[1]王威,丛旭,武佳佳,等.城市供水管网漏损动态预测的Bootstrap-Lee-Carter模型*[J].中国安全生产科学技术,2021,17(6):30-35.[doi:10.11731/j.issn.1673-193x.2021.06.005]
WANG Wei,CONG Xu,WU Jiajia,et al.Bootstrap-Lee-Carter model for dynamic prediction of leakage in urban water supply pipeline network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(6):30-35.[doi:10.11731/j.issn.1673-193x.2021.06.005]
点击复制
城市供水管网漏损动态预测的Bootstrap-Lee-Carter模型*
WANG Wei,CONG Xu,WU Jiajia,et al.Bootstrap-Lee-Carter model for dynamic prediction of leakage in urban water supply pipeline network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(6):30-35.[doi:10.11731/j.issn.1673-193x.2021.06.005]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 17
- 期数:
- 2021年6期
- 页码:
- 30-35
- 栏目:
- 学术论著
- 出版日期:
- 2021-06-30
文章信息/Info
- Title:
- Bootstrap-Lee-Carter model for dynamic prediction of leakage in urban water supply pipeline network
- 文章编号:
- 1673-193X(2021)-06-0030-06
- 关键词:
- 供水管网; 漏损; Lee-Carter模型; Bootstrap方法; 管道漏点率
- Keywords:
- water supply pipeline network; leakage; Lee-Carter model; Bootstrap method; pipeline leakage rate
- 分类号:
- X959
- 文献标志码:
- A
- 摘要:
- 为对某城市供水片区的不同管径和管材的管道漏点率进行动态预测，考虑城市供水管网漏损时变特征，采用Bootstrap方法估计Lee-Carter参数模型。针对供水管网漏点率进行经典Lee-Carter模型预测，并通过残差等高线图及其同方差性质检验，比较分析最小二乘法和加权最小二乘法估计Lee-Carter模型参数的拟合效果；考虑供水管网漏损时变引起的模型参数不确定性扰动，利用残差Bootstrap方法抽样模拟Lee-Carter模型参数置信区间和模型改进后的供水管网漏损预测结果。结果表明：Bootstrap-Lee-Carter模型相比经典Lee-Carter模型具有更高的预测精度。
- Abstract:
- In order to dynamically predict the leakage rate of pipelines with different diameters and materials in a certain urban water supply area,considering the time-varying characteristics of the leakage in urban water supply pipeline network,the Bootstrap method was used to estimate the Lee-Carter parameter model.The classical Lee-Carter model was used to predict the leakage rate of water supply pipeline network,and through the residual contour map and the homoscedasticity test,the least square method and the weighted least square method were used to estimate the fitting effect of the parameters in Lee-Carter model.Considering the uncertainty perturbation of model parameters caused by the time-varying leakage of the water supply pipeline network,the confidence interval of parameters in Lee-Carter model and the prediction results of water supply pipeline network leakage of the improved model were simulated with sampling by using the residual Bootstrap method.The results showed that the Bootstrap-Lee-Carter model had higher prediction accuracy than the classical Lee-Carter model.
参考文献/References:
［1］BARTON N A,FAREWELL T S,HALLETT S H,et al.Improving pipe failure predictions:factors affecting pipe failure in drinking water networks ［J］.Water Research,2019,164:114926.
［2］王圃,邱云龙,夏清泉,等.组合模型在给水管网漏损预测中的应用［J］.中国给水排水,2006(17):67-69.
WANG Pu,QIU Yunlong,XIA Qingquan,et al.Application of combined model in leakage prediction of water supply network ［J］.China Water & Wastewater,2006(17):67-69.
［3］邱云龙.给水管网漏损预测的研究与应用［D］.重庆：重庆大学,2006.
［4］王丽娟,张宏伟.差分自回归移动平均模型预测管网漏损的研究［J］.中国给水排水,2010,26(11):127-129.
WANG Lijuan,ZHANG Hongwei.Research on differential autoregressive moving average model to predict pipe network leakage ［J］.China Water & Wastewater,2010,26(11):127-129.
［5］KANG J,ZOU Z H.Timeprediction model for pipeline leakage based on grey relational analysis ［J］.Physics Procedia,2012,25:2019-2024.
［6］包涵,刘遂庆.灰色模型在供水管网漏损预测中的应用比较［J］.给水排水,2010,46(1):157-159.
BAO Han,LIU Suiqing.Application comparison of grey model in leakage prediction of water supply pipe network ［J］.Water Supply and Drainage,2010,46(1):157-159.
［7］王志红,王保民.基于灰色马尔可夫链的管网漏损率预测［J］.山西建筑,2016,42(2):129-131.
WANG Zhihong,WANG Baomin.Pipe network leakage rate prediction based on grey Markov chain ［J］.Shanxi Construction,2016,42(2):129-131.
［8］DONGWOO J,HYOSEON P,GYEWOON C.Estimation of leakage ratio using principal component analysis and artificial neural network in water distribution systems ［J］.Sustainability,2018,10(3):1-13.
［9］邵圆媛.嵌套BP/GMS神经网络模型在供水管网漏损预测中的研究［D］.重庆：重庆大学,2018.
［10］汪健.基于小波神经网络对供水管网的研究［D］.昆明：昆明理工大学,2016.
［11］刘晓然,王威,杨谆,等.供水管网漏损影响因子相关性特征模拟与动态分级控制［J］.西安建筑科技大学学报(自然科学版),2019,51(3):440-446.
LIU Xiaoran,WANG Wei,YANG Zhun,et al.Simulation and dynamic hierarchical control of correlation characteristics of water supply pipeline network leakage influencing factors ［J］.Journal of Xi’an University of Architecture and Technology (Natural Science Edition),2019,51(3):440-446.
［12］LEE R D,CARTER L R.Modeling and forecasting US mortality ［J］.Journal of the American Statistical Association,1992,87(419):659-671.
［13］曾燕,陈曦,邓颖璐.创新的动态人口死亡率预测及其应用［J］.系统工程理论与实践,2016,36(7):1710-1718.
ZENG Yan,CHEN Xi,DENG Yinglu.Innovative dynamic population mortality prediction and its application ［J］.System Engineering Theory and Practice,2016,36(7):1710-1718.
［14］赵明宪,饶碧玉,王静.基于集对分析的城市供水管网漏损预测及降漏研究［J］.山东科学,2018,31(2):120-126.
ZHAO Mingxian,RAO Biyu,WANG Jing.Research on leakage prediction and leakage reduction of urban water supply pipe network based on set pair analysis ［J］.Shandong Science,2018,31(2):120-126.
［15］程琮,范华.Levene方差齐性检验［J］.中国卫生统计,2005(6):408-420.
CHENG Cong,FAN Hua.Levenetest for homogeneity of variance［J］.Chinese Health Statistics,2005(6):408-420.
相似文献/References:
[1]刘朝峰,兰玥,张晓博,等.供水管网震后流量监测点的动态分级优化布局研究[J].中国安全生产科学技术,2018,14(1):12.[doi:10.11731/j.issn.1673-193x.2018.01.002]
LIU Chaofeng,LAN Yue,ZHANG Xiaobo,et al.Study on dynamic classification for layout optimization of
post-earthquake flow monitoring points in water supply network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(6):12.[doi:10.11731/j.issn.1673-193x.2018.01.002]
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-04-30
* 基金项目： 国家自然科学基金项目（51678017,51978023）
作者简介： 王威，博士，副研究员，主要研究方向为城市与工程安全减灾。
