泵站建筑物变形面板数据聚类分析方法

娄本星; 祁洁; 马福恒; 周晨露

doi:10.12170/20220531001

泵站建筑物变形面板数据聚类分析方法

娄本星^{1, 2,},
祁洁³,
马福恒^1, ,,
周晨露³

1.
南京水利科学研究院，江苏南京 210029
2.
河海大学水利水电学院，江苏南京 210098
3.
南水北调东线江苏水源有限责任公司，江苏南京 210009

基金项目: 江苏省水利科技项目（2021006）；国家自然科学基金联合基金重点项目（U2243244）；国家重点研发计划资助项目（2019YFC1510802）

详细信息

作者简介:
娄本星（1996—），男，河南新乡人，博士研究生，主要从事水工建筑物安全监控与预警等研究。E-mail：bxlou@hhu.edu.cn

通讯作者:
马福恒（E-mail：fhma@nhri.cn）

中图分类号: TV675
计量
- 文章访问数: 0171
- HTML全文浏览量: 057
- PDF下载量: 013
出版历程
- 收稿日期: 2022-05-30
- 网络出版日期: 2023-01-03
- 刊出日期: 2023-10-29

Clustering analysis model of deformation panel data for pumping station buildings

LOU Benxing^{1, 2,},
QI Jie³,
MA Fuheng^1, ,,
ZHOU Chenlu³

1.
Nanjing Hydraulic Research Institute, Nanjing 210029, China
2.
College of Water Conservancy & Hydropower Engineering, Hohai University, Nanjing 210098, China
3.
Jiangsu Water Sources Co., Ltd., of Eastern Route of the South-to-North Water Diversion Project, Nanjing 210009, China

摘要

摘要: 泵站建筑物监测系统日益完善，监测点数量众多，传统泵站安全监测主要以单测点变形量为主，不能反映泵站建筑物整体的安全性态。以泵站垂直位移为研究对象，基于面板数据聚类理论和动态时间规整算法，建立一种融合趋势信息的泵站变形相似度指标及度量方法，以定量分析测点间监测序列的相似程度；引入空间关联矩阵，提出考虑泵站测点空间关联性的变形分区方法；在此基础上，构建基于面板数据分析方法的泵站变形测点聚类分析模型。结合南水北调某泵站枢纽，验证了模型的有效性。工程实例表明，所构建模型可以根据泵站面板数据将测点分为4个分区，能够有效描述泵站相应区域的总体变形特征和荷载特点，为泵站建筑物安全监测提供了新方法。
- 泵站建筑物 /
- 面板数据 /
- 变形性态 /
- 相似度指标 /
- 聚类分析
Abstract: The monitoring system of pump station buildings becomes increasingly perfect, with a large number of monitoring points. Currently, the monitoring sequence of single point is mainly used in the safety monitoring of pump station building, which cannot reflect the overall state. In view of this, the vertical displacement of pump station was taken as the research object, and a similarity index and corresponding measurement method were put forward to analyze the similarity of monitoring sequences of deformation for pump station quantitatively based on panel data theory and dynamic time warping algorithm. By introducing the spatial incidence matrix, the zoning method of pump station considering the position of measuring points was proposed. Finally, the cluster analysis model of deformation of pump station based on panel data analysis method was established. Then the validity of the proposed model was verified through a case study of a pump station project of the South-to-North Water Diversion Project. The results show the measuring points can be divided into four zones by using the model proposed, and the characteristics of deformation and load are clarified effectively, thus providing a novel method for the safety monitoring of the pump station buildings.
- pump station buildings /
- panel data /
- deformation behavior /
- similarity index /
- clustering analysis

HTML全文

图 1 DTW算法点对点映射图

Figure 1. Mapping diagram of DTW algorithm

下载: 全尺寸图片幻灯片

图 2 DTW算法存在的缺陷

Figure 2. Defects of DTW algorithm

下载: 全尺寸图片幻灯片

图 3 序列趋势转换

Figure 3. The method of trend conversion

下载: 全尺寸图片幻灯片

图 4 泵站建筑物结构布置

Figure 4. Structure layout of pump station buildings

下载: 全尺寸图片幻灯片

图 5 垂直位移测点布置

Figure 5. Layout of vertical displacement monitoring points

下载: 全尺寸图片幻灯片

图 6 泵站垂直位移测点聚类图

Figure 6. Clustering results of vertical displacement for pump station

下载: 全尺寸图片幻灯片

图 7 泵站垂位移测点聚类分区结果

Figure 7. Zoning results of vertical displacement for pump station

下载: 全尺寸图片幻灯片

图 8 各分区测点监测序列

Figure 8. Monitoring sequence of measuring points in four zones

下载: 全尺寸图片幻灯片

参考文献(18)

[1]	朱松松, 李同春, 冯旭松, 等. 基于有限元法和逐步回归法的泵站位移统计模型构建方法[J]. 水利水电技术,2018,49(2):49-55 doi: 10.13928/j.cnki.wrahe.2018.02.008 ZHU Songsong, LI Tongchun, FENG Xusong, et al. Finite element method and stepwise regression method-based method for constructing displacement statistical model of pumping station[J]. Water Resources and Hydropower Engineering, 2018, 49(2): 49-55. (in Chinese) doi: 10.13928/j.cnki.wrahe.2018.02.008
[2]	陈悦, 汪程, 尹文中. 基于Kohonen聚类的特高拱坝变形分区[J]. 三峡大学学报(自然科学版),2019,41(1):1-4 doi: 10.13393/j.cnki.issn.1672-948x.2019.01.001 CHEN Yue, WANG Cheng, YIN Wenzhong. Deformation partitioning of super-high arch dam based on Kohonen clustering[J]. Journal of China Three Gorges University (Natural Sciences), 2019, 41(1): 1-4. (in Chinese) doi: 10.13393/j.cnki.issn.1672-948x.2019.01.001
[3]	SHAO C F, GU C S, YANG M, et al. A novel model of dam displacement based on panel data[J]. Structural Control and Health Monitoring, 2018, 25(1): e2037. doi: 10.1002/stc.2037
[4]	CHEN B, HU T Y, HUANG Z S, et al. A spatio-temporal clustering and diagnosis method for concrete arch dams using deformation monitoring data[J]. Structural Health Monitoring, 2019, 18(5/6): 1355-1371.
[5]	LIU Y T, ZHENG D J, GEORGAKIS C, et al. Deformation analysis of an ultra-high arch dam under different water level conditions based on optimized dynamic panel clustering[J]. Applied Sciences, 2022, 12(1): 481. doi: 10.3390/app12010481
[6]	黄潇霏. 混凝土坝健康状态的实测资料时空诊断方法[D]. 南京: 河海大学, 2018. HUANG Xiaofei. Spatio-temporal health diagnosis method for concrete dam based on monitoring information[D]. Nanjing: Hohai university, 2018. （in Chinese）
[7]	施玉群, 何金平. 基于信息熵的大坝多效应量聚类融合诊断模型[J]. 水力发电学报,2013,32(5):239-243 SHI Yuqun, HE Jinping. Multiple effect quantity fusion diagnosis model of dam health based on information entropy and cluster analysis[J]. Journal of Hydroelectric Engineering, 2013, 32(5): 239-243. (in Chinese)
[8]	HU J, MA F H. Zoned deformation prediction model for super high arch dams using hierarchical clustering and panel data[J]. Engineering Computations, 2020, 37(9): 2999-3021. doi: 10.1108/EC-06-2019-0288
[9]	牛景太, 姜灵, 邓志平, 等. 基于原型监测资料的特高拱坝变形实时风险率模型[J]. 水资源与水工程学报,2021,32(5):166-174 doi: 10.11705/j.issn.1672-643X.2021.05.22 NIU Jingtai, JIANG Ling, DENG Zhiping, et al. Real-time risk rate model for deformation of ultra-high arch dams based on prototype monitoring data[J]. Journal of Water Resources and Water Engineering, 2021, 32(5): 166-174. (in Chinese) doi: 10.11705/j.issn.1672-643X.2021.05.22
[10]	黄成章, 顾冲时, 何菁. 混凝土坝变形监测缺失数据处理新方法[J]. 水利水电科技进展,2022,42(2):89-94 HUANG Chengzhang, GU Chongshi, HE Jing. A novel method for processing missing data of concrete dam deformation[J]. Advances in Science and Technology of Water Resources, 2022, 42(2): 89-94. (in Chinese)
[11]	孙冬璞, 曲丽. 时间序列特征表示与相似性度量研究综述[J]. 计算机科学与探索,2021,15(2):195-205 doi: 10.3778/j.issn.1673-9418.2003063 SUN Dongpu, QU Li. Survey on feature representation and similarity measurement of time series[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(2): 195-205. (in Chinese) doi: 10.3778/j.issn.1673-9418.2003063
[12]	李因果, 何晓群. 面板数据聚类方法及应用[J]. 统计研究,2010,27(9):73-79 doi: 10.3969/j.issn.1002-4565.2010.09.011 LI Yinguo, HE Xiaoqun. Panel data clustering method and application[J]. Statistical Research, 2010, 27(9): 73-79. (in Chinese) doi: 10.3969/j.issn.1002-4565.2010.09.011
[13]	褚洪洋, 柴跃廷, 刘义. 基于层次分裂算法的价格指数序列聚类[J]. 清华大学学报(自然科学版),2015,55(11):1178-1183 doi: 10.16511/j.cnki.qhdxxb.2015.21.010 CHU Hongyang, CHAI Yueting, LIU Yi. Cluster analysis of a price index series based on the hierarchical division algorithm[J]. Journal of Tsinghua University (Science and Technology), 2015, 55(11): 1178-1183. (in Chinese) doi: 10.16511/j.cnki.qhdxxb.2015.21.010
[14]	王玲, 孟建瑶, 徐培培, 等. 基于多维时间序列形态特征的相似性动态聚类算法[J]. 工程科学学报,2017,39(7):1114-1122 WANG Ling, MENG Jianyao, XU Peipei, et al. Similarity dynamical clustering algorithm based on multidimensional shape features for time series[J]. Chinese Journal of Engineering, 2017, 39(7): 1114-1122. (in Chinese)
[15]	林钱洪, 王志海, 原继东, 等. 基于趋势信息的时间序列分类方法[J]. 中国科学技术大学学报,2019,49(2):138-148 LIN Qianhong, WANG Zhihai, YUAN Jidong, et al. Trend information for time series classification[J]. Journal of University of Science and Technology of China, 2019, 49(2): 138-148. (in Chinese)
[16]	李海林, 杨丽彬. 基于增量动态时间弯曲的时间序列相似性度量方法[J]. 计算机科学,2013,40(4):227-230 doi: 10.3969/j.issn.1002-137X.2013.04.049 LI Hailin, YANG Libin. Similarity measure for time series based on incremental dynamic time warping[J]. Computer Science, 2013, 40(4): 227-230. (in Chinese) doi: 10.3969/j.issn.1002-137X.2013.04.049
[17]	乔美英, 刘宇翔, 陶慧. 一种基于信息熵和DTW的多维时间序列相似性度量算法[J]. 中山大学学报(自然科学版),2019,58(2):1-8 doi: 10.13471/j.cnki.acta.snus.2019.02.001 QIAO Meiying, LIU Yuxiang, TAO Hui. A similarity metric algorithm for multivariate time series based on information entropy and DTW[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2019, 58(2): 1-8. (in Chinese) doi: 10.13471/j.cnki.acta.snus.2019.02.001
[18]	刘云霞. 基于动态时间规整的面板数据聚类方法研究及应用[J]. 统计研究,2016,33(11):93-101 LIU Yunxia. Research and application of panel data clustering method based on dynamic time warping[J]. Statistical Research, 2016, 33(11): 93-101. (in Chinese)

施引文献(15)

期刊类型引用(10)

1.	刘俊谊，焦经纬，谢朝勇，马冬冬，施建明. 装配式快速堵口临时堤坝的稳定性分析. 水利水运工程学报. 2021(02): 72-77 . 本站查看
2.	黄健华. 基于水力模型试验的堤防工程安全运营分析研究. 水利科技与经济. 2021(06): 52-58 . 百度学术
3.	陈榕. 正四面体钢架在小型决口封堵中的技术应用. 水利科学与寒区工程. 2021(06): 96-98 . 百度学术
4.	刘昉，戚园春，侯庆志，吴敏睿，冉聃颉，冯卫鹏. 冻土条件下无黏性土堤漫顶溃决试验研究. 水利水电技术(中英文). 2021(12): 146-156 . 百度学术
5.	邓成进，党发宁，陈兴周，袁秋霜，陈莉丽. 库区滑坡涌浪三维数值模拟分析. 水利水运工程学报. 2020(06): 64-71 . 本站查看
6.	王笑，陈辉，张东，王赵明，赵溦. 溃坝波数值模拟及其在坡面水流问题中的应用. 水电能源科学. 2019(08): 30-33 . 百度学术
7.	曾秀娟，谢涛. 不同水头与流量条件下堤防梯形决口水流特性数值模拟. 江西水利科技. 2018(01): 15-21 . 百度学术
8.	胡海松. 基于flow-3d软件溢流坝不同鼻坎角度的三维数值模拟. 人民珠江. 2017(08): 72-75+83 . 百度学术
9.	谢秀新，邹浩，刘路. 那苏瓦卡里水电站排砾廊道FLOW-3D水力模拟分析. 中国水运(下半月). 2017(10): 73-76 . 百度学术
10.	谢秀新，邹浩，刘路. 那苏瓦卡里水电站排砾廊道FLOW-3D水力模拟分析. 中国水运(下半月). 2017(20): 73-76 . 百度学术