基于数据驱动的给水管网爆管信号识别综述  

Overview of Data-Driven Identification of Pipe Bursting Signals of Water Supply Network

作　　者：陶剑 何立新[1,2] 王昊[3] 龙岩[1,2] TAO Jian;HE Li-xin;WANG Hao;LONG Yan(School of Water Conservancy and Hydroelectric Power,Hebei University of Engineering,Handan 056038,China;Hebei Key Laboratory of Intelligent Water Conservancy,Hebei University of Engineering,Handan 056038,China;School of Civil and Transportation Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]河北工程大学水利水电学院,河北邯郸056038 [2]河北工程大学河北省智慧水利重点实验室,河北邯郸056038 [3]北京工业大学城市建设学部,北京100124

出　　处：《海河水利》2023年第5期66-69,73,共5页Haihe Water Resources

摘　　要：通过数据驱动方法对给水管网爆管进行预测是近些年兴起的新方法。以数据驱动为核心,从数据预处理、数据驱动方法类别和模型性能评估对方法进行说明,并在数据驱动方法类别中从分类、预测-分类、统计过程控制3个维度详细论述了不同方法的优劣,最后给出了参考性结论和建议,可为基于数据驱动的给水管网爆管信号识别相关研究提供参考。Predicting pipe bursting in water supply network through a data-driven approach is a new method that has emerged in recent years.Taking data-driven as the core,the method is explained from the data preprocessing,category of data-driven methods and model performance evaluation.The advantages and disadvantages of different methods are discussed in detail in terms of classification,prediction-classification and statistical process control in the data-driven method category.Finally,this paper provides a reference conclusion and suggestion for research on data-driven identification of water supply network bursting signals,which can be used for reference.

关 键 词：数据驱动 给水管网 分类 预测-分类 统计过程控制 

分 类 号：TU991.38[建筑科学—市政工程]