Artificial neural network for the selection of buildable structural systems

In this study, artificial neural networks have been developed to acquire construction knowledge from past projects to integrate buildability considerations into the preliminary structural design process. Four artificial neural network models are presented. These allow the generation of an expeditious solution for given sets of design and buildability constraints. Once information is entered into the models, a recommendation of which structural scheme to choose is generated instantaneously. Thus, valuable design time is released, allowing designers the opportunity to invest in other equally important design tasks. The information entered into the models consists of site-related information including site access; availability of working space; and speed of erection, and conceptual design information including type of building; number of storeys and gross floor area. The results show that artificial neural networks can be successfully used for the implementation of buildability at the preliminary stage of design.