Date of Award


Document Type


Degree Name

Doctor of Philosophy (PhD)


Construction Management

First Advisor

T. Warren Liao


The investigation of commercial/industrial failures is a vital, but complex task. This paper presents an Intelligent Failure Analysis System (aIFAS). It is a system designed by a failure analyst with the goal of making failure investigation easier. The knowledge base for aIFAS comes from commercial laboratory reports. The methodologies employed represents the experience gained from over five years of development. One goal of aIFAS is to provide a case-based expert system tool to help find answers. Functionality ranges from matching a new case to stored example cases to extracting relational data from the aIFAS knowledge base. This study focuses on two objectives beyond implementation of aIFAS First, a more compact file structure to represent the failure mode/attribute data is explored. Second, five candidate metrics for case matching are compared. Comparisons are accomplished using a parametric analytic engine built into aIFAS. Combinations of features are tested against a single set of fifty cases, as well as, with multiple trials of randomly selected cases. The Relative Time Unit and Performance Score measures are introduced. They offer a semi-quantitative yardstick that introduces both accuracy and speed into the assessment process. A more compact, grouped format for attribute representation gave improved performance. It shows promise as a means to inject fuzzy logic into aIFAS. The City Block and Hamming distance algorithm were the most stable and efficient metrics.