Wide-ranging Probabilistic Physics-guided Machine Learning Approach to Break Down the Limits of Current Fatigue Predictive Tools for Metals

BREAKDOWN aims to revolutionize engineering design by integrating micro-scale material inhomogeneities into a probabilistic framework to enhance fatigue understanding and sustainability in structural applications.

Subsidie
€ 1.499.954
2024

Projectdetails

Introduction

It appears paradoxical how today's frontier & high-impact research seeks to design new materials to delay structural failures – especially fatigue – while the same effort is not seen concerning the way materials can be efficiently and safely used in real structural applications.

Project Objectives

BREAKDOWN aims to transform engineering products’ design methods by identifying and including a set of (sub)micro-scale material inhomogeneities characteristics in a novel probabilistic framework. The time has come to exploit modern experimental techniques to probe material properties at a small scale, which are scarcely involved in current fatigue characterisation schemes.

Methodology

To attain this very ambitious goal, the project will rely on a breakdown of different classes of inhomogeneities to advance the fundamental mechanical understanding of their contribution to fatigue. Then, these inhomogeneities will be reunited within an advanced Bayesian Physics-Guided Neural Network (B-PGNN) framework.

  1. Feasibility Study: Over the past three years, I assiduously worked to prove the feasibility of BREAKDOWN and demonstrate its superior capabilities.
  2. Knowledge Advancement: However, I have merely scratched the surface of what is potentially achievable with this approach, both in terms of knowledge advancement and real engineering applications.

Experimental Campaign

An extensive multimodal experimental characterisation campaign will be conducted on different material inhomogeneity states to separate and identify their individual influence on fatigue in a systematic and detailed way.

Numerical and Analytical Models

Cutting-edge numerical & analytical models will be developed and exploited as the physics knowledge in the B-PGNN scheme to effectively tackle the small datasets issue when dealing with fatigue and to ensure the soundness of results.

Expected Outcomes

The outstanding capabilities of the framework developed in BREAKDOWN will be confirmed through specific demonstrators. BREAKDOWN will excellently contribute towards the development of a much more sustainable design procedure with unprecedented social, economic, and environmental benefits.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 1.499.954
Totale projectbegroting€ 1.499.954

Tijdlijn

Startdatum1-12-2024
Einddatum30-11-2029
Subsidiejaar2024

Partners & Locaties

Projectpartners

  • UNIVERSITA DEGLI STUDI DI UDINEpenvoerder

Land(en)

Italy

Vergelijkbare projecten binnen European Research Council

ERC Advanced...

Data-Driven Bioinspired Design of Fatigue Super-Resistant Structures: learning by Nature and Flying into the future

ButterFly aims to revolutionize fatigue design by developing a novel mechanistic approach inspired by natural materials' durability, enhancing structural integrity in industrial applications.

€ 2.499.811
ERC Advanced...

Configurational Mechanics of Soft Materials: Revolutionising Geometrically Nonlinear Fracture

SoftFrac aims to advance soft fracture mechanics through innovative modeling and algorithms, enhancing the resilience of soft devices in robotics, electronics, and tissue engineering.

€ 2.494.538
ERC Starting...

Hard work, plastic flow: a data-centric approach to dislocation-based plasticity

This project aims to bridge the gap between individual and collective dislocation behavior in metals by utilizing data-driven analysis of dislocation trajectories to develop novel plasticity models.

€ 1.498.839
ERC Consolid...

Solving the multi-scale problem in materials mechanics: a pathway to chemical design

Develop a groundbreaking computational framework to predict the viscoelastic and plastic behavior of complex materials across various deformation rates, overcoming current simulation limitations.

€ 952.785
ERC Advanced...

Automated Model Discovery for Soft Matter Systems

The project aims to democratize constitutive modeling of soft materials through automated neural network discovery, enhancing accessibility and innovation in scientific research and training.

€ 2.775.408

Vergelijkbare projecten uit andere regelingen

EIC Pathfinder

digital based bio-waste derived meta-PANels Towards A REvolutionary building Identity

The PANTAREI project aims to reduce embodied CO2 in buildings by developing adaptive computational tools for bio-waste-derived meta-structures through a collaborative, multi-disciplinary approach.

€ 3.085.000