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.
[1]KAISER NATHAND, BEHR RICHARDA, MINOR JOSEPHE, et al. Impact resistance of laminated glass using “sacrificial ply” design concept. , 2000,6(1):24-34.
[2]SAXE TIMOTHYJ, BEHR RICHARDA, MINOR JOSEPHE, et al. Effects of missile size and glass type on impact resistance of “sacrificial ply” laminated glass. , 2002,8(1):24-39.
[3]WANGXING-ER, YANGJIAN, LIUQIANG, et al. Experimental investigations into SGP laminated glass under low velocity impact. , 2018,122:91-108.
[4]ZHANGXI-HONG, HAOHONG, MAGUO-WEI. Laboratory test and numerical simulation of laminated glass window vulnerability to debris impact. , 2013,55:49-62.
[5]CHENSHUN-HUA, ZANGMENG-YAN, WANGDI, et al. Finite element modelling of impact damage in polyvinyl butyral laminated glass. , 2016,138:1-11.
[6]WANGXING-ER, YANGJIAN, LIUQING-FENG, et al. A comparative study of numerical modelling techniques for the fracture of brittle materials with specific reference to glass. , 2017,152:493-505.
[7]MOHAGHEGHIANIMAN, WANGY, JIANGL, et al. Quasi-static bending and low velocity impact performance of monolithic and laminated glass windows employing chemically strengthened glass. , 2017,63:165-186.
[8]ALTERCHRISTIAN, KOLLINGSTEFAN, SCHNEIDERJENS. An enhanced non-local failure criterion for laminated glass under low velocity impact. , 2017,109:342-353.
[9]ZHANGYANG-MEI, WANGXING-ER, YANGJIAN. Experimental study of multiple layered SGP laminated glass under hard body impact. , 2018,33(10):1110-1118.
[10]WANGXING-ER, YANGJIAN, WANGFEILIANG, et al. Simulating the impact damage of laminated glass considering mixed mode delamination using FEM/DEM. , 2018,202:1239-1252.
[11]LIUXIAO-GEN, BAOYI-WANG, SONGYI-LE, et al. The calculation method The calculation method and influence factor to the natural frequency of laminated glass. , 2008, (27) 5:918-923.
[12]DASSANTANU, SRIVASTAVA ASHOKN, CHATTOPADHYAYADITI. Classification of Damage Signatures in Composite Plates using One-class SVMs. 2007 IEEE Aerospace Conference. 2007: 1-19.
[13]LIHONG-NAN, GAODONG-WEI, YITING-HUA. Advances in structural health monitoring systems in civil engineering. , 2008(02):151-166.
[14]JIANGZHEN-YU, ZHANGZHONG, FRIEDRICHKLAUS. Prediction on wear properties of polymer composites with artificial neural networks. , 2007,67(2):168-176.
[15]CHATTERJEESANKHADEEP, SARKARSARBARTHA, HORESIRSHENDU, et al. Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings. , 2017,28(8):2005-2016.
[16]XUHAN, YANGJIAN, WANGXING-ER, et al. Application of back propagation neural network on debonding prediction of glass curtain walls with concealed frames. , 2019,47(8):1073-1079.
[17]SHENGMING-JIAN, CHENPU-HUI, QIANYI-BIN. An estimating method of compressive strength of composite laminates after low-velocity impact. , 2019,53(10):1182-1186.
[19]HUANGGUANG-BIN, DINGXIAO-JIAN, ZHOUHONG-MING. Optimization method based extreme learning machine for classification. , 2010,74(1/2/3):155-163.
[20]MIRJALILISEYEDALI, LEWISANDREW. The whale optimization algorithm. , 2016,95:51-67.
[21]VEERFA, LOUTER PIETERCHRISTIAAN, BOSFP. The strength of annealed, heat-strengthened and fully tempered float glass. , 2009,32(1):18-25.
[22]FAWCETTTOM. An introduction to ROC analysis. , 2006,27(8):861-874.
[23]HUANGJ, LUJ, LING C X. Comparing Naive Bayes, Decision trees, and SVM with AUC and Accuracy. Third IEEE International Conference on Data Mining. 2003: 553-556.
[24]BARAKATN, BRADLEY AP. Rule Extraction from Support Vector Machines: Measuring the Explanation Capability Using the Area under the ROC Curve. 2006: 812-815.
[25]ZHANGX, JIANGC. Improved SVM for Learning Multi-Class Domains with ROC Evaluation. 2007 International Conference on Machine Learning and Cybernetics. 2007: 2891-2896.
[27]GUIGUO-QING, PANHONG, LIN ZHI-BIN,et al.Data-driven support vector machine with optimization techniques for structural health monitoring and damage detection. , 2017,21(2):523-534.
[28]HUANGGUANG-BIN, WANG DIANHUI, LANYUAN. Extreme learning machines: a survey. International. , 2011,2(2):107-122.
[29]HOSL, YANGSHI-YOU, NIGUANG-ZHENG, et al. A particle swarm optimization-based method for multiobjective design optimizations. , 2005,41(5):1756-1759.
[30]YANGXI-YUN, GUANWEN-YUAN, LIUYU-QI, et al. Prediction intervals forecasts of wind power based on PSO-KELM. , 2015,35(S1):146-153.
孟嫣然, 王星尔, 杨健, 徐涵, 岳峰. 基于机器学习算法的夹层玻璃冲击破坏预测模型研究[J]. 无机材料学报, 2021, 36(1): 61. Yanran MENG, Xinger WANG, Jian YANG, Han XU, Feng YUE. Research on Machine Learning Based Model for Predicting the Impact Status of Laminated Glass[J]. Journal of Inorganic Materials, 2021, 36(1): 61.