Sutures, the soft collagenous tissue joining interdigitating bony protrusions on the edges of bone plates, play a significant mechanical role in allowing a turtle shell to respond optimally to a range of loading regimes. In this contribution, qualitative and quantitative aspects of the mechanical behaviour of turtle shell suture regions are investigated by means of mathematical modelling. Notable features of the model include: (i) a geometrically realistic three dimensional model for the suture geometry; (ii) taking the hyperelastic, anisotropic and incompressible nature of the suture material into account; and (iii) a novel method for defining the collagen fibre directions within the suture. The model is validated against a physical three point bending test and replicates many of the qualitative and quantitative aspects of the mechanical behaviour. The model is then used to elucidate the effect that sutures have on the shell's mechanical behaviour during a predator attack. It is found that the sutures increase the energy required from a predator during an attack whilst cushioning the brittle bone, and so protecting it from fracture. Additionally, longer bony protrusions increase strain energy absorption but also increase the likelihood of fracture.
We study 2D RVEs based on microstructures inspired by limpet teeth with the objective of efficiently identifying auxetic designs and building surrogates for effective elastic response. The starting point is an unbalanced database; thus, we run a weighted random forest classifier and a neural network classifier to balance it. The resulting feature importances provide an interpretable ranking of 18 geometric and material variables and guide importance-biased Monte Carlo sampling. Random forest and FCNN classifiers are used to prioritize candidates. Dataset rebalancing is achieved by adding newly FEM-confirmed auxetic samples and applying clustering-guided downsampling to the non-auxetic majority. On this final set, a multi-output FCNN regressor predicts nine targets: inclusion volume fractions and minima/means/maxima of Young’s modulus and Poisson’s ratio. Overall, the framework supports rapid, interpretable screening and property prediction for auxetic composite designs while reducing the need for repeated FEM evaluations.