Skip to main content
eScholarship
Open Access Publications from the University of California

Deep learning virtual indenter maps nanoscale hardness rapidly and non-destructively, revealing mechanism and enhancing bioinspired design

Abstract

Over evolution, organisms develop complex material structures fit to their environments. Based on these time-tested designs, human-engineered bioinspired structures offer exciting possible materials configurations. However, navigating diverse structure spaces for attaining desired properties remains non-trivial. We focus on the hardest biological tissue in humans, tooth enamel, to examine the structure-property relationship. While typical hardness measurements are time consuming and destructive, we propose that artificial intelligence models can predict properties directly and enable high-throughput, non-destructive characterization. We train a deep image regression neural network as a surrogate model and visualize with gradient ascent and saliency maps to identify structural features contributing most to hardness. This model demonstrates improved spatial resolution and sensitivity compared with experimental hardness maps. Using this rapid hardness testing model, a generative adversarial model, and a genetic algorithm that operates in latent space, allows for guided materials design, yielding proposed designs for bioinspired structures with precisely controlled hardness.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View