Zhang Yi, Li Suzhen
College of Civil Engineering, Tongji University, Siping 1239, Shanghai 200092, China.
State Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Siping 1239, Shanghai 200092, China.
Sensors (Basel). 2025 Aug 15;25(16):5069. doi: 10.3390/s25165069.
Accurate monitoring of leakage in urban water supply pipelines is crucial for ensuring the safety of residential water usage. This study proposes a robust physical indicator for identifying leaks in urban water pipelines, grounded in the physical background of leakage noise sources. An integral form of the leakage source noise power spectral density is established, and a rigorous theoretical analysis leads to the development of an effective physical indicator. This indicator addresses the limitation of existing leakage detection methods that overly rely on data-driven features. Experiments were conducted to validate the effectiveness and robustness of the proposed indicator. The results show that the leakage detection models trained with physical features achieved recognition accuracies of 99.89% for Support Vector Machine (SVM) and 99.97% for eXtreme Gradient Boosting (XGBoost) in the experiments. In the field test conducted on an in-service water supply pipeline with a total length of 701 m, the recognition accuracies for SVM and XGBoost were 97.92% and 99.31%, respectively.
准确监测城市供水管道的泄漏情况对于确保居民用水安全至关重要。本研究基于泄漏噪声源的物理背景，提出了一种用于识别城市供水管道泄漏的可靠物理指标。建立了泄漏源噪声功率谱密度的积分形式，并通过严谨的理论分析得出了一种有效的物理指标。该指标克服了现有泄漏检测方法过度依赖数据驱动特征的局限性。通过实验验证了所提指标的有效性和鲁棒性。结果表明，在实验中，基于物理特征训练的泄漏检测模型对于支持向量机（SVM）的识别准确率为99.89%，对于极端梯度提升（XGBoost）的识别准确率为99.97%。在对一条总长701米的在用供水管道进行的现场测试中，SVM和XGBoost的识别准确率分别为97.92%和99.31%。
