Fuzzy Neural Network as Instance Generator for Case-Based Reasoning System: An Example of Selection of Heat Exchange Equipment in Mixing Tanks

Abstract

The early stages of design are characterised by imprecise and incomplete information about the features and properties of targeted product or process. Equipment selection is one of the decisions to be taken in an initial phase of design. Mixing is an example of process where the selection of the equipment is practically realised ‘by hand’. An application of rule-based or object-oriented tools in the selection of mixing equipment encounters many problems. The main reasons are the lack of well-structured knowledge and the great diversity of mixing problems. Case-based reasoning constitutes a good tool to handle the problems of mixing equipment selection. An instance generator for case-based reasoning system is described in this work. A fuzzy neural network system has been used to produce the cases. The following types of the equipment for heat exchange in stirred vessels have been considered: plain jacket, plain jacket with agitation nozzles, plain jacket with spiral baffles, dimple jacket, halfpipe jacket, helical coil, vertical coil and vertical plate coil.