Advancing deep learning-based acoustic leak detection methods towards application for water distribution systems from a data-centric perspective

• Published in: Water research (Oxford) Vol. 261; p. 121999
• Main Authors: Wu, Yipeng, Ma, Xingke, Guo, Guancheng, Jia, Tianlong, Huang, Yujun, Liu, Shuming, Fan, Jingjing, Wu, Xue
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.09.2024
• Subjects: Acoustic leak detection; Acoustics; Convolutional neural network; Data augmentation; Deep Learning; Neural Networks, Computer; Time–frequency spectrogram; Water - chemistry; Water distribution system; Water Supply; Time–frequency spectrogram; Acoustic leak detection; Data augmentation; Water distribution system; Convolutional neural network
• ISSN: 0043-1354; 1879-2448; 1879-2448
• DOI: 10.1016/j.watres.2024.121999

•Augmentation of acoustic data in both time and time-frequency domains is explored.•Data augmentation before splitting prevents biased results due to data leakage.•IAAFT enhances accuracy by 7% and is well suited for acoustic leak detection.•Sequential use of IAAFT and masking synergizes for improved performance. Against the backdrop of severe leakage issue in water distribution systems (WDSs), numerous researchers have focused on the development of deep learning-based acoustic leak detection technologies. However, these studies often prioritize model development while neglecting the importance of data. This research explores the impact of data augmentation techniques on enhancing deep learning-based acoustic leak detection methods. Five random transformation-based methods—jittering, scaling, warping, iterated amplitude adjusted Fourier transform (IAAFT), and masking—are proposed. Jittering, scaling, warping, and IAAFT directly process original signals, while masking operating on time-frequency spectrograms. Acoustic signals from a real-world WDS are augmented, and the efficacy is validated using convolutional neural network classifiers to identify the spectrograms of acoustic signals. Results indicate the importance of implementing data augmentation before data splitting to prevent data leakage and overly optimistic outcomes. Among the techniques, IAAFT stands out, significantly increasing data volume and diversity, improving recognition accuracy by over 7%. Masking enhances performance mainly by compelling the classifier to learn global features of the spectrograms. Sequential application of IAAFT and masking further strengthens leak detection performance. Furthermore, when applying a complex model to acoustic leakage detection through transfer learning, data augmentation can also enhance the effectiveness of transfer learning. These findings advance artificial intelligence-driven acoustic leak detection technology from a data-centric perspective towards more mature applications. [Display omitted]