BHP-operated coal washeries, sinter plants, blast furnaces, coke ovens etc. AshMod is currently undergoing online testing at the coal washing plants.