An integration of neural network and rule-based systems for design and planning of mechanical assemblies

A case associative assembly planning system (CAAPS), which integrates neural computing techniques and rule-based systems has been developed. The neural network computing captures the designer´s design concept and self-organizes similar experienced designs. The CBAPM (CLIPS-based assembly planning module), a component of CAAPS, generates a task-level assembly plan automatically. The design concept is expressed by a standard pattern format representing components´ 3D geometry. A feature-based model translates the conceptual design into a preliminary boundary representation (B-rep). Based on a refinement of the B-rep assembly representation, assembly plans are generated for practical use in a single-robot assembly workcell. A feasible assembly plan that minimizes tool changes and subassembly reorientations is generated from the system. The CBCAPM presented draws input relationships directly from the conceptual design and the geometry of the assembly. At all stages of the design process the designer can consult the design cluster memory and plan cluster memory to see what “experience” knows of similar assemblies. Efficient use of prior experiences is emphasized