DECOUPLED STOCHASTIC MODEL AND SURVEY METHOD FOR EXTRAORDINARY LOAD
-
摘要:
临时性活荷载是建筑楼面活荷载的重要部分，但基于荷载单元的传统模型造成现场调查困难，样本匮乏导致临时性活荷载研究长期停滞不前。对此，研究提出了临时性活荷载的解耦随机模型，将活荷载解耦为数量和幅值两种独立随机变量，既可对不同临时性活荷载事件统一建模，也可对荷载的数量和幅值分别采样统计而大大方便了荷载调查。与解耦随机模型相配合，进一步研究了结合目标检测和多目标跟踪的机器视觉调查方法，利用泛在监控设施实现临时性活荷载的持续性调查。以常见人群聚集型临时性活荷载为例，阐述了机器视觉调查方法的实施过程，并通过实际场景下的调查实验验证了调查方法的有效性。解耦随机模型结合机器视觉调查方法为临时性活荷载大样本的获取以及楼面活荷载设计值的研究提供了可行的新方式。
Abstract:Extraordinary load is an essential part of the live load on buildings. However, the traditional model based on load cells makes the field survey be difficult, and the lack of survey data has led to the long-term stagnation of extraordinary load studies. This study proposes a decoupled stochastic model for extraordinary load, which decouples extraordinary load into two independent random variables of load quantity and magnitude. The proposed model enables unified modeling of different extraordinary load events and simplifies the load investigation by conducting sample statistics separately. Based on the decoupled stochastic model, a machine vision survey method, combining object detection and multiple-object tracking, is further proposed to conduct extraordinary load surveys sustainably using widespread public surveillance facilities. Taking the extraordinary load of crowd gathering as an example, the implementation of the machine vision survey method is presented, and the effectiveness of the new survey method is verified by the survey experiment under actual scenes. The decoupled stochastic model combined with the machine vision survey method provides a feasible way to obtain large samples of extraordinary load and study the design value of floor live loads.
-
Keywords:
- extraordinary load /
- live load survey /
- live load /
- object detection /
- multiple-object tracking
-
-
![]()
图 6 人群头部检测数据集的示例图像与标注样本
Figure 6. Images and annotation samples of the crowd head detection dataset
![]()
图 8 拥挤情况下人群头部跟踪结果示例
Figure 8. Examples of crowd head tracking results under crowded condition
表 1 调查场景详细信息
Table 1 Details of survey scenes
场景 调查区域 区域面积/
m2摄像头
数量调查时长/
s场景1 教室 79 1 120 场景2 走廊 25 2 120 场景3 教室、走廊 247 4 120 场景4 教室、走廊、大厅、楼梯 633 6 120 
下载: 导出CSV
表 2 不同图像尺寸下机器视觉调查方法的评估指标
Table 2 Evaluation metrics for machine vision survey method at different image sizes
图像尺寸 均方根误差 最大值相对误差/(%) 调查时间/s 384 1.57 4.01 81.3 448 0.98 1.95 82.2 512 1.22 2.30 84.2 576 0.81 0.71 89.5 640 0.68 0.70 91.1 704 0.72 1.03 96.9 768 0.65 0.92 99.2
下载: 导出CSV
-
[1] 曹振熙, 曹普. 建筑工程结构荷载学[M]. 北京: 中国水利水电出版社, 2006: 1 − 4. CAO Zhenxi, CAO Pu. Load of civil engineering structure [M]. Beijing: China Water Power Press, 2006: 1 − 4. (in Chinese)
[2] GB 55001−2021, 工程结构通用规范[S]. 北京: 中国建筑工业出版社, 2021. GB 55001−2021, General code for engineering structures [S]. Beijing: China Architecture & Building Press, 2021. (in Chinese)
[3] JIN X Y, ZHAO J D. Development of the design code for building structures in China [J]. Structural Engineering International, 2012, 22(2): 195 − 201. doi: 10.2749/101686612X13291382990886
[4] 陈隽, 李洋, 臧笛. 建筑活荷载的大数据调查方法研究[J]. 同济大学学报(自然科学版), 2020, 48(2): 208 − 214. CHEN Jun, LI Yang, ZANG Di. Research on big data survey method of building live load [J]. Journal of Tongji University (Natural Science), 2020, 48(2): 208 − 214. (in Chinese)
[5] 《建筑结构设计统一标准》编委会荷载组. 办公楼与住宅楼面活荷载的统计分析[J]. 冶金建筑, 1982(1): 56 − 61. Load Group of Editorial Committee of Unified Standard for Design of Building Structures. Statistical analysis of floor live loads on office buildings and residential [J]. Industrial Construction, 1982(1): 56 − 61. (in Chinese)
[6] CHOI E C C. Extraordinary live load in office buildings [J]. Journal of Structural Engineering, 1991, 117(11): 3216 − 3227. doi: 10.1061/(ASCE)0733-9445(1991)117:11(3216)
[7] MCGUIRE R K, CORNELL C A. Live load effects in office buildings [J]. Journal of the Structural Division, 1974, 100(7): 1351 − 1366. doi: 10.1061/JSDEAG.0003816
[8] ELLINGWOOD B, CULVER C. Analysis of live loads in office buildings [J]. Journal of the Structural Division, 1977, 103(8): 1551 − 1560. doi: 10.1061/JSDEAG.0004693
[9] CHOI E C C. Live load for office buildings: Effect of occupancy and code comparison [J]. Journal of Structural Engineering, 1990, 116(11): 3162 − 3174. doi: 10.1061/(ASCE)0733-9445(1990)116:11(3162)
[10] ANDAM K A. Variability in stochastic sustained and extraordinary load processes [J]. Building and Environment, 1990, 25(4): 389 − 396. doi: 10.1016/0360-1323(90)90013-H
[11] 吴小强, 姚继涛, 刘雅君. 住宅楼面活荷载的统计分析及楼板可靠度的分析[J]. 工程力学, 2012, 29(3): 90 − 94. WU Xiaoqiang, YAO Jitao, LIU Yajun. Statistical analysis of live load on residence floor and analysis of residence floor reliability [J]. Engineering Mechanics, 2012, 29(3): 90 − 94. (in Chinese)
[12] 陈淮, 葛素娟, 李静斌, 等. 中原地区住宅建筑结构活荷载调查与统计分析[J]. 土木工程学报, 2006, 39(5): 29 − 34, 64. CHEN Huai, GE Sujuan, LI Jingbin, et al. Survey and statistical analysis of live loads of residential buildings in the central plains region [J]. China Civil Engineering Journal, 2006, 39(5): 29 − 34, 64. (in Chinese)
[13] PEIR J C. A stochastic live load model for buildings [D]. Massachusetts: Massachusetts Institute of Technology, 1972.
[14] 李杰. 论第三代结构设计理论[J]. 同济大学学报(自然科学版), 2017, 45(5): 617 − 624, 632. LI Jie. On the third generation of structural design theory [J]. Journal of Tongji University (Natural Science), 2017, 45(5): 617 − 624, 632. (in Chinese)
[15] 朱前坤, 陈建邦, 张琼, 等. 基于计算机视觉人行桥挠度影响线非接触式识别[J]. 工程力学, 2021, 38(8): 145 − 153. doi: 10.6052/j.issn.1000-4750.2020.08.0557 ZHU Qiankun, CHEN Jianbang, ZHANG Qiong, et al. A non-contact recognition for deflection influence line of footbridge based on computer vision [J]. Engineering Mechanics, 2021, 38(8): 145 − 153. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.08.0557
[16] 许泽坤, 陈隽. 非线性结构地震响应的神经网络算法[J]. 工程力学, 2021, 38(9): 133 − 145. doi: 10.6052/j.issn.1000-4750.2020.09.0645 XU Zekun, CHEN Jun. Neural network algorithm for nonlinear structural seismic response [J]. Engineering Mechanics, 2021, 38(9): 133 − 145. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.09.0645
[17] SON H, CHOI H, SEONG H, et al. Detection of construction workers under varying poses and changing background in image sequences via very deep residual networks [J]. Automation in Construction, 2019, 99: 27 − 38. doi: 10.1016/j.autcon.2018.11.033
[18] WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric [C]// Proceedings of 2017 IEEE International Conference on Image Processing (ICIP). Beijing: IEEE, 2017: 3645 − 3649.
[19] HARRIS M E, BOVA C J, COROTIS R B. Area-dependent processes for structural live loads [J]. Journal of the Structural Division, 1981, 107(5): 857 − 872. doi: 10.1061/JSDEAG.0005709
[20] ANDAM K A. Floor live loads for office buildings [J]. Building and Environment, 1986, 21(3/4): 211 − 219.
[21] KUMAR S. Live loads in office buildings: Lifetime maximum load [J]. Building and Environment, 2002, 37(1): 91 − 99. doi: 10.1016/S0360-1323(00)00075-5
[22] GLENN J, ALEX S, AYUSH C, et al. YOLOv5 [CP/OL]. https://github.com/ultralytics/yolov5, 2022-06-05.
[23] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation [C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759 − 8768.
[24] IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift [C]// Proceedings of the 32nd International Conference on Machine Learning. Lille: JMLR. org, 2015: 448 − 456.
[25] ELFWING S, UCHIBE E, DOYA K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning [J]. Neural Networks, 2018, 107: 3 − 11. doi: 10.1016/j.neunet.2017.12.012
[26] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: A new backbone that can enhance learning capability of CNN [C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle: IEEE, 2020: 1571 − 1580.
[27] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904 − 1916. doi: 10.1109/TPAMI.2015.2389824
[28] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context [C]// Proceedings of the 13th European Conference on Computer Vision. Zurich: Springer, 2014: 740 − 755.
[29] KINGMA D P, BA J. Adam: A method for stochastic optimization [J]. arXiv preprint arXiv, 2014: 1 − 15. doi: 10.48550/arXiv.1412.6980
[30] GOYAL P, DOLLÁR P, GIRSHICK R, et al. Accurate, large minibatch sgd: Training imagenet in 1 hour [J]. arXiv preprint arXiv, 2017: 1 − 12. doi: 10.48550/arXiv.1706.02677
[31] LOSHCHILOV I, HUTTER F. SGDR: Stochastic gradient descent with warm restarts [J]. arXiv preprint arXiv, 2016: 1 − 16. doi: 10.48550/arXiv.1608.03983
[32] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes (VOC) challenge [J]. International Journal of Computer Vision, 2010, 88(2): 303 − 338. doi: 10.1007/s11263-009-0275-4
[33] GB/T 10000−2023, 中国成年人人体尺寸[S]. 国家标准化管理委员会, 2023. GB/T 10000−2023, Human dimensions of Chinese adults [S]. Standardization Administration of China, 2023. (in Chinese)
-
期刊类型引用(1)
1. 曾豪, 陈隽, 李洋. 楼面活荷载影响面等效因子取值及应用研究. 工程力学. 2025(07) 
本站查看
其他类型引用(0)
计量
- 文章访问数: 200
- HTML全文浏览量: 30
- PDF下载量: 33
- 被引次数: 1
