无机材料学报 ›› 2021, Vol. 36 ›› Issue (1): 61-68.DOI: 10.15541/jim20200187

• 研究论文 • 上一篇    下一篇

基于机器学习算法的夹层玻璃冲击破坏预测模型研究

孟嫣然1,2,3,王星尔1,2,3,4,杨健1,2,3(),徐涵1,2,3,岳峰1,2   

  1. 1. 上海交通大学 船舶海洋与建筑工程学院, 上海 200240
    2. 上海交通大学 海洋工程国家重点实验室, 上海 200240
    3. 上海市公共建筑和基础设施数字化运维重点实验室, 上海 200240
    4. 宁波大学 冲击与安全工程教育部重点实验室, 宁波 315211
  • 收稿日期:2020-04-09 修回日期:2020-05-22 出版日期:2021-01-20 发布日期:2020-06-15
  • 作者简介:孟嫣然(1996-), 女, 硕士研究生. E-mail: yrmeng@sjtu.edu.cn
  • 基金资助:
    国家重点研发计划(2017YFC0806100);国家自然科学基金(51908352);冲击与安全工程教育重点实验室(宁波大学开放课题)(CJ201906)

Research on Machine Learning Based Model for Predicting the Impact Status of Laminated Glass

MENG Yanran1,2,3,WANG Xinger1,2,3,4,YANG Jian1,2,3(),XU Han1,2,3,YUE Feng1,2   

  1. 1. School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    2. State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    3. Shanghai Key Laboratory for Digital Maintenance of Buildings and Infrastructure, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    4. Key Laboratory of Impact and Safety Engineering, Ministry of Education, Ningbo University, Ningbo 315211, China
  • Received:2020-04-09 Revised:2020-05-22 Online:2021-01-20 Published:2020-06-15
  • About author:MENG Yanran(1996-), female, Master candidate. E-mail: yrmeng@sjtu.edu.cn
  • Supported by:
    National Key Research and Development Program of China(2017YFC0806100);National Natural Science Foundation of China(51908352);Project of Key Laboratory of Impact and Safety Engineering(Ningbo University, Ministry of Education)(CJ201906)

摘要:

在诸如风致飞射物撞击等刚体冲击作用下, 建筑夹层玻璃因自身脆性特征极易破坏。针对这个问题提出了在刚体冲击下夹层玻璃破坏状态的预测方法, 综合考虑了玻璃构型、中间胶层、支撑条件及尺寸等多种设计参数。首先针对多类夹层玻璃进行往复刚体冲击试验, 建立567组PVB及210组SGP的两种不同中间胶层的夹层玻璃试验数据库; 随后基于鲸鱼优化下的核极限学习机(WOA-KELM)机器学习算法, 建立夹层玻璃破坏状态的预测模型, 并与支持向量机(Support Vector Machine, SVM)及最小二乘支持向量机(Least Squares Support Vector Machine, LSSVM)建立的相应预测模型进行对比分析。结果表明, WOA-KELM模型破坏状态预测精度达88.45%, 能较好地预测夹层玻璃的破坏, 满足工程应用的需求, 且预测模型精度及实时性均优于其他模型。

关键词: 夹层玻璃, 冲击破坏, 机器学习, 核极限学习机

Abstract:

Architectural laminated glass exhibits significant vulnerability under hard body impacts such as windborne debris impacts. In this work, a prediction model is proposed for assessing the impact status of laminated glass under hard body impact. Multiple design variables including the glass make-ups, interlayer types, support conditions and size are considered. The impact tests with consecutive impact attempts are first conducted. A comprehensive database encompassing the failure condition of each glass layer is then established. This database has 567 groups of PVB laminated glass data and 210 groups of SGP laminated glass data. A combined WOA-KELM machining learning based model is subsequently developed to predict the impact status of laminated glass. The modelling results are compared with that from SVM and LSSVM based models. The results show that the proposed model has a prediction accuracy of 88.45% in failure status of each glass layer. Such model can well predict the impact status of laminated glass and shows better performance in both accuracy and computation cost than other models.

Key words: laminated glass, impact failure, machine learning, kernel extreme learning machine

中图分类号: