Nick Vlassis

<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:media="http://search.yahoo.com/mrss/"
	
	>

<channel>
	<title>Nick Vlassis</title>
	<link>https://nickvlassis.com</link>
	<description>Nick Vlassis</description>
	<pubDate>Sun, 04 Jan 2026 14:55:11 +0000</pubDate>
	<generator>https://nickvlassis.com</generator>
	<language>en</language>
	
		
	<item>
		<title>Index</title>
				
		<link>https://nickvlassis.com/Index</link>

		<pubDate>Tue, 24 Jan 2023 16:19:52 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Index</guid>

		<description></description>
		
	</item>
		
		
	<item>
		<title>Mobile header</title>
				
		<link>https://nickvlassis.com/Mobile-header</link>

		<pubDate>Tue, 24 Jan 2023 16:19:52 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Mobile-header</guid>

		<description>Nick N. Vlassis

mech[Ai]

Computational Mechanics &#38;amp; Artificial Intelligence Lab 
Nick Napoleon Vlassis is an Assistant Professor in the Department of Mechanical &#38;amp; Aerospace Engineering at Rutgers University.

Home
About
PublicationsGoogle Scholar
Hiring
News FeedEmail&#38;nbsp;</description>
		
	</item>
		
		
	<item>
		<title>‎ </title>
				
		<link>https://nickvlassis.com/36188078</link>

		<pubDate>Wed, 22 May 2024 14:56:08 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/36188078</guid>

		<description>
	News Feed


	New Publication:&#38;nbsp;A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural LanguageJanuary 8, 2025


	Our paper "A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language" has been accepted in Computer Methods in Applied Mechanics and Engineering (CMAME). This work presents a novel framework that integrates LLMs and DDPMs to enable intuitive, natural language-driven microstructure design.

Read more here:&#38;nbsp;https://doi.org/10.1016/j.cma.2025.117742


	------------------------------------------------------------


	New Publication: Synthesizing Realistic Sand Assemblies with Denoising Diffusion
August 14, 2024

	We are pleased to announce the acceptance and publication of our latest paper titled "Synthesizing Realistic Sand Assemblies with Denoising Diffusion in Latent Space" in the International Journal for Numerical and Analytical Methods in Geomechanics.

Authors: Nikolaos N. Vlassis, WaiChing Sun, Khalid A. Alshibli, Richard A. RegueiroAccess the paper here: http://doi.org/10.1002/nag.3818

This paper presents a novel approach for generating realistic sand grains using a denoising diffusion algorithm applied to point cloud data. The study also includes an open-source repository with synthetic sand grains and real synchrotron microcomputed tomography (SMT) scans https://doi.org/10.17632/fh8h4859nh.1.

	
------------------------------------------------------------

	Special Issue Launch: "Machine Learning in Multi-scale Modeling" in Applied Sciences MDPI - Call for Papers
May 22, 2024
	Dear Colleagues,We are excited to announce the launch of a peer-reviewed Special Issue on "Machine Learning in Multi-scale Modeling" for engineering and materials science. This Special Issue is part of the "Computing and Artificial Intelligence" section of Applied Sciences MDPI.We invite you to submit original, high-quality research papers by 20 October 2024 on the following topics:• Physics-informed ML for constitutive modeling in multi-scale structural and material systems• The use of artificial neural networks (ANNs) to predict effective material properties• Graph- and manifold-learning techniques in computational solid mechanics and material design• Supervised and unsupervised ANN methods, including reduced-order simulations in computational mechanics• The application of ANNs and ML-based optimization in the design ofmetamaterials relating to 3D-printing technologies• Generative AI and deep learning-aided techniques for the multi-scale modeling and inverse design of materials and structural systems, including multiphysics composites and porous metamaterials• Model-free approaches in computational mechanics• Causal discovery for interpretable modeling• Data-driven methods for solving partial differential equations (PDEs).Yousef Heider (Institut für Baumechanik und Numerische Mechanik (IBNM), Leibniz Universität Hannover)Nick Vlassis (Rutgers University)Guest Editors
https://www.mdpi.com/journal/applsci/special_issues/NQT1D69Z48
------------------------------------------------------------


</description>
		
	</item>
		
		
	<item>
		<title>ID3EA DEMO DOWNLOAD</title>
				
		<link>https://nickvlassis.com/ID3EA-DEMO-DOWNLOAD</link>

		<pubDate>Wed, 05 Nov 2025 18:01:35 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/ID3EA-DEMO-DOWNLOAD</guid>

		<description>
	ID3EA DEMO DOWNLOAD


	ID3EA: Applied Artificial Intelligence for Engineering Mechanics ShowcaseNovember 5, 2025


	Download the interactive demo:

https://drive.google.com/file/d/1thAaYaXC8S3Zm9YMJqdsAsBBy5iUInnB/view?usp=drive_link


	------------------------------------------------------------


</description>
		
	</item>
		
		
	<item>
		<title>Teaching</title>
				
		<link>https://nickvlassis.com/Teaching</link>

		<pubDate>Sun, 04 Jan 2026 14:45:41 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Teaching</guid>

		<description>
	Teaching
	

Course Syllabi taught at Rutgers

Click the links below to access the syllabi

16:650:550: Mechanics of Materials (Graduate)16:650:606: Applied Deep Learning for Engineering Mechanics&#38;nbsp;14:650:291: Mechanics of Materials (Undergraduate)


 </description>
		
	</item>
		
		
	<item>
		<title>Mech Mat Grad Syllabus</title>
				
		<link>https://nickvlassis.com/Mech-Mat-Grad-Syllabus</link>

		<pubDate>Sun, 04 Jan 2026 14:55:11 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Mech-Mat-Grad-Syllabus</guid>

		<description>16:650:550 Mechanics of Materials - Course Syllabus

&#38;nbsp;
Lectures:&#38;nbsp; Monday and Wednesday, 7:30 PM – 8:50 PM, Hill Center 009

 
	Pre-requisite: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;

Instructor: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;

Office: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;

Phone: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;&#38;nbsp;

Email: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;
 &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;&#38;nbsp;
Website: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;

Office Hours: &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp; &#38;nbsp;
	14:650:291 Mechanics of Materials

Nikolaos N. Vlassis, Assistant Professor

ENG A-200

848-445-5517

&#38;nbsp;nick.vlassis@rutgers.edu

https://canvas.rutgers.edu

&#38;nbsp;Wednesdays 2:00-4:00 PM or by appointment, A200


Recommended Textbooks: 

Arthur P. Boresi, Richard J. Schmidt, Advanced Mechanics of Materials, 6th Edition, Wiley, 2002

Ansel C. Ugural, Saul K. Fenster, Advanced Mechanics of Materials and Applied Elasticity, Prentice Hall, 2011 

W. Michael Lai, David Rubin, Erhard Krempl, Introduction to Continuum Mechanics, Elsevier, 2010


Course Outline: 12 Weeks of Lectures + 10 HWs + 1 Midterm + Final Exam


Method of Evaluation:

Homework &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;50%

In-class Midterm &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;20%&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; 

In-class Final Exam &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp;30%&#38;nbsp; 

 
Topics covered: 

Fundamentals (stress and strain) 

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Definition of stress and the tensorial indicial notation 

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Stress transformation, principal stresses, maximum shear stress, and invariants

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Mohr’s circle

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Definition of deformation and strain

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Summary of equilibrium, kinematic, and constitutive equations, and compatibility.

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Elastic constitutive law: anisotropic, orthotropic, and isotropic

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Thermal stresses, thermal strains, and other types of eigenstrains 

Applied Problems

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Boundary value problems – governing equations and boundary conditions

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Plane stress and plane strain problems 

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; The Airy stress function

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Beam theory (tension, torsion and bending)

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Other common BVP applications

 Extensions

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Energy principles

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Failure theories

· &#38;nbsp;&#38;nbsp;&#38;nbsp;&#38;nbsp; Inelastic materials and plasticity


 </description>
		
	</item>
		
		
	<item>
		<title>Denoising diffusion models for inverse design of inflatable structures with programmable deformations</title>
				
		<link>https://nickvlassis.com/Denoising-diffusion-models-for-inverse-design-of-inflatable</link>

		<pubDate>Tue, 24 Sep 2024 20:04:29 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Denoising-diffusion-models-for-inverse-design-of-inflatable</guid>

		<description>
	Denoising diffusion models for inverse design of inflatable structures with programmable deformationsSara Karimi, Nikolaos N. Vlassis,
https://arxiv.org/abs/2508.13097

	Programmable structures are systems whose undeformed geometries and material property distributions are deliberately designed to achieve prescribed deformed configurations under specific loading conditions. Inflatable structures are a prominent example, using internal pressurization to realize large, nonlinear deformations in applications ranging from soft robotics and deployable aerospace systems to biomedical devices and adaptive architecture. We present a generative design framework based on denoising diffusion probabilistic models (DDPMs) for the inverse design of elastic structures undergoing large, nonlinear deformations under pressure-driven actuation. The method formulates the inverse design as a conditional generation task, using geometric descriptors of target deformed states as inputs and outputting image-based representations of the undeformed configuration. Representing these configurations as simple images is achieved by establishing a pre- and postprocessing pipeline that involves a fixed image processing, simulation setup, and descriptor extraction methods. Numerical experiments with scalar and higher-dimensional descriptors show that the framework can quickly produce diverse undeformed configurations that achieve the desired deformations when inflated, enabling parallel exploration of viable design candidates while accommodating complex constraints.

Read more →


&#60;img width="766" height="710" width_o="766" height_o="710" data-src="https://freight.cargo.site/t/original/i/c4aabc7ce9be9197abdd240b8fe3499c7df673f5ee796862f091fe30194331dd/balloon-ezgif.com-optimize.gif" data-mid="237767628" border="0" data-scale="48" src="https://freight.cargo.site/w/766/i/c4aabc7ce9be9197abdd240b8fe3499c7df673f5ee796862f091fe30194331dd/balloon-ezgif.com-optimize.gif" /&#62;
&#60;img width="2294" height="464" width_o="2294" height_o="464" data-src="https://freight.cargo.site/t/original/i/e0339df97ccaa7929769f23a3dccb32d76954a93883047d7883dd5333ff25ea5/Screenshot-2025-09-01-at-2.37.53PM.png" data-mid="237691490" border="0"  src="https://freight.cargo.site/w/1000/i/e0339df97ccaa7929769f23a3dccb32d76954a93883047d7883dd5333ff25ea5/Screenshot-2025-09-01-at-2.37.53PM.png" /&#62;&#60;img width="2258" height="424" width_o="2258" height_o="424" data-src="https://freight.cargo.site/t/original/i/e29ea468b3e128182b9da3b33fb891d8b7b6be00d648bb177666da98b56e4a87/Screenshot-2025-09-01-at-2.38.06PM.png" data-mid="237691489" border="0"  src="https://freight.cargo.site/w/1000/i/e29ea468b3e128182b9da3b33fb891d8b7b6be00d648bb177666da98b56e4a87/Screenshot-2025-09-01-at-2.38.06PM.png" /&#62;&#60;img width="2268" height="1092" width_o="2268" height_o="1092" data-src="https://freight.cargo.site/t/original/i/3322e070d96efa1b79cf0e6291b929cc882ca8eeb2b51fbd05e5837ad117f7a2/Screenshot-2025-09-01-at-2.37.24PM.png" data-mid="237691487" border="0"  src="https://freight.cargo.site/w/1000/i/3322e070d96efa1b79cf0e6291b929cc882ca8eeb2b51fbd05e5837ad117f7a2/Screenshot-2025-09-01-at-2.37.24PM.png" /&#62;&#60;img width="2161" height="939" width_o="2161" height_o="939" data-src="https://freight.cargo.site/t/original/i/8d079d1757d247c495b12817e2eb6fb7cc1bf7141dc8c044117b6bbbc6c51878/Screenshot-2025-09-01-at-2.38.44PM.png" data-mid="237691488" border="0"  src="https://freight.cargo.site/w/1000/i/8d079d1757d247c495b12817e2eb6fb7cc1bf7141dc8c044117b6bbbc6c51878/Screenshot-2025-09-01-at-2.38.44PM.png" /&#62;</description>
		
	</item>
		
		
	<item>
		<title>A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language</title>
				
		<link>https://nickvlassis.com/A-Large-Language-Model-and-Denoising-Diffusion-Framework-for-Targeted</link>

		<pubDate>Mon, 01 Sep 2025 12:32:02 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/A-Large-Language-Model-and-Denoising-Diffusion-Framework-for-Targeted</guid>

		<description>
	A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural LanguageNikita Kartashov, Nikolaos N. Vlassis,
https://doi.org/10.1016/j.cma.2025.117742

	Microstructure plays a critical role in determining the macroscopic properties of materials, with applications spanning alloy design, MEMS devices, and tissue engineering, among many others. Computational frameworks have been developed to capture the complex relationship between microstructure and material behavior. However, despite these advancements, the steep learning curve associated with domain-specific knowledge and complex algorithms restricts the broader application of these tools. To lower this barrier, we propose a framework that integrates Natural Language Processing (NLP), Large Language Models (LLMs), and Denoising Diffusion Probabilistic Models (DDPMs) to enable microstructure design using intuitive natural language commands. Our framework employs contextual data augmentation, driven by a pretrained LLM, to generate and expand a diverse dataset of microstructure descriptors. A retrained NER model extracts relevant microstructure descriptors from user-provided natural language inputs, which are then used by the DDPM to generate microstructures with targeted mechanical properties and topological features. The NLP and DDPM components of the framework are modular, allowing for separate training and validation, which ensures flexibility in adapting the framework to different datasets and use cases. A surrogate model system is employed to rank and filter generated samples based on their alignment with target properties. Demonstrated on a database of nonlinear hyperelastic microstructures, this framework serves as a prototype for accessible inverse design of microstructures, starting from intuitive natural language commands.

Read more →


&#60;img width="1744" height="752" width_o="1744" height_o="752" data-src="https://freight.cargo.site/t/original/i/36d43d8c22c0627ef189bb2c9f1e4b5ad0b61d285067d93c3e5497d591fd7fcf/Sep-24-2024-16-20-02.gif" data-mid="237691352" border="0" data-scale="97" src="https://freight.cargo.site/w/1000/i/36d43d8c22c0627ef189bb2c9f1e4b5ad0b61d285067d93c3e5497d591fd7fcf/Sep-24-2024-16-20-02.gif" /&#62;
&#60;img width="936" height="746" width_o="936" height_o="746" data-src="https://freight.cargo.site/t/original/i/a6c41bb7dc42887e8775390715da6649292a6ccba283c72c1530f735cf4a8538/Sep-24-2024-16-23-38.gif" data-mid="237691353" border="0" data-scale="54" src="https://freight.cargo.site/w/936/i/a6c41bb7dc42887e8775390715da6649292a6ccba283c72c1530f735cf4a8538/Sep-24-2024-16-23-38.gif" /&#62;&#60;img width="428" height="674" width_o="428" height_o="674" data-src="https://freight.cargo.site/t/original/i/fc6926d8ddc4fb24a2e123093d253166c3bfe0c34930d68024d68d370825e4ae/Sep-24-2024-16-32-10.gif" data-mid="237691354" border="0" data-scale="29" src="https://freight.cargo.site/w/428/i/fc6926d8ddc4fb24a2e123093d253166c3bfe0c34930d68024d68d370825e4ae/Sep-24-2024-16-32-10.gif" /&#62;&#60;img width="1919" height="942" width_o="1919" height_o="942" data-src="https://freight.cargo.site/t/original/i/587ae56aa8987d9386fd1b6bdf5b121abf7ad8171cfacc880daa752e4264f45b/ezgif.com-crop.gif" data-mid="237691351" border="0" data-scale="64" src="https://freight.cargo.site/w/1000/i/587ae56aa8987d9386fd1b6bdf5b121abf7ad8171cfacc880daa752e4264f45b/ezgif.com-crop.gif" /&#62;</description>
		
	</item>
		
		
	<item>
		<title>Synthesizing realistic sand assemblies with denoising diffusion in latent space</title>
				
		<link>https://nickvlassis.com/Synthesizing-realistic-sand-assemblies-with-denoising-diffusion-in</link>

		<pubDate>Sat, 21 Oct 2023 20:19:39 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Synthesizing-realistic-sand-assemblies-with-denoising-diffusion-in</guid>

		<description>
	Synthesizing realistic sand assemblies with denoising diffusion in latent space
Vlassis, Sun, Alshibli, Regueiro, Synthesizing realistic sand assemblieswith denoising diffusion in latent space. Int J Numer Anal Methods. 2024;1-24. https://doi.org/10.1002/nag.381

	The shapes and morphological features of grains in sand assemblies have far-reaching implications in many engineering applications, such as geotechnical engineering, computer animations, petroleum engineering, and concentrated solar power. Yet, our understanding of the influence of grain geometries on macroscopic response is often only qualitative, due to the limited availability of high-quality 3D grain geometry data. In this paper, we introduce a denoising diffusion algorithm that uses a set of point clouds collected from the surface of individual sand grains to generate grains in the latent space. By employing a point cloud autoencoder, the three-dimensional point cloud structures of sand grains are first encoded into a lower-dimensional latent space. A generative denoising diffusion probabilistic model is trained to produce synthetic sand that maximizes the log-likelihood of the generated samples belonging to the original data distribution measured by a Kullback-Leibler divergence. Numerical experiments suggest that the proposed method is capable of generating realistic grains with morphology, shapes and sizes consistent with the training data inferred from an F50 sand database. We then use a rigid contact dynamic simulator to pour the synthetic sand in a confined volume to form granular assemblies in a static equilibrium state with targeted distribution properties. To ensure third-party validation, 50,000 synthetic sand grains and the 1,542 real synchrotron microcomputed tomography (SMT) scans of the F50 sand, as well as the granular assemblies composed of synthetic sand grains are made available in an open-source repository.

Read more →


&#60;img width="1800" height="2400" width_o="1800" height_o="2400" data-src="https://freight.cargo.site/t/original/i/0eda9739a71abfaafe1c462920c6f45a31dcce4bd0bc1ffddfac3adfb21cadfb/B_mesh.gif" data-mid="194416752" border="0" data-scale="32" src="https://freight.cargo.site/w/1000/i/0eda9739a71abfaafe1c462920c6f45a31dcce4bd0bc1ffddfac3adfb21cadfb/B_mesh.gif" /&#62;&#60;img width="1360" height="1208" width_o="1360" height_o="1208" data-src="https://freight.cargo.site/t/original/i/a19b7cdc680554336dfe1f02af06286aa0272ed4e2dd2862d7e75785fbddb558/Screenshot-2023-10-21-at-4.24.01-PM.png" data-mid="194416778" border="0" data-scale="72" src="https://freight.cargo.site/w/1000/i/a19b7cdc680554336dfe1f02af06286aa0272ed4e2dd2862d7e75785fbddb558/Screenshot-2023-10-21-at-4.24.01-PM.png" /&#62;&#60;img width="1676" height="972" width_o="1676" height_o="972" data-src="https://freight.cargo.site/t/original/i/655b7bd5e623c4b2064d64f1d4a8053ba77c5d75cf2918de0ac4b16fd03ad24a/Screenshot-2023-10-21-at-4.24.14-PM.png" data-mid="194416777" border="0"  src="https://freight.cargo.site/w/1000/i/655b7bd5e623c4b2064d64f1d4a8053ba77c5d75cf2918de0ac4b16fd03ad24a/Screenshot-2023-10-21-at-4.24.14-PM.png" /&#62;&#60;img width="1954" height="1108" width_o="1954" height_o="1108" data-src="https://freight.cargo.site/t/original/i/9beedc548cd79ca867f849bc2b1837eee96a964d749ccf459572ca36d1eea460/Screenshot-2023-10-21-at-4.24.28-PM.png" data-mid="194416776" border="0"  src="https://freight.cargo.site/w/1000/i/9beedc548cd79ca867f849bc2b1837eee96a964d749ccf459572ca36d1eea460/Screenshot-2023-10-21-at-4.24.28-PM.png" /&#62;</description>
		
	</item>
		
		
	<item>
		<title>Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties</title>
				
		<link>https://nickvlassis.com/Denoising-diffusion-algorithm-for-inverse-design-of-microstructures</link>

		<pubDate>Tue, 24 Jan 2023 16:19:53 +0000</pubDate>

		<dc:creator>Nick Vlassis</dc:creator>

		<guid isPermaLink="true">https://nickvlassis.com/Denoising-diffusion-algorithm-for-inverse-design-of-microstructures</guid>

		<description>
	Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
Vlassis, Sun, CMAME, 2023.

	We propose a denoising diffusion algorithm for discovering microstructures with fine-tuned nonlinear properties. These generative models utilize diffusion dynamics for denoising images and generating synthetic samples. By learning the reverse of a Markov diffusion process, the algorithm manipulates microstructures' topology, generating numerous prototypes with constitutive responses closely aligned to defined nonlinear responses. A convolutional neural network surrogate is trained to identify the subset of microstructures with precise properties, replacing high-fidelity finite element simulations. Our study confirms the algorithm's ability to create microstructures with specific nonlinear material properties within the latent space of the training data. Furthermore, the algorithm can be extended to incorporate additional topological and geometric modifications. Validated against the open-source mechanical MNIST data set, the algorithm performs successful inverse design of nonlinear effective media and quantitatively maps the nonlinear structure-property relationship.

Read more →


	&#60;img width="548" height="752" width_o="548" height_o="752" data-src="https://freight.cargo.site/t/original/i/a68a9f5a2e6a872a5b160c4c143e4bc8c19bd21a35b343f2309b4c51f97bb6e2/diffusion_micro.gif" data-mid="185555343" border="0"  src="https://freight.cargo.site/w/548/i/a68a9f5a2e6a872a5b160c4c143e4bc8c19bd21a35b343f2309b4c51f97bb6e2/diffusion_micro.gif" /&#62;
	&#60;img width="2128" height="588" width_o="2128" height_o="588" data-src="https://freight.cargo.site/t/original/i/bf62b484351f8cb61d7d909fc84f2af740ff5caa1bb7aa50a655941888892dbc/image68.png" data-mid="185560005" border="0"  src="https://freight.cargo.site/w/1000/i/bf62b484351f8cb61d7d909fc84f2af740ff5caa1bb7aa50a655941888892dbc/image68.png" /&#62;&#60;img width="2582" height="916" width_o="2582" height_o="916" data-src="https://freight.cargo.site/t/original/i/5ef0f528c3ad6aa645957e312e7c3f86ebb0e45af92f28aeb38f7404c5b157a9/Screenshot-2025-03-22-at-2.06.02PM.png" data-mid="228631985" border="0" data-scale="100" src="https://freight.cargo.site/w/1000/i/5ef0f528c3ad6aa645957e312e7c3f86ebb0e45af92f28aeb38f7404c5b157a9/Screenshot-2025-03-22-at-2.06.02PM.png" /&#62;&#60;img width="2572" height="1672" width_o="2572" height_o="1672" data-src="https://freight.cargo.site/t/original/i/eca7ccc210eb37104c9402f4de422555308550fc0e027683b3c227074ae69a9a/image89.png" data-mid="185560052" border="0"  src="https://freight.cargo.site/w/1000/i/eca7ccc210eb37104c9402f4de422555308550fc0e027683b3c227074ae69a9a/image89.png" /&#62;
</description>
		
	</item>
		
	</channel>
</rss>