Machine intelligence continues to rise in popularity as an aid to the design and discovery of novel metamaterials. The properties of metamaterials are essentially controllable via their architectures and until recently, the design process has relied on a combination of trial-and-error and physics-based methods for optimization. These processes can be time-consuming and challenging, especially if the design space for metamaterial optimization is explored thoroughly. Artificial intelligence (AI) and machine learning (ML) can be used to overcome challenges like these as pre-processed massive metamaterial datasets can be used to very accurately train appropriate models. The models can be broad, describing properties, structure, and function at numerous levels of hierarchy, using relevant inputted knowledge. Here, we present a comprehensive review of the literature where state-of-the-art machine intelligence is used for the design, discovery and development of metamaterials. In this review, individual approaches are categorized based on methodology and application. We further present machine intelligence trends over a wide range of metamaterial design problems including: acoustics, photonics, plasmonics, mechanics, and more. Finally, we identify and discuss recent research directions and highlight current gaps in knowledge.

Powder epoxy composites have several advantages for the processing of large composite structures, including low exotherm, viscosity and material cost, as well as the ability to carry out separate melting and curing operations. This work studies the mode I and mixed-mode toughness, as well as the in-plane mechanical properties of unidirectional stitched glass and carbon fibre reinforced powder epoxy composites. The interlaminar fracture toughness is studied in pure mode I by performing Double Cantilever Beam tests and at 25% mode II, 50% mode II and 75% mode II by performing Mixed Mode Bending testing according to the ASTM D5528-13 test standard. The tensile and compressive properties are comparable to that of standard epoxy composites but both the mode I and mixed-mode toughness are shown to be significantly higher than that of other epoxy composites, even when comparing to toughened epoxies. The mixed-mode critical strain energy release rate as a function of the delamination mode ratio is also provided. This paper highlights the potential for powder epoxy composites in the manufacturing of structures where there is a risk of delamination.

This paper considers the effects of claw morphology on the gripping efficiency of arboreal (Varanus varius) and burrowing (Varanus gouldii and Varanus panoptes) lizards. To ensure a purely morphological comparison between the lizards, we circumvent the material effects of claws from different species, by modelling and testing claw replicates of the same material properties. We correlate climbing efficiency to critical morphological features including; claw height (hc), width (wc), length (lc), curvature () and tip angle (γ), which are expressed as ratios to normalise mechanically beneficial claw structures. We find that there is strong correlation between the static grip force Fsg and the claw aspect and the cross-sectional rigidity ratio , and milder correlation (i.e. higher scatter) with the profile rigidity ratio . These correlations are also true for the interlocking grip force Fint over different shaped and sized protuberances, though we note that certain protuberance size-shape couplings are of detriment to the repeatability of Fint. Of the three lizard species, the claws of the arboreal (V. varius) are found to be superior to those of the burrower lizards (V. gouldii and V. panoptes) as a result of the V. varius claws having a smaller aspect, a higher cross-sectional rigidity ratio and a small profile rigidity ratio, which are deemed noteworthy morphological parameters that influence a claw's ability to grip effectively.

Brachyuran crab carapaces are protective, impact-resistant exoskeletons with elaborate material microstructures. Though several research efforts have been made to characterise the physical, material and mechanical properties of the crab carapace, there are no studies detailing how crab morphologies might influence impact resistance. The purpose of this paper is to characterise and compare Brachyuran crab carapace morphologies in relation to their impact properties, using opto-digital, experimental and numerical methods. We find that crab carapaces with both extended carapace arc-lengths and deep carapace grooves lose stiffness rapidly under cyclic impact loading, and fail in a brittle manner. Contrarily, carapaces with smaller arc lengths and shallower, more broadly distributed carapace grooves are more effective in dissipating stresses caused by impact throughout the carapace structure. This allows them to retain stiffness for longer, and influences their failure mode, which is ductile (denting), rather than brittle fracture. The findings in this paper provide new bioinspired approaches for the geometrical designs by which means material failure under cyclic impact can be controlled and manipulated.