This paper describes our ongoing work on a hybrid approach to process planning, that attempts to combine the best characteristics of both variant and generative process planning while avoiding the worst limitations of each. Our approach uses a database of designs and process plans that are classified using design signatures, graphical structures based on detailed product design attributes that are more meaningful and accurate than GT codes and can be computed automatically from the designs stored in the database. We are developing ways to use design signatures to classify and retrieve "slices" of designs and plans, so that when a process plan is needed for a new design, we will be able to retrieve the plan slices that are most relevant, and combine them and modify them to produce a plan for the new design.
展开▼