Machine learning approach for analysing and predicting the modulus response of the structural epoxy adhesive at elevated temperatures

Abstract

For bonded Fibre Reinforced Polymer (FRP) strengthening systems in civil engineering projects, the adhesive joint performance is a key factor in the effectiveness of the strengthening; however, it is known that the material properties of structural epoxy adhesives change with temperature. This present paper examines the implied relationship between the curing regimes and the storage modulus response of the adhesive using a Machine Learning (ML) approach.A dataset containing 157 experimental data collected from the scientific papers and academic theses was used for training and testing an Artificial Neural Network (ANN) model. The sensitivity analysis reveals that the curing conditions have a significant effect on the glass transition temperatures (Tg) of the adhesive, and consequently on the storage modulus response at elevated temperatures. Curing at an extremely high temperature for a long time does not, however, guarantee a better thermal performance. For the studied adhesive, curing in a warm (≥ 45 °C) and dry (near 0 % RH) environment for 21 days is recommended for practical applications. A software with a Graphical User Interface (GUI) was established, which can predict the storage modulus response of the adhesive, plot the corresponding response curve, and estimate the optimum curing condition.

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

“…Engineers have been using ML techniques to explore the complex behaviour of structural materials, as they can extract intricate relationships between inputs and outputs and summarise the implied nonlinear laws. Unified ML models that generate new predictions without extensive experimentation can be further developed [23][24][25][26]. Despite the high predictive accuracy of ML models, they are often seen as black boxes that lack physical explanations.…”