Leakage Detection in Water Distribution Systems Based on Time–Frequency Convolutional Neural Network
Authors:
- 1 February 2021
- journal article
- research article
- Published by American Society of Civil Engineers (ASCE) in Journal of Water Resources Planning and Management
- Vol. 147 (2) , 04020101
Abstract
Effectively detecting leaks is critical to improving leakage control management. Acoustic detection is one of the main leakage detection methods, and has been widely used in water utilities. Nevertheless, the effectiveness of this method is unsatisfactory in cases with various types of noise. To tackle this problem, this work proposes a leakage spectrogram to represent the features of leakage signals, and developed a time–frequency convolutional neural network (TFCNN) model to identify leakage signals. The performance of the TFCNN model was compared with other classification models (i.e., decision tree, support vector machine, multilayer perceptron, random forest, and extreme gradient boosting) under different signal-to-noise ratio (SNR) conditions. The results showed that the proposed method improves the accuracy and stability of leakage detection. Compared with other classification models, the TFCNN model had the best performance, and its mean accuracy reached 98% under different SNR conditions. Even in the case of SNR, the mean detection accuracy reached 90%. In practice, the mean detection accuracy reached 99% for different time–frequency resolutions. The transfer learning–based TFCNN model is a promising method for leakage detection in cases in which there are insufficient data sets.
Keywords
This publication has 42 references indexed in Scilit:
- Leak detection in water-filled plastic pipes through the application of tuned wavelet transforms to Acoustic Emission signalsApplied Acoustics, 2010
- Development and Verification of an Online Artificial Intelligence System for Detection of Bursts and Other Abnormal FlowsJournal of Water Resources Planning and Management, 2010
- A review of methods for leakage management in pipe networksUrban Water Journal, 2010
- Detection of leak acoustic signal in buried gas pipe based on the time–frequency analysisJournal of Loss Prevention in the Process Industries, 2009
- Spectral analysis of leak detection in a zigzag pipeline: A filter diagonalization method-based algorithm applicationMeasurement, 2009
- Wavelets for the Analysis of Transient Pressure Signals for Leak DetectionJournal of Hydraulic Engineering, 2007
- On the selection of acoustic/vibration sensors for leak detection in plastic water pipesJournal of Sound and Vibration, 2005
- A model of the correlation function of leak noise in buried plastic pipesJournal of Sound and Vibration, 2004
- Energy and Costs of Leaky Pipes: Toward Comprehensive PictureJournal of Water Resources Planning and Management, 2002
- Joint time-frequency analysisIEEE Signal Processing Magazine, 1999