CCE Theses and Dissertations

Date of Award


Document Type


Degree Name

Doctor of Philosophy (PhD)


College of Computing and Engineering


Greg Simco

Committee Member

Lee J. Leitner

Committee Member

William L. Hafner


The lack of knowledge and understanding of diagnostic aircraft propulsion systems causes inappropriate problem diagnosis. Because of increasing complexity, technicians are incapable of performing the necessary tasks in accordance with standard regulations. More sophisticated systems are needed today to "assist" the user technician in decision-making. This work provided a study of rule-based and frame-based expert system techniques to determine the most appropriate solution in the domain of complex diagnosis using large amounts of deterministic data. The study produced a framework that facilitates the diagnosing of faults on aircraft engines, thus reducing the burden on the aircraft mechanic regardless of experience level.

An intelligent system, the Virtually Automated Maintenance Analysis System (V AMAS), was created as a test model. It was used to compare the relative efficiency of the different expert systems techniques and the effectiveness of expert systems. One aviation malfunction problem was identified. Information collected for the Main Ignition Malfunction was developed into question sets and coded. Six specific subsets of problems were addressed.

This research compared the rule-based and frame-based knowledge representation techniques using a set of evaluation factors: computational efficiency, correctness, expressiveness, and consistency. From the analysis it was concluded that the frame based knowledge representation technique ranked higher than the rule-based representation, and is suitable for use with an expert system to represent an aircraft propulsion system 's deterministic data.

Files over 10MB may be slow to open. For best results, right-click and select "Save as..."

Share Feedback