Optimal kernel extreme learning machine model for predicting the fracture state and impact response of laminated glass panels. (May 2021)

• Record Type: Journal Article
• Authors: Wang, Xing-er; Meng, Yanran; Yang, Jian; Huang, Xuhao; Wang, Feiliang; Xu, Han
• Is Part Of: Thin-walled structures. Volume 162(2021)
• Publication Date: 2021-05
• Subjects: Laminated glass -- Impact response -- Fracture prediction -- Machine learning -- Kernel extreme learning machine; Thin-walled structures -- Periodicals; 690.1
• DOI: 10.1016/j.tws.2021.107541
• Languages: English
• ISSNs: 0263-8231

Abstract

Abstract: The structural calculations of laminated glass (LG) under impact are commonly not available in sophisticated load scenarios such as consecutive impacts in typhoon or calculating the post-fracture response of LG. In this work, a flexible prediction model based on kernel extreme learning machine (KELM) was proposed for assessing the fracture state and characteristic impact response of LG under impact, which only used rough material properties and preliminary experimental data. Multiple design variables such as glass make-up, panel size, interlayer type and thickness, and support conditions were considered. Impact tests with consecutive impact attempts were first conducted. Then, a comprehensive database was established which include the fracture state of each glass layer and characteristic impact response, which encompasses peak impact force, contact duration and impact energy dissipation ratio. 567 groups of polyvinyl butyral (PVB) LG data and 210 groups of SentryGlas® (SG) LG data were finally recorded and collected for the database. An optimal KELM model was subsequently developed via introducing whale optimization algorithm (WOA). The modelling results were compared with those from two popular models, i.e. support vector machine (SVM) and least squares SVM (LSSVM) based models to identify both potential strengths and shortcomings. The results show that the proposed model has better performance in both prediction accuracy and computation cost than other examined models. The proposed model has the highest prediction accuracy of 88.45% in evaluating the fracture state, more than 86% in the characteristic impact response. Highlights: A KELM based prediction model was proposed for LG under hard body impact. 777 groups of data were recorded by impact tests on LG panels for the model database. Multiple design variables of LG were considered in the database. The WOA algorithm was adopted to optimize the KELM model. The applicability of the model was examined by comparing with two popular models.