A NEURAL-NETWORK APPROACH FOR DATUM SELECTION IN COMPUTER-AIDED PROCESS PLANNING

The goal of process planning is to convert design specifications into manufacturing instructions to make products within the specifications at the lowest cost. Therefore, for a computer-aided process planning s ystem (CAPP) to generate a feasible and economical process plan, the t olerance information from design and manufacturing processes must be c arefully studied. The geometric tolerances are usually specified in de sign only when higher accuracy of a feature (such as flatness, roundne ss, etc.) or a relationship (such as parallelism, perpendicularity, et c.) is required. For the relationships with dimensional tolerances or geometric tolerances with specified design datum(s), the selection of manufacturing datum and setup in process planning plays a very importa nt role to make parts precisely and economically. This paper presents a neural network approach for CAPP to automatically select manufacturi ng datums for rotational parts on the basis of the shape of the parts and tolerance constraints. A back-propagation algorithm is used and so me experiments are conducted. The results are analyzed and further res earch is proposed.