{"title":"A new approach to multiaxial fatigue life prediction: A multi-dimensional multi-scale composite neural network with multi-depth","authors":"","doi":"10.1016/j.engfracmech.2024.110501","DOIUrl":null,"url":null,"abstract":"<div><div>Many multiaxial fatigue life prediction methods tend to increase additional parameters and model depth as the complexity of the loading path increases. This leads to issues such as poor model robustness, limited flexibility, and single-dimensional approaches. In this study, a multi-dimensional multi-scale composite neural network with multi-depth is proposed to address these challenges and enhance prediction accuracy. Initially, physical and sensitive features serve as input data for the proposed model, to enhance the richness of input features. Subsequently, a multi-dimensional feature extraction module is deployed to extract feature information from the composite data. To process these features, an improved multi-domain query cascaded transformer network (IMQCT) is employed as the feature processing module of the proposed model. The proposed model is verified to have better prediction accuracy and extrapolation capability by using experimental data from nine materials and comparing its performance with six machine learning models.</div></div>","PeriodicalId":11576,"journal":{"name":"Engineering Fracture Mechanics","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Fracture Mechanics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0013794424006647","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MECHANICS","Score":null,"Total":0}
引用次数: 0
Abstract
Many multiaxial fatigue life prediction methods tend to increase additional parameters and model depth as the complexity of the loading path increases. This leads to issues such as poor model robustness, limited flexibility, and single-dimensional approaches. In this study, a multi-dimensional multi-scale composite neural network with multi-depth is proposed to address these challenges and enhance prediction accuracy. Initially, physical and sensitive features serve as input data for the proposed model, to enhance the richness of input features. Subsequently, a multi-dimensional feature extraction module is deployed to extract feature information from the composite data. To process these features, an improved multi-domain query cascaded transformer network (IMQCT) is employed as the feature processing module of the proposed model. The proposed model is verified to have better prediction accuracy and extrapolation capability by using experimental data from nine materials and comparing its performance with six machine learning models.
期刊介绍:
EFM covers a broad range of topics in fracture mechanics to be of interest and use to both researchers and practitioners. Contributions are welcome which address the fracture behavior of conventional engineering material systems as well as newly emerging material systems. Contributions on developments in the areas of mechanics and materials science strongly related to fracture mechanics are also welcome. Papers on fatigue are welcome if they treat the fatigue process using the methods of fracture mechanics.