Stress, Strain, or Energy? - which one is superior predictor of fatigue life in notched Components? - a novel Machine Learning-Based framework

Aug 5, 2026

Upload by Hazel

This paper introduces an efficient framework for accurately predicting the fatigue lifetime of notched components under uniaxial loading within the high-cycle fatigue regime. Various machine learning algorithms are evaluated across materials, loading conditions, notch geometries, and fatigue lives, and the study identifies whether stress, strain, or energy is the better measure. The method leverages profile-based field distributions of response parameters to separate notch geometries, validated on metals, additive-manufactured specimens, and carbon fiber composites.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Fatigue life estimation background

Limitations of empirical relationships

Machine learning approaches for fatigue analysis

Engineering Fracture Mechanics 309 (2024) 110401 Contents lists available at ScienceDirect Engineering Fracture Mechanics journal [homepage:](homepage: www.elsevier.com/locate/engfracmech)[ www.elsevier.com/locate/engfracmech](homepage: www.elsevier.com/locate/engfracmech) | Stress, Strain, or Energy? which one is superior predictor of fatigue life in notched Components? a novel Machine Learning-Based framework | | | | | --- | --- | --- | --- | | A.M. Mirzaei
Department of Structural, Geotechnical and Building Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Torino, Italy School of Aerospace, Transport and Manufacturing, Cranfield University, Bedford MK43 0AL, UK | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Fatigue life prediction Notch
Machine learning Additive manufacturing
Carbon fiber laminated composites | | This paper introduces an efficient framework for accurately predicting the fatigue lifetime of notched components under uniaxial loading within the high-cycle fatigue regime. For this purpose, various machine learning algorithms are applied to a wide range of materials, loading conditions, notch geometries, and fatigue lives. Traditional approaches for this task have mostly relied on one of the mechanical response parameters, such as stress, strain, or energy. This study also concludes which of these parameters serves as a better measure. The key idea of the framework is to use the profile (field distribution represented by some points) of the mechanical response parameters (stress, strain, and energy release rate) to distinguish between different notch geometries. To demonstrate the accuracy and broad applicability of the framework, it is initially validated using metal materials, subsequently applied to specimens produced through additive manufacturing techniques, and ultimately tested on carbon fiber laminated composites. This research demonstrates the effective use of all three parameters in estimating fatigue lifetime, while stress-based predictions exhibit the highest accuracy. Among the machine learning algorithms investigated, Gradient Boosting and Random Forest yield the most successful results. A noteworthy finding is the significant improvement in prediction accuracy achieved by incorporating new data generated based on the Basquin equation. | | 1. Introduction Estimating fatigue life is a vital task in the design and maintenance of various mechanical systems and structures. This process involves predicting how many cycles (life) a material can endure before failure due to cyclic loading, a phenomenon commonly encountered in real-world structures [1]. Mostly, fatigue life estimation has relied on empirical relationships derived from extensive experimental testing, focusing on mechanical response parameters, e.g., stress [2], strain [3], or energy [4]. Therefore, these methods can be time-consuming, expensive, and may lack precision for diverse materials or loading conditions. Recently, machine learning (ML) has emerged as a leading solution in the field of materials science and technology [5], specifically fatigue failure [6]. It offers the potential to enhance prediction accuracy by identifying patterns within existing datasets [7,8]. This section provides a review of the current state of the art in fatigue analysis through machine learning, initially exploring its broad applications across various problems and materials, then narrowing down to its use in additively manufactured specimens, and ultimately presenting advanced models to set E-mail addresses: amir.mirzaei@polito.it, [amir.mirzaei@cranfield.ac.uk](amir.mirzaei@cranfield.ac.uk). [https://doi.org/10.1016/j.engfracmech.2024.110401](https://doi.org/10.1016/j.engfracmech.2024.110401) Received 14 May 2024; Received in revised form 30 July 2024; Accepted 13 August 2024 Available online 17 August 2024 0013-7944/© 2024 The Author(s). Published by Elsevier Ltd. This is

FAQs

What fatigue-life problem does the framework address?

It predicts fatigue lifetime of notched components under uniaxial loading in the high-cycle fatigue regime.

How does the method decide between stress, strain, and energy as predictors?

It uses field-profile information (point-based field distributions) of stress, strain, and energy release rate to distinguish notch geometries, then evaluates which parameter yields better prediction accuracy.

What datasets or specimen types are used to validate the approach?

The framework is validated first on metal materials, then applied to additive-manufactured specimens, and finally tested on carbon fiber laminated composites.

Aug 5, 2026

Upload by Hazel