Search for: All records

Abstract This article presents a novel approach for generating metamaterial designs by leveraging texture information learned from stochastic microstructure samples with exceptional mechanical properties. This eXplainable Artificial Intelligence (XAI)-based approach reduces the reliance on brainstorming and trial-and-error in inspiration-driven design practices. The key research question is whether the texture information extracted from stochastic microstructure samples can be used to design metamaterials with periodic structural patterns that surpass the original stochastic microstructures in mechanical properties. The proposed approach employs a pretrained supervised neural network and applies the Activation Maximization Texture Synthesis (AMTS) method to extract representative textures from high-performance stochastic microstructure samples. These textures serve as building blocks for creating novel periodic metamaterial designs. Using three benchmark cases of stochastic microstructure-inspired periodic metamaterial design, we compare the proposed approach with an earlier XAI design approach based on Gradient-weighted Regression Activation Mapping (Grad-RAM). Unlike the proposed approach, Grad-RAM extracts local microstructure patches directly from the original sample images rather than synthesizing representative textures to generate novel periodic metamaterial designs. Both XAI-based design approaches are evaluated based on the mechanical properties of the resulting designs. The relative merits of both approaches in terms of design performance and the need for human intervention are discussed. 

Climate extremes, such as hurricanes, combined with large-scale integration of environment-sensitive renewables, could exacerbate the risk of widespread power outages. We introduce a coupled climate-energy model for cascading power outages, which comprehensively captures the impacts of climate extremes on renewable generation, and transmission and distribution networks. The model is validated with the 2022 Puerto Rico catastrophic blackout during Hurricane Fiona – a unique system-wide blackout event with complete records of weather-induced outages. The model reveals a resilience pattern that was not captured by the previous models: early failure of certain critical components enhances overall system resilience. Sensitivity analysis on various scenarios of behind-the-meter solar integration demonstrates that lower integration levels (below 45%, including the current level) exhibit minimal impact on system resilience in this event. However, surpassing this critical level without pairing it with energy storage can exacerbate the probability of catastrophic blackouts. 

This work presents a systematic study of the relationship between structural stochasticity and the crush energy absorption capability of lattice structures, with controlled stiffness and weight. We develop a Voronoi tessellation-based approach to generate multiple series of lattice structures with either equal weight or equal stiffness, smoothly transitioning from periodic to stochastic configurations for crush energy absorption analysis. The generated lattice series fall into two categories, originating from periodic honeycomb and diamond lattice structures. A new stochasticity metric is proposed for quantifying the structural stochasticity and is compared with the state-of-the-art stochasticity metrics to ensure a consistent measurement. The crush energy absorption properties are obtained using explicit finite element analysis and we observe similar stochasticity-property trends in simulations using both elastic-plastic and hyperelastic materials. We report a new observation that an intermediate level of stochasticity between periodic and high randomness leads to the best crush energy absorption performance. Our analysis reveals that this optimal performance arises from enhanced activation of deformation hinges, promoting efficient energy absorption.