Prediction of failure load in flat-joggle-flat co-cured composite joints using artificial neural networks

Abstract

The current research examines the impact of bonding angle, bonding width, and adherend thickness on the failure load of flat-joggle-flat (FJF) co-cured composite joints. The primary goal of this work is to use an artificial neural network (ANN) to predict the failure load at the FJF joint. The experimental data was fed into the network, and the Colab tool was used to design and train the ANN network using a back-propagation algorithm. Experimental results revealed that, 8 mm to 12 mm adherend thickness, 25 mm adherend width, and a 10° to 15° bonding angle, gave maximum failure load. The ANN model estimated the predictive failure load with acceptable error. The results obtained from ANN, R2= 0.9803 for training andR2 = 0.9242 for testing the data, are within the acceptable error, so the experimental and ANN results are consistent and in good agreement.