Inference of service operations in a serviceability design expert system

This paper describes a method to infer service operations of a mechanical system based on its candidate design. The overall research goal is to develop a methodology and tool to deploy serviceability in the early stages of life-cycle design. Serviceability is an important life-cycle issue, but is often not considered as thoroughly as manufacturability, assembly, etc. Our graphics-based computer tool employs the concept of service mode analysis (SMA) to assess the impact of component relationships on life-cycle service costs. An AI program infers required repair labor actions from the design description, analyses life-cycle service costs and assesses qualitative serviceability. The tool also provides comments and suggestions for design improvements.