Machine learning/finite element analysis - A collaborative approach for predicting the axial impact response of adhesively bonded joints with unique sandwich composite adherends

Modelling nonlinear shear creep behaviour of a structural adhesive using deep neural networks (DNN)

“…The deep neural networks (DNN) were used to accurately model the nonlinear shear creep behaviour of the structural adhesive. DNN have been successfully adopted in many studies to analyse material properties, and its theoretical background is briefly outlined here, while a fuller explanation can be found in the cited papers [32][33][34][35]. The process of developing the DNN predictive model will also be presented, which includes the use of k-fold cross-validation to tune the hyperparameters.…”

“…This self-learning refers to the inherent ability of the system to acquire knowledge directly from the data without explicit programming, which is also known as machine learning [34]. Deep neural networks (DNN) are a specific type of ANN that consists of multiple layers of interconnected nodes, allowing them to model more complex data relationships and achieve superior performance compared to conventional ANN [35].…”

“…In a DNN model, the layers are typically organised into an input layer, three or more hidden layers, and an output layer. The input layer receives data, which is then transformed by the hidden layers, and the output layer produces a prediction [34,35]. The architecture of the DNN model used in this study is shown in Figure 5, where the input layer consists of three neurons: temperature (T), stress (σ), and time (t), and the output layer predicts the shear creep (ε).…”

“…A single neuron receives inputs, multiplies each input by the corresponding weight, adds a bias, and then passes the sum through an activation function to produce an output. The weights and biases are adjustable parameters learnt during training that determine the impact of the inputs, while the activation function introduces nonlinearity and enables the model to learn complex patterns [32][33][34][35].…”