当前位置:首页  科学研究  研究成果  论文  2025年

【Engineering Fracture Mechanics】A machine learning-based method for fatigue crack growth rate prediction in the near-threshold region

时间:2025-08-31来源:国际前沿科学研究院点击:213

Jincai Ye, Pengfei Cui, Wanlin Guo*

Engineering Fracture MechanicsIF:4.7),Available online 11 July 2025

Abstract

This study presents a neural network-based incremental learning scheme designed to predict  fatigue crack growth rate (CGR) against the stress intensity factor (SIF) range (ΔK) in the near-  threshold region. CGR datasets are generally small, with most data concentrated in the Paris  region. Near-threshold region data are even more limited due to the significant time and labor  required for their acquisition. To better handle small datasets, we designed a machine learning  model incorporating multiple incremental information, demonstrating superior prediction accu racy compared to traditional fatigue crack growth models across various material datasets,  particularly in the near-threshold region. Given the inherent uncertainties arising from envi ronmental factors, material processing variations, and limited training datasets, the prediction  model may not always perform effectively. To overcome these challenges, we implemented a  correction strategy that leverages minimal experimental CGR data to correct the model. This  approach significantly enhances the prediction accuracy of the model. Moreover, by incorpo rating the fatigue crack closure model, ΔK was unified to the effective SIF range ΔK  eff  , enables  simultaneous correction of CGR data across different stress ratios. Finally, the effectiveness of the  correction strategy was further discussed for high-entropy alloy under different temperature  conditions. This study significantly enhances prediction accuracy in the near-threshold region and  presents applicability to CGR data under various conditions, providing a time and cost-efficient  data acquisition approach for engineering applications.


联系我们

电话:025-84896467
邮箱:IFS@nuaa.edu.cn
邮编:210016
地址:江苏省南京市秦淮区御道街29号

链接

--校内链接--

  • 校内链接

--校外链接--

  • 校外链接

关注我们

微信公众号