Democratizing biomedical simulation through automated model discovery and a universal material subroutine

Computational Mechanics, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 14, 2024

Abstract Personalized computational simulations have emerged as a vital tool to understand the biomechanical factors of disease, predict disease progression, and design personalized intervention. Material modeling is critical for realistic biomedical simulations, poor model selection can life-threatening consequences patient. However, selecting best requires profound domain knowledge limited few highly specialized experts in field. Here we explore feasibility eliminating user involvement automate process material finite element analyses. We leverage recent developments constitutive neural networks, machine learning, artificial intelligence discover from thousands possible combinations functional building blocks. integrate all discoverable models into workflow by creating universal subroutine that contains more than 60,000 models, made up 16 individual terms. prototype this using biaxial extension tests healthy human arteries input stress stretch profiles across aortic arch output. Our results suggest networks robustly various flavors arterial data, feed these directly simulation, strain compare favorably classical Holzapfel model. Replacing dozens subroutines single subroutine—populated via automated discovery—will make user-friendly, robust, less vulnerable error. Democratizing simulation automating could induce paradigm shift physics-based modeling, broaden access technologies, empower individuals with varying levels expertise diverse backgrounds actively participate scientific discovery push boundaries simulation.

Language: Английский

---

Neural networks meet anisotropic hyperelasticity: A framework based on generalized structure tensors and isotropic tensor functions

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2025, Volume and Issue: 437, P. 117725 - 117725

Published: Jan. 21, 2025

Language: Английский

---

Automated model discovery for tensional homeostasis: Constitutive machine learning in growth and remodeling

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 186, P. 109691 - 109691

Published: Jan. 21, 2025

Language: Английский

---

Convex neural networks learn generalized standard material models

Journal of the Mechanics and Physics of Solids, Journal Year: 2025, Volume and Issue: unknown, P. 106103 - 106103

Published: March 1, 2025

Language: Английский

---

A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains

Engineering With Computers, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 2, 2024

Abstract We propose a novel finite element-based physics-informed operator learning framework that allows for predicting spatiotemporal dynamics governed by partial differential equations (PDEs). The Galerkin discretized weak formulation is employed to incorporate physics into the loss function, termed (FOL), along with implicit Euler time integration scheme temporal discretization. A transient thermal conduction problem considered benchmark performance, where FOL takes temperature field at current step as input and predicts next step. Upon training, network successfully evolution over any initial high accuracy compared solution element method (FEM) even heterogeneous conductivity arbitrary geometry. advantages of can be summarized follows: First, training performed in an unsupervised manner, avoiding need large data prepared from costly simulations or experiments. Instead, random patterns generated Gaussian process Fourier series, combined constant fields, are used cover possible cases. Additionally, shape functions backward difference approximation exploited domain discretization, resulting purely algebraic equation. This enhances efficiency, one avoids time-consuming automatic differentiation optimizing weights biases while accepting discretization errors. Finally, thanks interpolation power FEM, geometry microstructure handled FOL, which crucial addressing various engineering application scenarios.

Language: Английский

---

Machine learning-based constitutive modelling for material non-linearity: A review

Mechanics of Advanced Materials and Structures, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 19

Published: Dec. 17, 2024

Machine learning (ML) models are widely used across numerous scientific and engineering disciplines due to their exceptional performance, flexibility, prediction quality, ability handle highly complex problems if appropriate data available. One example of such areas which has attracted a lot attentions in the last couple years is integration data-driven approaches material modeling. There been several successful researches implementing ML-based constitutive instead classical phenomenological for various materials, particularly those with non-linear mechanical behaviors. This review paper aims systematically investigate literature on materials classify these based suitability non-linearity including Non-linear elasticity (hyperelasticity), plasticity, visco-elasticity, visco-plasticity. Furthermore, we also reviewed compared that have applied architectured as groups designed represent specific behaviors might not exist conventional categories. The other goal this provide initial steps understanding modeling, artificial neural networks (ANN), Gaussian processes, random forests (RF), generated adversarial (GANs), support vector machines (SVM), different regression physics-informed (PINN). outlines collection methods, types data, processing approaches, theoretical background ML models, advantage limitations potential future research directions. comprehensive will researchers knowledge necessary develop high-fidelity, robust, adaptable, flexible, accurate advanced materials.

Language: Английский

---

Automated model discovery for textile structures: The unique mechanical signature of warp knitted fabrics

Acta Biomaterialia, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

---

Artificial Intelligence in Automotives: ANNs’ Impact on Biodiesel Engine Performance and Emissions

Energies, Journal Year: 2025, Volume and Issue: 18(2), P. 438 - 438

Published: Jan. 20, 2025

This paper explores the integration and advancements of artificial neural networks (ANNs) in modeling diesel engine performance, particularly focusing on biodiesel-fueled engines. ANNs have emerged as a vital tool predicting optimizing parameters, contributing to enhancement fuel efficiency reduction emissions. The novelty this review lies its critical analysis existing literature ANN applications biodiesel engines, identifying gaps optimization emission control. While shown promise efficiency, reduction, highlights their limitations areas for improvement, especially context with big data sophisticated algorithms paves way more accurate reliable modeling, essential advancing sustainable eco-friendly automotive technologies. research underscores growing importance aligning global efforts towards cleaner energy solutions.

Language: Английский

---

An anisotropic thermo-mechanically coupled constitutive model for glass fiber reinforced polyamide 6 including crystallization kinetics

International Journal of Plasticity, Journal Year: 2025, Volume and Issue: unknown, P. 104341 - 104341

Published: April 1, 2025

Language: Английский

---

Prediction using inelastic constitutive artificial neural networks for impact of dead-time on inverters in wireless power transfer systems

e-Prime - Advances in Electrical Engineering Electronics and Energy, Journal Year: 2025, Volume and Issue: 12, P. 100993 - 100993

Published: April 22, 2025

Language: Английский

---