重载汽车引起的场地振动在产生和传递过程中受车重、车速、路面不平顺等级、土体参数等多场耦合影响,其传递衰减规律不明且难以准确预测.探讨了车重、车速、路面不平顺等级、土体参数与振动衰减性能之间的关系,首先基于数值模型建立了车致振动数据库,随后采用麻雀搜索算法(sparrow search algorithm,SSA)优化误差反向传播(back propagation,BP)神经网络训练得到交通荷载下不同场地振动响应及衰减规律的预测模型SSA-BP,并基于博弈论的SHAP (Shapley additive explanation)算法进行模型可解释性分析.研究结果表明:数值模型能够准确模拟重载汽车引起的地面振动传播,与原位试验数据在时域和频域特性上高度一致;BP模型在处理高离散性数据时预测误差超过10%,而SSA-BP模型对各类数据集均保持较高预测精度;粉土环境下车速对周围环境产生的振动加速度影响相关性最大,黏土、砾石环境下距振动源距离对周围环境产生的振动加速度影响相关性最大.SHAP值分析显示,随剪切波速的减小,车速影响呈先减小后增大的趋势,而车重和路面不平顺等级的影响呈逐渐增大的趋势.
Ground vibrations caused by overloaded vehicles are influenced by factors such as vehicle weight, speed, road surface roughness, and soil parameters, making their attenuation patterns complex and difficult to accurately predict. This study characterizes and predicts the relationships between vehicle weight, speed, road surface roughness, soil parameters, and vibration attenuation performance. A prediction model for vibration response and attenuation at different sites under traffic loads is developed using a sparrow search algorithm (SSA)-optimized back propagation (BP) neural network. Additionally, a game-theory-based Shapley additive explanation (SHAP) algorithm is used for the model inter-pretability analysis. The results show that the model accurately simulates ground vibration propagation due to overloaded vehicles with high consistency in time- and frequency-domain characteristics when compared to field test data. Although the BP model exhibits prediction errors exceeding 10% for high-dispersity data, the SSA-BP model maintains high prediction accuracy across various datasets. In silty soil environments, the vehicle speed exhibits the strongest correlation with the vibration acceleration in the surrounding environment, whereas in clay and gravel environments, the distance from the vibration source exhibits the strongest correlation. The SHAP value analysis indicates that with the decrease in shear wave velocity, the effect of driving speed initially decreases and then increases, whereas the effects of vehicle weight and road surface grade gradually increase.
[1] 周云. 交通荷载对周边建筑的振动影响分析[D]. 浙江: 浙江大学, 2005.
[2] Lamb E H. On the propagation of tremors over the surface of an elastic solid [J]. Philosophical Transactions of the Royal Society of London, 1904, 203: 1-42.
[3] Miller G F, Pursey H. On the partition of energy between elastic waves in a semi-infinite solid [J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1955, 233(1192): 55-69.
[4] Woods R D. Screening of surface wave in soils [J]. Journal of the Soil Mechanics & Foundations Division, 1968, 94: 951-980.
[5] Mohanna M, Sadek M, Shahrour I. Numerical modeling of traffic-induced ground vibration [J]. Computers & Geotechnics, 2012, 39(39): 116-123.
[6] 严涛, 肖新标, 金学松, 等. 地铁列车运行引起的环境振动3 维数值分析[J]. 铁道建筑, 2010(7): 67-69.
[7] 和振兴, 翟婉明, 罗震. 地铁列车引起的地面振动[J]. 西南交通大学学报, 2008, 43(2): 218-221.
[8] 夏禾, 张楠, 曹艳梅. 列车对周围地面及建筑物振动影响的试验研究[J]. 铁道学报, 2004, 26(4): 93-98.
[9] 中华人民共和国第一机械工业部. 动力机器基础设计规范: GBJ40—79[S]. 北京: 中国建筑工业出版社, 1980.
[10] 苏宇, 刘维宁, 范欢, 等. 神经网络用于地铁列车振动在地层中传播规律预测的研究[C]// 2007中国交通高层论坛. 2012: 243-247.
[11] Yao J B, Xia H, Zhang N, et al. Prediction on building vibration induced by moving train based on support vector machine and wavelet analysis [J]. Journal of Mechanical Science and Technology, 2014, 28(6): 2065-2074.
[12] 倪小东, 张宇科, 焉磊, 等. 基于HSS-MCC融合模型及SSA-BP神经网络开展深基坑超大变形预测研究[J]. 湖南大学学报(自然科学版), 2024, 51(9): 1-11.
[13] 熊仲明, 熊俊龙, 王泽坤, 等. 基于神经网络的跨越地裂缝框架结构地震损伤及预测研究[J]. 防灾减灾工程学报, 2024, 44(2): 362-371.
[14] 李莉, 管婷婷. 考虑多种损坏构成特征的沥青路面预防性养护决策方法[J]. 上海大学学报(自然科学版), 2022, 28(4): 689-701.
[15] 陈璠. 环境激励下的场地振动衰减规律试验研究[D]. 北京: 北京建筑大学, 2019.
[16] 许暮迪, 张辉, 花雨萌, 等. 空间框架式客运车站振动舒适度分析[J]. 铁道科学与工程学报, 2020, 17(10): 2635-2641.
[17] 张新豪, 孙昊, 孙继梅. 基于车致振动响应的双层钢桁梁桥行人舒适性评价[C]// 2023世界交通运输大会(WTC2023). 2023: 7.
[18] Wang H, Zhang C, Jiang D S T. Vibration characteristics and isolation in vibration-sensitive areas under moving vehicle load [J]. Soil Dynamics and Earthquake Engineering, 2022, 153(2): 107077.
[19] 罗文俊, 曹浩. 空沟和废弃轮胎填充沟隔振效果的有限元分析[J]. 建筑结构, 2020, 50(S2): 360-365.
[20] 张锋, 冯德成, 凌贤长, 等. 重载汽车-路面-路基垂向耦合动力学模型[J]. 中国公路学报, 2015, 28(4): 1-12.
[21] 詹苏涛. 基于刚度不均匀性的重载汽车作用下沥青路面的动力响应[D]. 哈尔滨: 哈尔滨工业大学, 2013.
[22] 国家市场监督管理总局, 国家标准化管理委员会. 机械振动道路路面谱测量数据的报告: GB/T 7031—2005[S]. 北京: 中国标准出版社, 2005.
[23] 白建方, 楼梦麟. 行波输入下土层有限元网格的划分原则[J]. 世界地震工程, 2009, 25(1): 48-51.
[24] 刘桓. 双排隔振桩对铁路振动隔振效果试验研究[D]. 张家口: 河北建筑工程学院, 2020.
[25] 周警. 精密设备基础减振隔振技术研究[D]. 南京: 东南大学, 2019.
[26] Yang Y B, Ge P, Li Q, et al. 2.5D vibration of railway-side buildings mitigated by open or infilled trenches considering rail irregularity [J]. Soil Dynamics and Earthquake Engineering, 2018, 106: 204-214.
[27] 薛建凯. 一种新型的群智能优化技术的研究与应用[D]. 上海: 东华大学, 2021.
[28] Ye M, Li L, Yoo D Y, et al. Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation [J]. Construction and Building Materials, 2023, 408: 133752.
