Methods and an implemented system for automatic generation of process plans from the CAD boundary representation of a part is presented. Investigating the issues in the development of a system with this capability is very useful, because such a system integrates the design and manufacturing processes and enables construction of plans to make the part with out the need for manual interpretation of the shape of the part or an expert process planner. In order to achieve this task, we simultaneously address two problems. The first problem is the machine understanding of the shape of a part from its low level boundary representation, and the second problem is developing a plan based on this semantic information. The architecture of our system at the highest level consists of a solid modeler, a shape description system, an automatic process planner, and the interfaces between them. Techniques like cooperative reasoning, and combining geometric evidences are used in a graph-based hypothesis generate-eliminate approach to automatically extract the shape primitives of a designed part and to determine the relations between these shape primitives from the boundary representation CAD data, and thus produce the higher level semantic information. A case-based planner (also developed at Purdue’s Knowledge-Based Systems Lab) uses the information produced by the shape description system to construct a conceptual plan for machining the part. Examples illustrate the details of the reasoning performed by our system, and illuminate the advantages our system offers over the existing systems. The shape description system, the process planner and the interfaces are developed in LISP.
ASJC Scopus subject areas