Abstract:The impact resistance of half steel-concrete composite slabs (HSC slabs) is very excellent, which can effectively resist rockfall impact. Under the premise of meeting the requirements of relevant codes, HSC slabs can be designed to reduce the deformation of HSC slabs under rockfall impact, so as to maximize the safety of infrastructure and people in mountain areas. To quickly and accurately deal with the complex nonlinear relationship between HSC slabs deformation and design parameters, the prediction models of HSC slabs maximum deformation under impact are established based on three machine learning algorithms, and the model is verified by finite element results. On this basis, taking the maximum deformation, self-weight and cost of HSC slabs under rockfall impact as the optimization goal, the genetic algorithm is used to optimize the design of a HSC roof slab in a mountain building, and the optimal solution set of design parameters such as thickness and connector size of HSC roof slabs is solved. The research results show that the gaussian process regression (GPR) model has the highest prediction accuracy for the deformation of HSC roof panels, which can replace the complex and time-consuming finite element calculation, and effectively improve the calculation efficiency of the objective equation, and the final optimization results give a variety of optimization schemes, which can effectively reduce the deformation of HSC roof slabs, and provide a reference for engineering design.
[1] 郭科萱. 落石冲击效应计算方法研究 [J]. 科技创新导报, 2017, 14(31): 64-67.
GUO Ke-xuan. Study on calculation method of rockfall impact effect [J]. Science and Technology Innovation Herald, 2017, 14(31): 64-67.
[2] 向欣. 边坡落石运动特性及碰撞冲击作用研究 [D]. 中国地质大学, 2010.
[3] THOENI K, GIACOMINI A, LAMBERT C,et al. A 3D discrete element modelling approach for rockfall analysis with drapery systems [J]. International Journal of Rock Mechanics and Mining Sciences, 2014, 68: 107-119.
[4] BOURRIER F, LAMBERT S, BAROTH J,et al. A Reliability-Based Approach for the Design of Rockfall Protection Fences [J]. Rock Mechanics & Rock Engineering, 2015, 48(1).
[5] 赵唯以, 王琳, 郭全全,等. 双钢板混凝土组合结构抗冲击性能的研究进展 [J]. 钢结构, 2020, 035(003): P.26-36.
ZHAO Wei-yi, WANG Lin, GUO Quan-quan,et al. Research advances of impact Resistance of steel-concrete composite structures [J]. Steel Construction, 2020, 035(003): P.26-36.
[6] 刘青峰. 新型双钢板-混凝土组合剪力墙抗冲击性能及抗爆性能研究 [D]. 天津大学, 2019.
[7] Specification for Safety-Related Steel Structures for Nuclear Facilities [S]. US-AISC, 2012:
[8] GRISARO H, DANCYGIER A N. Assessment of the perforation limit of a composite RC barrier with a rear steel liner to impact of a non-deforming projectile [J]. International Journal of Impact Engineering, 2014, 64(2): 122-136.
[9] BRUHL J C, VARMA A H, JOHNSON W H. Design of composite SC walls to prevent perforation from missile impact [J]. International Journal of Impact Engineering, 2015, 75(1): 75-87.
[10] ZHAO W, GUO Q, DOU X,et al. Impact response of steel-concrete composite panels: Experiments and FE analyses [J]. Steel and Composite Structures, 2018, 26(3): 255-263.
[11] REMENNIKOV A M, KONG S Y. Numerical simulation and validation of impact response of axially-restrained steel–concrete–steel sandwich panels [J]. Composite Structures, 2012, 94(12): 3546-3555.
[12] SADIQ M, XIUYUN Z, RONG P. Simulation analysis of impact tests of steel plate reinforced concrete and reinforced concrete slabs against aircraft impact and its validation with experimental results [J]. Nuclear Engineering and Design, 2014, 273: 653-667.
[13] BRUHL J C, VARMA A H, KIM J M. Static resistance function for steel-plate composite (SC) walls subject to impactive loading [J]. Nuclear Engineering and Design, 2015, 295: 843-859.
[14] GUO Q, ZHAO W. Displacement response analysis of steel-concrete composite panels subjected to impact loadings [J]. International Journal of Impact Engineering, 2019, 131: 272-281.
[15] WANG L, ZHAO W, YANG G,et al. TDOF model for evaluating the global and local impact response of steel-plate composite panels [J]. Thin-Walled Structures, 2021, 164: 107879.
[16] 叶四桥. 隧道洞口段落石灾害研究与防治 [D]. 西南交通大学, 2008.
[17] 窦旭强, 赵唯以, 可飞,等. 双钢板-混凝土组合剪力墙落锤冲击性能研究 [J]. 建筑结构学报, 2017, 38(S1): 84-89.
DOU Xu-qiang, ZHAO Wei-yi, KE Fei,et al. Drop hammer impact behavior of double steel-concrete composite shear walls [J]. Journal of Building Structures, 2017, 38(S1): 84-89.
[18] 窦旭强. 落锤冲击作用下双钢板混凝土组合墙的动力响应研究 [D]. 北京航空航天大学, 2018.
[19] JONES N. Structural Impact [M]. Cambridge: Cambridge University Press, 1989.
[20] LS-DYNA.LS-DYNA keyword user's manual[M]. Version 971.USA: Livermore Software Corporation,2010.
[21] 陈泰江, 章广成, 向欣. 落石冲击混凝土棚洞力学特性研究 [J]. 岩土力学, 2022, 43(01): 277-85+98.
CHEN Tai-jiang,ZHANG Guang-cheng,XIANG Xin. Investigations on mechanical characteristics of rockfall impact on concrete shed cave [J]. Rock and Soil Mechanics, 2022, 43(01): 277-85+98.
[22] 李明星, 王显会, 周云波,等. 基于神经网络的车辆抗冲击防护组件优化 [J]. 爆炸与冲击, 2020, 40(02): 110-118.
LI Ming-xing,WANG Xian-hui,ZHOU Yun-bo,et al. Research on optimization of vehicle anti-shock protection components based on neural network [J]. Explosion and Shock Waves, 2020, 40(02): 110-118.
[23] HUI Z, HASTIE T. Regularization and variable selection via the elastic net [J]. Journal of the Royal Statistical Society, 2005, 67(5): 768.
[24] TIBSHIRANI R. Regression shrinkage and selection via the lasso [J]. Journal of the Royal Statistical Society Series B: Methodological, 1996, 73(1).
[25] TUTZ G, BINDER H. Boosting ridge regression [J]. Computational Statistics and Data Analysis, 2007, 51(12): 6044-6059.
[26] AHMAD M S, ADNAN S M, ZAIDI S,et al. A novel support vector regression (SVR) model for the prediction of splice strength of the unconfined beam specimens [J]. Construction and Building Materials, 2020, 248: 118475.
[27] GUO K, YANG G. Load-slip curves of shear connection in composite structures: prediction based on ANNs [J]. Steel and Composite Structures, 2020, 36(5): 493-506.
[28] 史忠植. 神经网络 [M]. 北京:高等教育出版社, 2009.
[29] NGUYEN-TUONG D, SEEGER M W, PETERS. Model Learning with Local Gaussian Process Regression [J]. Advanced Robotics, 2009, 23(15): 2015-2034.
[30] RICHARDSON R R, OSBORNE M A, HOWEY D A. Gaussian process regression for forecasting battery state of health [J]. Journal of Power Sources, 2017, 357: 209-219.
[31] DEISENROTH M P, FOX D, RASMUSSEN C E. Gaussian Processes for Data-Efficient Learning in Robotics and Control [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(2): 408-423.
[32] 李琳娜, 钟东望, 黄小武,等. 基于动态预测的深水爆炸试验容器可靠性分析 [J]. 爆炸与冲击, 2021, 41(01): 117-124.
LI Lin-na,ZHONG Dong-wang,HUANG Xiao-wu,et al. Reliability analysis of deepwater explosion test vesselbased on dynamic prediction [J]. Explosion and Shock Waves, 2021, 41(01): 117-124.
[33] 王文竹, 李杰, 刘刚,等. 基于Kriging代理模型鼓式制动器稳定性的优化设计 [J]. 振动与冲击, 2021, 40(11): 134-8+62.
WANG Wen-zhu,LI Jie,LIU Gang,et al. Optimization design of drum brake stability based on Kriging surrogate model [J]. Journal of Vibration and Shock, 2021, 40(11): 134-8+62.
[34] DEB K, PRATAP A, AGARWAL S,et al. A fast and elitist multiobjective genetic algorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[35] LIU X Y, FEATHERSTON C A, KENNEDY D. Two-level layup optimization of composite laminate using lamination parameters [J]. Composite Structures, 2019, 211: 337-350.