This project will engage with Artificial Intelligence (AI) methods recently developed for structural engineering applications, as is proving to be an efficient alternative approach to classic modelling techniques, and attempt to reduce the percentage of uncertainty of the results as well as saving significant human time and effort spent in experiments.
This study will focus on finding an efficient scheme for the topology optimisation in order to create long-span steel members (beams) with high buckling strength than the one created by just using empirical approaches in conjunction with machine learning for developing the most optimum floor-plate layouts of given geometric and loading characteristics. Buckling optimisation will be studied for first time at this scale using advanced algorithms of Altair’s Hyperworks software tools. Together with machine (supervised) learning Neural Network algorithms (via regression analyses), the limitations of classical prediction models will be demonstrated.
This PhD is part of an interdisciplinary research programme which attempts to tackle the global challenge of environmental change and provides solutions for Civil Engineers and Architects especially when design large scale structures. It is anticipated that the proposed methodology will be also adoptable to other construction systems and projects.
This studentship is funded by EPSRC iCASE with additional support from industrial collaborator SC4 UK Ltd. Funding covers the cost of tuition fees as well as maintenance grant (£18,009 in Session 2019/20.