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. 

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. 

Additive manufacturing enables the fabrication of complex designs while minimizing waste, but faces challenges related to defects and process anomalies. This study presents a novel multimodal Retrieval-Augmented Generation-based framework that automates anomaly detection across various Additive Manufacturing processes leveraging retrieved information from literature, including images and descriptive text, rather than training datasets. This framework integrates text and image retrieval from scientific literature and multimodal generation models to perform zero-shot anomaly identification, classification, and explanation generation in a Laser Powder Bed Fusion setting. The proposed framework is evaluated on four L-PBF manufacturing datasets from Oak Ridge National Laboratory, featuring various printer makes, models, and materials. This evaluation demonstrates the framework's adaptability and generalizability across diverse images without requiring additional training. Comparative analysis using Qwen2-VL-2B and GPT-4o-mini as MLLM within the proposed framework highlights that GPT-4o-mini outperforms Qwen2-VL-2B and proportional random baseline in manufacturing anomalies classification. Additionally, the evaluation of the RAG system confirms that incorporating retrieval mechanisms improves average accuracy by 12% by reducing the risk of hallucination and providing additional information. The proposed framework can be continuously updated by integrating emerging research, allowing seamless adaptation to the evolving landscape of AM technologies. This scalable, automated, and zero-shot-capable framework streamlines AM anomaly analysis, enhancing efficiency and accuracy. 

Abstract This paper 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 of 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. 

In this paper, we present a computational investigation into the dynamic behavior of a tunable multi-position metamaterial switch. We examine the dynamical characteristics of the metamaterial switch, which can transition between positions ranging from state 0 to state 5. Each state corresponds to fixed, stable bandgaps, and the switch does not require external stimuli to maintain its properties. By adjusting the position of the switch, we can effectively modify the location of complete bandgaps, allowing for precise control over the propagation of elastic waves. We demonstrate the utility of the proposed metamaterial switch by enabling wave-guiding capabilities and achieving tunable multiplexing across different frequencies. In addition, we expand the analysis by combining multiple unit cells into supercells with varying configurations, enabling further tuning of dispersion characteristics and bandgap properties. The presented design principles can be applied to various applications in elastic wave manipulation and vibration isolation. 

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. 

Abstract Additive manufacturing enables the fabrication of complex designs while minimizing waste, but faces challenges related to defects and process anomalies. This study presents a novel multimodal Retrieval-Augmented Generation-based framework that automates anomaly detection across various Additive Manufacturing processes leveraging retrieved information from literature, including images and descriptive text, rather than training datasets. This framework integrates text and image retrieval from scientific literature and multimodal generation models to perform zero-shot anomaly identification, classification, and explanation generation in a Laser Powder Bed Fusion setting. The proposed framework is evaluated on four L-PBF manufacturing datasets from Oak Ridge National Laboratory, featuring various printer makes, models, and materials. This evaluation demonstrates the framework’s adaptability and generalizability across diverse images without requiring additional training. Comparative analysis using Qwen2-VL-2B and GPT-4o-mini as MLLM within the proposed framework highlights that GPT-4o-mini outperforms Qwen2-VL-2B and proportional random baseline in manufacturing anomalies classification. Additionally, the evaluation of the RAG system confirms that incorporating retrieval mechanisms improves average accuracy by 12% by reducing the risk of hallucination and providing additional information. The proposed framework can be continuously updated by integrating emerging research, allowing seamless adaptation to the evolving landscape of AM technologies. This scalable, automated, and zero-shot-capable framework streamlines AM anomaly analysis, enhancing efficiency and accuracy. 

Reconstructing 3D granular microstructures within volumes of arbitrary geometries from limited 2D image data is crucial for predicting the material properties, as well as performances of structural components accounting for material microstructural effects. We present a novel generative learning framework that enables exascale reconstruction of granular microstructures within complex 3D geometric volumes. Building upon existing transfer learning techniques using pre-trained convolutional neural networks (CNN), we introduce several key innovations to overcome the difficulties inherent in arbitrary geometries. Our framework incorporates periodic boundary conditions using circular padding techniques, ensuring continuity and representativeness of the reconstructed microstructures. We also introduce a novel seamless transition reconstruction (STR) method that creates statistically equivalent transition zones to integrate multiple pre-existing 3D microstructure volumes. Based on STR, we propose a cost-effective strategy for reconstructing microstructures within complex geometric volumes, minimizing computational waste. Validation through numerical experiments using kinetic Monte Carlo simulations demonstrates accurate reproduction of grain statistics, including grain size distributions and morphology. A case study involving the reconstruction of a 4-blade propeller microstructure illustrates the method’s capability to efficiently handle complex geometries. The proposed framework significantly reduces computational demands while maintaining high reconstruction quality, paving the way for scalable microstructure reconstruction in materials design and analysis.