A machine learning assisted preliminary design methodology for bolted composite joints in large structures

Abstract

Damage initiation hotspots around features, such as bolts and ply drops, must be investigated during the preliminary design phase of large composite structures, such as composite airframes. A global-local modelling approach is commonly employed to perform this investigation, whereby a global low-fidelity model is used to drive high-fidelity local models around the features of interest. However, this methodology is slow, repetitive and expert-dependent. In this investigation, we address these issues by applying machine learning techniques to this global-local modelling framework and demonstrate the time-saving benefit when predicting damage initiation of bolted composite joints. Feature engineering of model inputs and outputs, and appropriate customization of machine learning methods enables damage initiation prediction. Special consideration is given to the boundary conditions that must be varied to simulate the response of the bolted composite joints. Results show over three orders of magnitude time-saving benefit and satisfactory accuracy of the proposed methodology. This indicates its potential to be developed further into a rapid design and optimisation tool.