Extraction of Structural System Designs from Topologies via Morphological Analysis and Artificial Intelligence

Structural system design is the process of giving form to a set of interconnected components 1 subjected to loads and design constraints while navigating a complex design space. While safe 2 designs are relatively easy to develop, optimal designs are not. Modern computational optimization 3 approaches employ population based metaheuristic algorithms to overcome challenges with the 4 system design optimization landscape. However, the choice of the initial population, or ground 5 structure, can have an outsized impact on the resulting optimization. This paper presents a new 6 method of generating such ground structures, using a combination of topology optimization (TO) 7 and a novel system extraction algorithm. Since TO generates monolithic structures, rather than 8 systems, its use for structural system design and optimization has been limited. In this paper, truss 9 systems are extracted from topologies through morphological analysis and artificial intelligence 10 techniques. This algorithm, and its assessment, constitutes the key contributions of this paper. The 11 structural systems obtained are compared with ground truth solutions to evaluate the performance 12 of the algorithms. The generated structures are also compared against benchmark designs from the 13 literature. The results indicate that the presented truss generation algorithm produces structures 14 comparable to those generated through metaheuristic optimization, while mitigating the need for 15 assumptions about initial ground structures. 16