WU Yi-wen,DU Kun,WU Han?qing,et al.Water Supply Network Burst Detection Based on Least Squares Support Vector Machine Interactive Prediction[J].China Water & Wastewater,2022,38(9):58-63.
基于LSSVM交互预测的供水管网爆管检测
- Title:
- Water Supply Network Burst Detection Based on Least Squares Support Vector Machine Interactive Prediction
- 关键词:
- 供水管网; 爆管; 最小二乘支持向量机(LSSVM); 交互预测
- Keywords:
- water supply network; pipe burst; LSSVM; interactive prediction
- 摘要:
- 随着我国越来越多的供水管网安装SCADA系统，基于数据预测的爆管检测方法越来越受到重视。传统基于数据预测的方法大多根据单点流量、压力的历史监测数据预测当前时刻监测值，当预测值与监测值的差值超过阈值时判定为爆管。然而，实践经验表明，监测数据的丢失与错误会严重影响单点预测结果，进而引起频繁误报与漏报。考虑到实际用水及监测数据的空间关联性（例如水压监测点布置距离越近其监测数据相关性越大），开展了基于最小二乘支持向量机（LSSVM）交互预测的供水管网爆管检测研究。对管网中不同位置监测数据构建多输入单输出LSSVM交互预测模型，选取1倍标准差为阈值进行爆管检测，并与传统的卡尔曼滤波爆管检测结果相对比。结果表明，LSSVM交互预测模型能降低数据丢失、数据错误对预测结果的影响，且对较小的爆管响应更加灵敏，进而有效地提高了基于数据预测的爆管检测性能。
- Abstract:
- With an increasing number of SCADA system installed in the water supply network, the method of pipe burst detection based on data prediction has been paid more and more attention. Most of the traditional methods based on data prediction predict the current monitoring value according to the historical monitoring data of single point flow and pressure. When the difference between the predicted value and the monitoring value exceeds the threshold, the pipe burst was identified. However, practical experience shows that the loss and error of monitoring data will seriously affect the single point prediction results, and then cause frequent false positives and missing reports. Considering the spatial correlation between actual water consumption and monitoring data (for example, the closer the distance of water pressure monitoring points is, the greater the correlation of monitoring data is), water supply network pipe burst was detected based on least squares support vector machine (LSSVM) interactive prediction. A multi input and single output LSSVM interactive prediction model was constructed based on the monitoring data of different positions in the pipe network. A double standard deviation was selected as the threshold value for pipe burst detection, and the detection results were compared with those of traditional Kalman filtering. LSSVM interactive prediction model could reduce the influence of data loss and data error on the prediction results, and was more sensitive to small pipe burst, thus effectively improving the performance of pipe burst detection based on data prediction.
相似文献/References:
[1]程伟平,陈亚威,许刚,等.基于遗传算法的供水管网爆管监控网络布置研究[J].中国给水排水,2020,36(15):46.
CHENG Wei-ping,CHEN Ya-wei,XU Gang,et al.Layout of Burst Monitoring Network in Water Distribution System Based on Genetic Algorithm[J].China Water & Wastewater,2020,36(9):46.
[2]程伟平,张邢,龙志宏,等.基于粒子源逆向追踪算法的管网污染源快速定位技术[J].中国给水排水,2020,36(19):50.
CHENG Wei-ping,ZHANG Xing,LONG Zhi-hong,et al.Rapid Pollution Source Location Technology in Water Distribution System Based on Particle Back-tracking Algorithm[J].China Water & Wastewater,2020,36(9):50.
[3]褚福敏,孙韶华,逯南南,等.供水管网中耐氯菌的分离鉴定及特性分析[J].中国给水排水,2020,36(21):42.
CHU Fu-min,SUN Shao-hua,LU Nan-nan,et al.Isolation, Identification and Characteristic Analysis of Chlorine-resistant Bacteria in Urban Water Supply Pipe Network[J].China Water & Wastewater,2020,36(9):42.
[4]吴潇勇,艾静,王圣,等.输配分离供水管网布局的构建与影响评估[J].中国给水排水,2020,36(21):53.
WU Xiao-yong,AI Jing,WANG Sheng,et al.Construction and Impact Assessment of Water Supply Network Layout with Separating Water Supply and Distribution Pipes[J].China Water & Wastewater,2020,36(9):53.
[5]苏炯恒,王琦,王礼炳,等.考虑成本–弹性–水质的供水管网多目标协同设计方法[J].中国给水排水,2020,36(21):58.
SU Jiong-heng,WANG Qi,WANG Li-bing,et al.A Multi-objective Coordinated Design Method for Water Distribution Networks Considering Cost, Resilience and Water Quality[J].China Water & Wastewater,2020,36(9):58.
[6]岳宏宇,吕谋,李红卫,等.基于群体智能优化算法的供水管网压力监测点布置[J].中国给水排水,2020,36(21):66.
YUE Hong-yu,L Mou,LI Hong-wei,et al.Arrangement of Pressure Monitoring Points in Water Supply Network Based on Swarm Intelligence Optimization Algorithm[J].China Water & Wastewater,2020,36(9):66.
[7]吉瑞博,王志红,龙志宏,等.基于风险评估的供水管网水质监测点优化模型研究[J].中国给水排水,2021,37(3):52.
JI Rui-bo,WANG Zhi-hong,LONG Zhi-hong,et al.Water Quality Monitoring Points Optimization Model for Water Supply Network Based on Risk Assessment[J].China Water & Wastewater,2021,37(9):52.
[8]杨佳莉,杜坤,陈洋,等.基于冗余选择策略差分进化的供水管网多目标优化[J].中国给水排水,2021,37(9):40.
YANG Jia-li,DU Kun,CHEN Yang,et al.Multi-objective Optimization of Water Distribution System Based on Differential Evolution of Redundant Selection Strategy[J].China Water & Wastewater,2021,37(9):40.
[9]卢慢,杜坤,宋志刚,等.基于耦合统计及模型驱动的供水管网爆管定位[J].中国给水排水,2021,37(9):46.
LU Man,DU Kun,SONG Zhi-gang,et al.Burst Location of Water Supply Pipe Network Based on Coupling Statistics and Model Driven[J].China Water & Wastewater,2021,37(9):46.
[10]龚珑聪,卓雄,许俊鸽.基于NB-IoT和DMA技术相结合的小区漏损控制分析[J].中国给水排水,2021,37(13):40.
GONG Long-cong,ZHUO Xiong,XU Jun-ge.Analysis of Leakage Management in Community Based on Combination of NB-IoT and DMA Technology[J].China Water & Wastewater,2021,37(9):40.
[11]赵文轩,杜坤,孟繁艺,等.面向爆管检测的供水管网水压监测点多目标优化[J].中国给水排水,2023,39(7):57.
ZHAOWen-xuan,DUKun,MENGFan-yi,et al.Multi-objective Optimization of Water Pressure Monitoring Points for Pipe Burst Detection in Water Supply Networks[J].China Water & Wastewater,2023,39(9):57.