ANN prediction of mode I fracture energy in epoxy adhesive joints: Adherend, adhesive, and strain rate effects

Abstract

In this investigation, the mode I fracture behavior of an epoxy adhesive joint has been investigated to probe the combined effects of adherend Young's modulus and thickness, strain rate, and adhesive length. Experimental fracture testing was conducted on double-cantilever beam (DCB) specimens under three various strain rate thresholds, namely, quasi-static (0.0005 s⁻¹), low (0.015 s⁻¹), and intermediate (0.5 s⁻¹). The specimens were constructed with varying adherend materials (i.e., copper, aluminum), thickness (12–20 mm), and adhesive lengths (25–75 mm). The fracture load was measured in each experiment, and the critical strain energy release rate, J_Ci, was calculated via a finite element analysis (FEA) in each case. Results with a 95 % confidence interval showed adherend thickness had a negligible effect within the investigated range (p-value = 0.462). J_Ci was significantly impacted by adhesive length (p-value = 0.009) and two other investigated parameters (p-values = 0.000). The development of artificial neural networks (ANNs) with Levenberg-Marquardt (LM) led to the prediction of J_Ci based on the examined parameters. With a mean absolute percentage error (MAPE) of 8.9 % and a mean squared error (MSE) of 683 J²/m⁴ on unseen test data, the ANN model built in this study was able to predict the J_Ci in epoxy adhesive joints, indicating its potential to produce an accurate prediction for J_Ci in epoxy adhesive joints. This work offers insights for precise fracture behavior prediction under mode I stress conditions as well as some helpful information that can be utilized to optimize adhesive joint design.