基于卷积神经网络的夹层玻璃开裂后拉伸性能快速评估方法

硅酸盐通报 ›› 2024, Vol. 43 ›› Issue (12): 4588-4596.

基于卷积神经网络的夹层玻璃开裂后拉伸性能快速评估方法

尹俊熙^1,2, 彭沈楠^1,2, 王星尔^1,2, 杨健^1,2

1.上海交通大学海洋工程全国重点实验室, 上海 200240;
2.上海交通大学船舶海洋与建筑工程学院, 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

收稿日期:2024-07-09 修订日期:2024-09-02 出版日期:2024-12-15 发布日期:2024-12-19
通信作者: 王星尔,博士,助理研究员。E-mail:matseyo@sjtu.edu.cn
作者简介:尹俊熙(2000—),男,硕士研究生。主要从事结构功能一体化材料的研究。E-mail:Yin_xi@sjtu.edu.cn
基金资助:
国家自然科学基金(52078293)

Fast Evaluation Method for Post-Fracture Tensile Properties of Laminated Glass Based on Convolutional Neural Network

YIN Junxi^1,2, PENG Shennan^1,2, WANG Xinger^1,2, YANG Jian^1,2

1. State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
2. Shanghai Key Laboratory for Digital Maintenance of Buildings and Infrastructure, School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2024-07-09 Revised:2024-09-02 Published:2024-12-15 Online:2024-12-19

摘要/Abstract

摘要： 夹层玻璃开裂后的承载性能对持续风灾或爆炸时建筑玻璃结构安全性非常重要。玻璃裂纹形态作为开裂后性能的关键影响因素,对夹层玻璃的拉伸硬化效应和局部失效触发有着重要作用。对采用离子性中间层(SG)的钢化夹层玻璃进行碎裂试验及碎裂后单轴拉伸试验,获取图形和力学性能的试验数据集,并和精细有限元模型校核,确定裂纹形态对应的碎片密度、最小最近邻距离、有效粘结系数等关键参数。随后,建立由表面应力调控裂纹形态的夹层玻璃开裂后有限元模型批量化生成方法,基于维诺(Voronoi)形态近似来扩充模拟数据集。采用卷积神经网络方法,基于裂纹形态图像识别训练,得到具有良好精度的夹层玻璃开裂后等效拉伸性能快速评估方法。

关键词: 夹层玻璃, SG中间层, 开裂后性能, 裂纹形态, 快速评估方法, 卷积神经网络

Abstract: The post-fracture load-bearing properties of laminated glass is crucial for the safety of architectural glass structures under long-duration wind disasters or explosions. Crack morphology significantly impacts the tension-stiffening effect and the triggering of local failure in laminated glass. Fragmentation tests and post-fracture uniaxial tensile tests were conducted on laminated tempered glass with SG interlayer to obtain the testing datasets of crack morphological images and associated mechanical properties. The refined finite element (FE) models were then calibrated with experimental outcomes to determine key parameters such as fragment density, minimum nearest neighbour distance, and effective bonding coefficients corresponding to the crack morphology. Subsequently, the batch generation of FE models for fractured laminated glass by adjusting surface compressive stress was established, which utilized Voronoi tessellation to approximate the actual morphology to expand the simulation dataset. The fast evaluation method based on convolutional neural network (CNN) with high accuracy for the equivalent tensile properties of fractured laminated glass was developed via image recognition training on crack morphology.

Key words: laminated glass, SG interlayer, post-fracture property, crack morphology, fast evaluation method, convolutional neural network

中图分类号:

TQ171

尹俊熙, 彭沈楠, 王星尔, 杨健. 基于卷积神经网络的夹层玻璃开裂后拉伸性能快速评估方法[J]. 硅酸盐通报, 2024, 43(12): 4588-4596.

YIN Junxi, PENG Shennan, WANG Xinger, YANG Jian. Fast Evaluation Method for Post-Fracture Tensile Properties of Laminated Glass Based on Convolutional Neural Network[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2024, 43(12): 4588-4596.

参考文献

[1] HÁLA P, ZEMANOVÁ A, PLACHÝ T, et al. Experimental modal analysis of glass and laminated glass large panels with EVA or PVB interlayer at room temperature[J]. Materials Today: Proceedings, 2022, 62: 2421-2428.
[2] WANG X E, YANG J, HUANG X H, et al. Voronoi-FDEM concept for modelling post-fracture response of progressively damaged structural glass[J]. Engineering with Computers, 2022, 38(4): 3025-3038.
[3] 陈素文, 陈志飞, 陈星. 中高应变率下夹层玻璃破碎后力学性能试验研究[J]. 建筑结构学报, 2023, 44(3): 102-112.
CHEN S W, CHEN Z F, CHEN X. Experimental study on post-fractured performance of laminated glass at medium-to-high strain rates[J]. Journal of Building Structures, 2023, 44(3): 102-112 (in Chinese).
[4] BARALDI D, CECCHI A, FORABOSCHI P. Broken tempered laminated glass: non-linear discrete element modeling[J]. Composite Structures, 2016, 140: 278-295.
[5] 朱禹翰, 杨健, 王星尔, 等. 物理钢化玻璃裂纹形态试验及Voronoi形态表征[J]. 硅酸盐学报, 2022, 50(2): 482-491.
ZHU Y H, YANG J, WANG X E, et al. Fracture morphology of tempered glass and Voronoi tessellation-based regeneration[J]. Journal of the Chinese Ceramic Society, 2022, 50(2): 482-491 (in Chinese).
[6] 王星尔, 杨健, 王翰坤. 夹层热钢化玻璃裂纹形态表征及开裂后力学行为[J]. 硅酸盐学报, 2019, 47(8): 1039-1046.
WANG X E, YANG J, WANG H K. Fracture morphology characterization and post-breakage behavior of laminated thermally tempered glass[J]. Journal of the Chinese Ceramic Society, 2019, 47(8): 1039-1046 (in Chinese).
[7] 张劲竹, 刘华新, 王家贺, 等. 混杂纤维混凝土高温后性能劣化分析与强度预测[J]. 硅酸盐通报, 2023, 42(4): 1260-1269.
ZHANG J Z, LIU H X, WANG J H, et al. Performance degradation analysis and strength prediction of hybrid fiber reinforced concrete after high temperature[J]. Bulletin of the Chinese Ceramic Society, 2023, 42(4): 1260-1269 (in Chinese).
[8] PAN Z F, YANG J, WANG X E, et al. Image-based surface scratch detection on architectural glass panels using deep learning approach[J]. Construction and Building Materials, 2021, 282: 122717.
[9] ABUEIDDA D W, ALMASRI M, AMMOURAH R, et al. Prediction and optimization of mechanical properties of composites using convolutional neural networks[J]. Composite Structures, 2019, 227: 111264.
[10] DING X X, HOU X N, XIA M, et al. Predictions of macroscopic mechanical properties and microscopic cracks of unidirectional fibre-reinforced polymer composites using deep neural network (DNN)[J]. Composite Structures, 2022, 302: 116248.
[11] ZHU Y H, YANG J, WANG X E, et al. Morphological characterization and reconstruction of fractured heat-treated glass[J]. Journal of Non-Crystalline Solids, 2023, 616: 122455.