Thermographic and Machine Learning approaches for a rapid estimation of gears bending fatigue strength

Aug 4, 2026

The estimation of the tooth root bending fatigue strength of gears is a key mechanical engineering challenge, often requiring multiple tests and long experimental campaigns. The study introduces a rapid, non-destructive framework that integrates thermographic measurements with machine learning, using Gaussian process regression and artificial neural networks. The method combines a green, non-contact thermography procedure with AI to support fast fatigue-strength evaluation. Statistical analyses confirm high accuracy across models, with Gaussian process regression and deep neural networks showing potential advantages for precision and reliability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

POLITECNICO DI TORINO Repository ISTITUZIONALE Thermographic and Machine Learning approaches for a rapid estimation of gears bending fatigue strength Original Thermographic and Machine Learning approaches for a rapid estimation of gears bending fatigue strength / Corsaro, Luca; Dehghanpour Abyaneh, Mohsen; Cura, Francesca Maria; Sesana, Raffaella. -In: FORSCHUNG IM INGENIEURWESEN-ENGINEERING RESEARCH. -ISSN 0015-7899. -ELETTRONICO. -89:1(2025), pp. 1-13.[10.1007/s10010-025-00863-6] Availability: This version is available at: 11583/3002699 since: 2025-09-01T14:33:02Z Publisher: Springer Published DOI:10.1007/s10010-025-00863-6 Terms of use: This article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository Publisher copyright (Article begins on next page) 04 October 2025 Forschung im Ingenieurwesen (2025)89:122 [https://doi.org/10.1007/s10010-025-00863-6](https://doi.org/10.1007/s10010-025-00863-6) ORIGINALARBEITEN/ORIGINALS Thermographic and Machine Learning approaches for a rapid estimation of gears bending fatigue strength Luca Corsaro1 · Mohsen Dehghanpour Abyaneh1 · Francesca Curà1 · Raffaella Sesana1 Received: 20 March 2025 / Accepted: 23 July 2025 © The Author(s) 2025 Abstract The estimation of the tooth root bending fatigue strength of gears is a topic of great interest in the ﬁeld of mechanical engineering. The assessment of this mechanical property is generally conducted through the execution of a series of tests and, in many cases, a long-time experimental campaign is necessary for the bending fatigue strength evaluation. The present study aims at the estimation of the bending fatigue strength in gears by using the well-known Thermographic Method with integrated Machine Learning techniques implementing Gaussian process regression and artiﬁcial neural networks. This approach allows for the combination of a Non-Destructive, green technique with Artiﬁcial Intelligence algorithms, determining a rapid and reasonable estimation of the bending fatigue strength for gears. Among all methods, the statistical analyses conﬁrm that all models have high accuracy. However, Gaussian process regression and deep neural networks may be superior in comparison with other methods, and their precision and reliability may be higher for advanced fatigue assessment. This tool could be helpful to cut down experimental workload with the help of Thermographic Method for the tooth root bending fatigue strength estimation, hence enabling very fast Non-Destructive evaluation of gear performance. Thermography approach combined with Machine Learning agrees sustainability by saving critical resource-intensive testing and leads to an advanced mechanical properties evaluation framework in gear systems, hence offering important alternative to the classical methods. 1 Introduction The application of Passive Thermography (PT) as Non-Destructive Testing (NDT) technique presents numerous advantages, including non-contact, full ﬁeld measurements and reduced testing time. In the speciﬁc context of mechanical research, several studies were conducted by using infrared (IR) detectors to investigate fatigue phenomena. The feasibility of these detectors for temperature analysis in fatigue tests was initiated around the 1970’s [1] and, ten years later, the topic of the fatigue limit estimation attracted signiﬁcant interest. The earliest documented application of the Thermographic Method can be found in [2, 3], where the One Curve Method (OCM) was proposed as a novel approach for a rapid fatigue limit estimation through the utilisation of PT. The papers identiﬁed an empirical linear All authors approved publication of the manuscript. 􀀂 Luca Corsaro luca.corsaro@polito.it 1 Department of Mechanical and Aerospace Engineering (DIMEAS), Politecnico Di Torino, 10129 Torino, Italy relation between stabilisation temperatures and the applied stres

FAQs

What is the main goal of the study?

To estimate gears tooth root bending fatigue strength rapidly by combining thermographic testing with machine learning techniques.

Which machine learning methods are used?

Gaussian process regression and artificial neural networks (deep neural networks).

Why is thermography useful in this context?

Passive thermography enables non-contact, full-field temperature measurements and can reduce testing time compared with conventional fatigue assessment methods.

Aug 4, 2026

Upload by Evangeline