A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods: Deep neuron networks and genetic programming

The aerospace, automotive and marine industries have witnessed a rapid increase of using adhesive bonded joints due to their advantages in joining dissimilar and/or new engineering materials. Joint strength is the key property evaluating capability joint. In this paper, developments black-box grey-box machine learning (ML) models are presented allow accurate predictions failure load single lap by considering mix continuous discrete design (geometry material) variables. Firstly, loads 300 joint samples with different geometry/material parameters calculated FE generate data set which accuracy validated experimental results. Then, deep neuron network (black-box) genetic programming (grey-box) model developed for accurately predicting Based on both ML models, case study conducted explore relationships between specific variables overall mechanical performances joint, optimal designs structure material can be obtained.