Design optimisation of braided composite beams for lightweight rail structures using machine learning methods

Braided composites have seen substantial industrial uptake for structural applications in the past decade. The dependence of their properties on braid angle provides opportunities lightweighting through structure-specific optimisation. This paper presents an integrated approach, combining finite element (FE) simulations and a genetic algorithm (GA) to optimise braided beam structures spaceframe chassis rail vehicle. number layers each were considered as design variables. A set 200 combinations these variables identified using sampling strategy FE simulations. results utilised develop surrogate model programming (GP) correlate with mass FE-predicted displacements under standard loads. was then used GA minimise without compromising mechanical performance. optimised rendered approximately 15.7% weight saving compared benchmark design.