Disordered Mechanical Metamaterials

Mechanical metamaterials, or architechted materials, are a class of artificial materials engineered to have exceptional mechanical properties that are difficult to find in conventional materials. Often inspired by biological systems, mechanical metamaterials are typically designed with an internal structure composed of multiple elements arranged in periodic patterns. The ordered geometries employed in mechanical metamaterials contrast with the disordered structures encountered in biological systems, formed through self-assembly in response to environmental pressures. In this talk, I will argue that there is a value in considering disorder in the design of mechanical metamaterials and discuss the emergence of novel features induced by disorder. I will then present a computational method for the automatic design of disordered mechanical metamaterial actuators that combines a reinforced Monte Carlo method with discrete element simulations. 3D printing of selected mechanical metamaterial actuators shows that the machine-generated structures can reach high efficiency, exceeding human-designed structures. I will also show that it is possible to design efficient actuators by training a deep neural network which is then able to predict the efficiency from the image of a structure and identify its functional regions.