Development of surrogate predictive models for the nonlinear elasto-plastic response of medium density fibreboard-based sandwich structures

Medium-density fibreboard (MDF) belongs to a class of engineered wood products facilitating efficient use of wood wastes. For this class of materials, the development of predictive models is crucial for the simulation of their responses under mechanical loads. In this study, samples of sandwich structures based on MDF as the skins and a mushroom-based foam as the core are fabricated and tested under edgewise compression tests. Results from the tests support the idea that increasing the thickness of the skins strengthens the response of the sandwich structure against buckling failure, but also revealed that thicker skins are susceptible to complex failure modes. Towards data-driven constitutive modelling of the nonlinear elastic-plastic response of this bio-based structure, predictive models premised on feedforward backpropagation neural network (FFNN), cascade-forward backpropagation neural network (CFNN), and generalized regression neural network (GRNN) were developed. Performance of the models was assessed via error criteria that include the coefficient of determination (R2), root mean squared error (RMSE) and mean absolute error (MAE). Results from the models indicate that CFNN with 15 hidden neurons under the Levenberg-Marquardt backpropagation training algorithm outperformed FFNN and GRNN models, with R2=1.0, RMSE=0.0030 and MAE=0.0019.