Arhore, Edore G.Yasaee, MehdiDayyani, Iman2022-09-202022-09-202022-09-02Arhore EG, Yasaee M, Dayyani I. (2022) Optimisation of convolutional neural network architecture using genetic algorithm for the prediction of adhesively bonded joint strength. Structural and Multidisciplinary Optimization, Issue 65, September 2022, Article number 2561615-147Xhttps://doi.org/10.1007/s00158-022-03359-xhttps://dspace.lib.cranfield.ac.uk/handle/1826/18457The classical method of optimising structures for strength is computationally expensive due to the requirement of performing complex non-linear finite element analysis (FEA). This study aims to optimise an artificial neural network (ANN) architecture to perform the task of predicting the strength of adhesively bonded joints in place of non-linear FEA. A manual multi-objective optimisation was performed to find a suitable ANN architecture design space. Then a genetic algorithm optimisation of the reduced design space was conducted to find an optimum ANN architecture. The generated optimum ANN architecture predicts efficiently the strength of adhesively bonded joints to a high degree of accuracy in comparison with the legacy method using FEA with a 93% savings in computational cost.enAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/adhesive jointsconvolutional neural networkgenetic algorithmcomposite adherendlightweight designArticle