Topology Optimization and Machine Learning-Based Parametric Optimization Techniques: A Comparative Study With Physical Validation

Abstract Topology optimization (TO) and Parametric Optimization (PO) are two fundamental structural optimization (SO) techniques. However, the current literature is not clear as to which optimization workflow is better suited for simulating and predicting real-world results, especially in the context of other factors relevant to deciding which workflow to use. The aim of this study is therefore to understand how these two techniques stack up against each other from a variety of perspectives − (1) time taken for optimization, (2) manufacturability, (3) real-life adherence to simulated results, and (4) overall stiffness. Both workflows are evaluated and compared systematically on a cantilever beam and with different volume fractions (VF) of beams − 30%, 50%, and 80%. The results achieved via software simulation for both PO and TO are then validated in a real-world physical setting. The simulated versus physically validated results are compared for all six TO and PO optimized cantilever beams. It was found that TO is faster and shows better stiffness, while PO is more manufacturable and shows better predictability between software-simulated and physically validated results. The conclusions of this study will assist structural designers in their choice of optimization workflow, given their design necessities and constraints.