Pragmatic generative optimization of novel structural lattice metamaterials with machine learning

Metamaterials, otherwise known as architected or programmable materials, enable designers to tailor mesoscale topology and shape to achieve unique material properties that are not present in nature. Additionally, with the recent proliferation of additive manufacturing tools across industrial sectors, the ability to readily fabricate geometrically complex metamaterials is now possible. However, in many high-performance applications involving complex multi-physics interactions, design of novel lattice metamaterials is still difficult. Design is primarily guided by human intuition or gradient optimization for simple problems. In this work, we show how machine learning guides discovery of new unit cells that are Pareto optimal for multiple competing objectives; specifically, maximizing elastic stiffness during static loading and minimizing wave speed through the metamaterial during an impact event. Additionally, we show that our artificial intelligence approach works with relatively few (3500) simulation calls. [Display omitted] •The geometry of metamaterials can be automatically designed to maximize their performance against multiple objectives.•The pragmatic approach combines a genetic algorithm with a convolutional neural network to efficiently invent manufacturable architectures.•The convolutional neural network performs best when the input is a 3x3 tiled lattice rather than a single unit cell.•Active learning enables a significant reduction in the number of example designs needed to train the convolutional neural network.