Pultruded GFRP Translaminar Fracture Toughness Evaluation Using a Hybrid Approach of Size-Effect and Machine Learning

The translaminar fracture toughness of pultruded Glass Fiber Reinforced Polymers (GFRP) is influenced by several factors, including the type of matrix, fiber, the fiber volume ratio, the proportion of plies at each angle and the size of the test specimens. Conventional test approaches tend to overestimate the fracture toughness of GFRP composites due to imperfect specimen fabrication. This paper introduces an anisotropic two-dimensional adaptation of phase field theory to evaluate the translaminar fracture toughness of pultruded GFRP in conjunction with the size effect. It is found that the fracture toughness is linearly correlated with the fiber volume ratio when the proportion of 0° plies ranges from 30% to 60%. Additionally, it was found that at the same fiber volume ratio, the fracture toughness increases with the increase of 0° plies by 5%. Five machine learning algorithms, i.e., BP, RF, SVR, GA-BP, and PSO-BP, are employed to predict the fracture toughness of pultruded GFRP laminates. It has been found that the PSO-BP algorithm is robust in predicting the fracture toughness of pultruded GFRP laminates, with the correlation coefficient R2 being 0.987 and 0.994 in the test and training set, respectively and the prediction error in fracture toughness being less than 4 kJ/m2. The trained machine learning method can accurately predict GFRP fracture toughness. When the proportion of 0° plies is larger than 50%, the increase in the fracture toughness is approximately twice that of those taking up a proportion of 30–50%. Fracture toughness predictions are provided using the developed machine learning model for pultruded GFRP profiles, which are commonly used in infrastructure construction with fiber volume ratios range of 60–70% and 0° layup percentages of 60–75%.