A case based reasoning system capturing fire modelling expertise

This paper describes the architecture of the case based reasoning (CBR) com ponent of Smartfire, a fire field modelling tool for use by members of the Fire Safety Engineering community who are not expert in modelling technique s. The CBR system captures the qualitative reasoning of an experienced mode ller in the assessment of room geometries so as to set up the important ini tial parameters of the problem. The system relies on two important reasonin g principles obtained from the expert: 1) there is a natural hierarchical r etrieval mechanism which may be employed; and 2) much of the reasoning on a qualitative level is linear in nature, although the computational solution of the problem is non-linear. The paper describes the qualitative represen tation of geometric room information on which the system is based, and the principles on which the CBR system operates.