Recent Advances in AI Based Synthesis of Structural Systems

The present paper describes a general framework for an AI based approach for developing near-optimal designs of load bearing truss and frame structures. The proposed framework is an adaptation of a recently proposed model for generic problem solving system. The approach is based upon a systematic decomposition of the problem space, and an application of design heuristics to incrementally generate an optimal structural topology to account for the applied loads. The principal shortcomings of a heuristic decomposition approach are underscored, and more rational quasi-procedural decomposition methods are proposed.