ABSTRACT

This paper describes the development of an expert tool for vehicle design that assists the designer in avoiding bad design decisions, which may cause corrosion problems during the life of the vehicle. The tool is an autonomous agent installed as part of designer's CAD/CAE system. It uses an AI Expert Production System containing Rules in its Knowledge Base and an Inference Engine that compares these stored Rules with the information (Facts) provided by the designer and CAD/CAE software. An important enhancement in this system not found in most Expert Systems is an Uncertainty Processor. The Uncertainty Processor calculates the estimated uncertainty (and its precision) associated with the delivered proposed conclusion. This is accomplished by calculating the cumulative values determined by propagating and combining the estimated error and precision found in each and every Rule and Fact used in the chaining logic required in arriving at the proposed final conclusion. Also included is a Knowledge Acquisition Facility used by corrosion and vehicle design experts to load supporting knowledge and Rules into the Knowledge Base, and an on-demand Explanation Facility to detail the logic used by the system to arrive at the conclusion.

INTRODUCTION

Corrosion resistance has historically been a secondary concern during preliminary and detailed design of new vehicles. The primary weapon used for corrosion control during the design process has been material selection, coatings, platting and insulators. Often, even after implementing these first lines of defenses, vehicle detailed geometry, incompatible adjacent materials and harsh environment/usage can cause corrosion due to galvanic, crevice, poultice, fretting and other mechanisms. The U. S. Army TACOM recognized this problem within the automotive industry and contracted GCAS Incorporated to develop expert design tools to augment existing design CAD/CAE software. This paper describes the design and development of this Corrosion Expert System, CES.

This content is only available via PDF.
You can access this article if you purchase or spend a download.