{"title":"A hybrid data-driven machine learning framework for predicting the impact resistance of composite armor","authors":"","doi":"10.1016/j.ijimpeng.2024.105125","DOIUrl":null,"url":null,"abstract":"<div><div>Composite armor plays a crucial role as the primary defense against high-velocity impacts from fragments and projectiles. However, balancing the need for lightweight structures with the requirement for robust protection remains a significant engineering challenge. Traditional approaches for predicting the protective performance of armor typically involve a combination of experimental testing and numerical simulations, both of which can be resource-intensive and costly. In contrast, data-driven methods combined with machine learning have demonstrated the potential to significantly reduce both time and economic costs, highlighting their substantial advantages in various engineering domains. Unfortunately, a mature machine learning framework for predicting the performance of multilayer composite armor against high-velocity impacts from large fragments has yet to be established. In this paper, a novel data-driven framework for predicting the ballistic performance of composite armor using a hybrid model of Support Vector Machine and Deep Neural Network was established. This framework employed hyperparameter optimization to enhance predictive performance, yielding a model with excellent accuracy. The proposed model was adaptable to multilayered armor with varying layer thicknesses, enabling rapid predictions of armor penetration, residual projectile kinetic energy, and armor deformation.</div></div>","PeriodicalId":50318,"journal":{"name":"International Journal of Impact Engineering","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0734743X24002501/pdfft?md5=edad608188e164a3bc4026d92471f9d4&pid=1-s2.0-S0734743X24002501-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Impact Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0734743X24002501","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Composite armor plays a crucial role as the primary defense against high-velocity impacts from fragments and projectiles. However, balancing the need for lightweight structures with the requirement for robust protection remains a significant engineering challenge. Traditional approaches for predicting the protective performance of armor typically involve a combination of experimental testing and numerical simulations, both of which can be resource-intensive and costly. In contrast, data-driven methods combined with machine learning have demonstrated the potential to significantly reduce both time and economic costs, highlighting their substantial advantages in various engineering domains. Unfortunately, a mature machine learning framework for predicting the performance of multilayer composite armor against high-velocity impacts from large fragments has yet to be established. In this paper, a novel data-driven framework for predicting the ballistic performance of composite armor using a hybrid model of Support Vector Machine and Deep Neural Network was established. This framework employed hyperparameter optimization to enhance predictive performance, yielding a model with excellent accuracy. The proposed model was adaptable to multilayered armor with varying layer thicknesses, enabling rapid predictions of armor penetration, residual projectile kinetic energy, and armor deformation.
期刊介绍:
The International Journal of Impact Engineering, established in 1983 publishes original research findings related to the response of structures, components and materials subjected to impact, blast and high-rate loading. Areas relevant to the journal encompass the following general topics and those associated with them:
-Behaviour and failure of structures and materials under impact and blast loading
-Systems for protection and absorption of impact and blast loading
-Terminal ballistics
-Dynamic behaviour and failure of materials including plasticity and fracture
-Stress waves
-Structural crashworthiness
-High-rate mechanical and forming processes
-Impact, blast and high-rate loading/measurement techniques and their applications