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

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.