Supplementary data for the paper "Leak detection in water supply pipeline with small-size leakage using deep learning networks"

In recent years, there has been significant advancement in pipeline transportation technology. However, the progress of this technology is impeded by a critical challenge – the issue of leakage, particularly when it comes to small-scale leaks in water pipelines that manifest weaker signals of leakage. To address those challenges, we experimental investigate leak detection in pipelines with small leaks (leakage flow accounting for only 1.60% to 1.90% of the total volume flow) under low-pressure conditions (130~220 kPa). However, the paper on the data has not been published and this data can only be used after obtaining our consent. For this reason, we only present the typical data and results. If you need to use the data, please contact us, we will be happy to share with you and more detailed description of the data.近年来，管道输送技术取得了显著进展。然而该技术的发展却受到一项关键难题的阻碍——泄漏问题，尤以输水管道的微小泄漏为甚，此类泄漏的泄漏信号往往更为微弱。为应对上述挑战，本研究针对低压工况（130~220 kPa）下的管道微小泄漏（泄漏流量仅占总容积流量的1.60%~1.90%）开展了泄漏检测实验研究。但本数据集相关论文尚未发表，该数据集仅可在获得我方授权后方可使用。因此，本次仅展示典型数据与实验结果。若您有使用该数据集的需求，请与我方联系，我们将乐于为您提供分享及更详尽的数据集说明。

搜集汇总

背景与挑战

背景概述

该数据集是用于支持深度学习网络检测供水管道中小规模泄漏的研究，包含低压力条件（130~220 kPa）下泄漏流量仅占总流量1.60%至1.90%的实验数据。由于相关论文尚未发表，数据需获得同意后方可使用，目前仅提供典型数据和结果示例。