A hierarchical hybrid expert system for steel welding materials selection system

Abstract

This paper outlines the development of a web-based expert system, steel welding materials selection expert system. The expert system inference engine employs all case-based reasoning (CBR), rule-based reasoning (RBR), and k-mean clustering method to generate a hierarchical hybrid recommendation list for cross validation. Moreover, this inference engine was designed to support a hierarchical multi-attribute structure. Unlike the traditional ‘flat’ attribute structure, this hierarchical multi-attribute structure allows experts and user to weigh the attributes dynamically and friendly.