Leak Detection Using Water Pipeline Vibration Sensor: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Suan Lee
,
Byeonghak Kim

Water leakage from aging water and wastewater pipes is a persistent problem, necessitating the improvement of existing leak detection and response methods. Artificial intelligence (AI)-based leak detection systems can quickly determine the source and location of a leak by analyzing data collected from various sensors and suggesting the best course of action to resolve it. IoT technology can be utilized to monitor leaks in real-time and respond automatically in conjunction with a centralized control system. 

  • water leak detection
  • deep learning
  • machine learning

1. Introduction

The detection of leaks is a crucial issue in today’s world, as it has the potential to affect the environment, human safety, and result in economic losses. Leaks of water, gas, electricity, and oil can occur in various forms, and hence, the detection of leaks is crucial in industrial, commercial, and residential areas. The objective of leak detection is to detect and control leaks in a timely manner to create a safe environment and minimize losses. Leak detection technologies can be broadly classified into physical and electronic methods. Physical methods are traditional and require experienced professionals, making them labor-intensive, time-consuming, and costly. Electronic methods, on the other hand, use modern technologies such as sensor technology, data analytics, and artificial intelligence (AI) to detect and analyze leaks. Therefore, electronic leak detection using AI is receiving a lot of attention from researchers.
AI-based leak detection systems can quickly determine the source and location of a leak by analyzing data collected from various sensors and suggesting the best course of action to resolve it. IoT technology can be utilized to monitor leaks in real-time and respond automatically in conjunction with a centralized control system. However, there are still significant challenges to be addressed in the development of leak detection technology, such as improving the accuracy and sensitivity of detection sensors, ensuring performance in various environments, and developing efficient data processing and analysis methods. Additionally, aging water pipelines consisting of a mixture of metal and non-metal pipes, coupled with various noises, including environmental, electrical, and natural sounds, make it difficult to detect leaks. There is an urgent need to develop technology that can accurately detect leaks in such a complex environment.

2. Leak Detection Using Water Pipeline Vibration Sensor

Recently, advancements in sensor technology have led to the proliferation of diverse sensors, enabling efficient data acquisition via sensor networks [1][2]. Water pipeline leakage detection techniques can be classified into three categories: software-based, hardware-based, and conventional methods; it then presents a comparative study of vibration sensors for water pipeline leakage detection and validates a water pipeline testbed using vibration sensors [3]. Liu et al. propose a water pipeline leakage detection method based on machine learning and wireless sensor networks (WSNs) that employs a leakage triggered networking method to reduce energy consumption and a leakage identification method using intrinsic mode function (IMF), approximate entropy (ApEn), principal component analysis (PCA), and a support vector machine (SVM) to enhance the precision and intelligence of leakage detection [4]. Fereidooni et al. propose a fast hybrid method using AI algorithms and hydraulic relations for detecting and locating leaks and identifying the volume of losses material in large scale water distribution networks (WDN) [5]. Luong et al. propose a data renovation method to improve the generalization ability of training data for an intelligent leak detection system based on statistical parameters extracted from acoustic emission signals [6]. Nkemeni et al. present a fully distributed solution for leak detection in a water distribution network using a distributed Kalman filter (DKF) that improves the accuracy of leak detection and power consumption in WSN applications [7]. Shukla et al. present a deep learning algorithm that uses scalogram images of vibration signals collected from accelerometers attached to the pipeline surface to detect leakages in water pipelines with up to 95% accuracy [8]. Mysorewala et al. present a feasibility study of leak detection in wall-mounted water pipelines through vibration measurements using low-power accelerometers; they offer a cost-effective and energy-efficient scheme to detect and classify leaks by optimally placing sensor nodes at carefully selected locations [9].
Wang et al. present an experimental study on water pipeline leak detection using in-pipe acoustic signal analysis and artificial neural network (ANN) prediction to investigate the effects of leak size, pipeline pressure, and flow velocity on the characteristic of acoustic signal and to improve the accuracy of leak recognition [10]. Guo et al. propose a time–frequency convolutional neural network (TFCNN) model for detecting leaks in water distribution systems based on acoustic signals, which improves the accuracy and stability of leakage detection even under low signal-to-noise ratio conditions [11]. Ravichandran et al. present an acoustic leak detection system for distribution water mains using machine learning methods, specifically a multi-strategy ensemble learning approach, which has demonstrated significant improvement in performance, resulting in a reduction of false positive reports by an order of magnitude [12]. Zhou et al. propose a novel ensemble transfer learning one-dimension convolutional neural network (TL1DCNN) approach for pipeline leak detection and localization, which integrates the results of a set of base learners to achieve superior performance compared to traditional methods and other deep learning methods [13]. Liu et al. describe a novel approach to leak detection in water pipes using a Maximum Entropy version of the Least Square Twin K-Class Support Vector Machine (MLT-KSVC) algorithm. This approach assigns different weights to leak samples based on the MaxEnt model, reducing the impact of outliers on the classification process and improving accuracy compared to other methods [14].
Pipelines are one of the least expensive means of transporting fluids over long distances and distributing fluids in large areas and cities. As such, monitoring these pipelines to predict and detect leakage accurately and promptly and to determine the location of the leak is of importance. Sekhavati et al. provides a review and comparative study of computational methods for pipeline leakage detection and localization, discussing the strengths, weaknesses, and limitations of five types of methods: mass/volume balance, negative pressure wave, pressure point analysis, statistical methods, and real-time transient modeling [15]. Tariq et al. present a study on the application of cost-effective MEMS-based accelerometers for leak detection in real water distribution networks, where experiments were conducted over ten months, and machine learning models were developed to improve leak detection accuracy [16]. Tijani et al. propose a reliable technique for pipeline leak detection using acoustic emission signals and deep learning to extract leak-related discriminant features from acoustic images obtained from time series acoustic emission signals using continuous wavelet transform [17]. Ahmad et al. propose a reliable technique for pipeline leak detection using acoustic emission signals and deep learning to extract leak-related features from acoustic images obtained from time series acoustic emission signals using continuous wavelet transform [18]. Xu et al. propose a method for identifying leaks in water pipes using an explainable ensemble tree model of vibration signals based on the wave propagation model and the leakage noise mechanism [19].
Deep learning techniques and algorithms are emerging as a disruptive technology with the potential to transform global economies, environments, and societies. Fu et al. provide a critical review of the role of deep learning in urban water management, examining its current applications and potential future directions to address key challenges in the field [20]. Yu et al. present a study on the effectiveness and practicability of using machine learning models to identify leaks in real pipe networks by classifying vibration signals collected by piezoelectric accelerometers installed in water distribution systems over several cities of China [21]. Zhang et al. describe the development of a convolutional neural network (CNN)–based model to classify acoustic wave files collected by the South Australian Water Corporation’s (SA Water’s) smart water network (SWN) over the city of Adelaide for pipe leak and crack detection with an accuracy of 92.44% [22]. Vanijjirattikhan et al. present the development of an AI-based water leak detection system with cloud information management that can systematically collect and manage leakage sounds and generate a model used by a mobile application to provide operators with guidance for pinpointing leaking pipes [23]. Choudhary et al. present a novel 1-D convolution neural network (1DCNN) model for leak detection, location, and size estimation in a smart water grid (SWG) that uses IoT sensors and devices to monitor water transportation; their method showed better accuracy compared to other state-of-the-art machine learning techniques [24].

This entry is adapted from the peer-reviewed paper 10.3390/s23218935

References

  1. Faheem, M.; Butt, R.A.; Raza, B.; Alquhayz, H.; Ashraf, M.W.; Shah, S.B.; Ngadi, M.A.; Gungor, V.C. QoSRP: A cross-layer QoS channel-aware routing protocol for the Internet of underwater acoustic sensor networks. Sensors 2019, 19, 4762.
  2. Faheem, M.; Ngadi, M.A.; Gungor, V.C. Energy efficient multi-objective evolutionary routing scheme for reliable data gathering in Internet of underwater acoustic sensor networks. Ad Hoc Netw. 2019, 93, 101912.
  3. Ismail, M.I.M.; Dziyauddin, R.A.; Salleh, N.A.A.; Muhammad-Sukki, F.; Bani, N.A.; Izhar, M.A.M.; Latiff, L.A. A review of vibration detection methods using accelerometer sensors for water pipeline leakage. IEEE Access 2019, 7, 51965–51981.
  4. Liu, Y.; Ma, X.; Li, Y.; Tie, Y.; Zhang, Y.; Gao, J. Water pipeline leakage detection based on machine learning and wireless sensor networks. Sensors 2019, 19, 5086.
  5. Fereidooni, Z.; Tahayori, H.; Bahadori-Jahromi, A. A hybrid model-based method for leak detection in large scale water distribution networks. J. Ambient. Intell. Humaniz. Comput. 2021, 12, 1613–1629.
  6. Luong, T.T.; Kim, J.M. The enhancement of leak detection performance for water pipelines through the renovation of training data. Sensors 2020, 20, 2542.
  7. Nkemeni, V.; Mieyeville, F.; Tsafack, P. A distributed computing solution based on distributed kalman filter for leak detection in WSN-based water pipeline monitoring. Sensors 2020, 20, 5204.
  8. Shukla, H.; Piratla, K. Leakage detection in water pipelines using supervised classification of acceleration signals. Autom. Constr. 2020, 117, 103256.
  9. Mysorewala, M.F.; Cheded, L.; Ali, I.M. Leak detection using flow-induced vibrations in pressurized wall-mounted water pipelines. IEEE Access 2020, 8, 188673–188687.
  10. Wang, W.; Sun, H.; Guo, J.; Lao, L.; Wu, S.; Zhang, J. Experimental study on water pipeline leak using In-Pipe acoustic signal analysis and artificial neural network prediction. Measurement 2021, 186, 110094.
  11. Guo, G.; Yu, X.; Liu, S.; Ma, Z.; Wu, Y.; Xu, X.; Wang, X.; Smith, K.; Wu, X. Leakage detection in water distribution systems based on time–frequency convolutional neural network. J. Water Resour. Plan. Manag. 2021, 147, 04020101.
  12. Ravichandran, T.; Gavahi, K.; Ponnambalam, K.; Burtea, V.; Mousavi, S.J. Ensemble-based machine learning approach for improved leak detection in water mains. J. Hydroinformatics 2021, 23, 307–323.
  13. Zhou, M.; Yang, Y.; Xu, Y.; Hu, Y.; Cai, Y.; Lin, J.; Pan, H. A pipeline leak detection and localization approach based on ensemble TL1DCNN. IEEE Access 2021, 9, 47565–47578.
  14. Liu, M.; Yang, J.; Zheng, W. Leak Detection in Water Pipes Based on Maximum Entropy Version of Least Square Twin K-Class Support Vector Machine. Entropy 2021, 23, 1247.
  15. Sekhavati, J.; Hashemabadi, S.H.; Soroush, M. Computational methods for pipeline leakage detection and localization: A review and comparative study. J. Loss Prev. Process Ind. 2022, 77, 104771.
  16. Tariq, S.; Bakhtawar, B.; Zayed, T. Data-driven application of MEMS-based accelerometers for leak detection in water distribution networks. Sci. Total Environ. 2022, 809, 151110.
  17. Tijani, I.A.; Abdelmageed, S.; Fares, A.; Fan, K.H.; Hu, Z.Y.; Zayed, T. Improving the leak detection efficiency in water distribution networks using noise loggers. Sci. Total Environ. 2022, 821, 153530.
  18. Ahmad, S.; Ahmad, Z.; Kim, C.H.; Kim, J.M. A method for pipeline leak detection based on acoustic imaging and deep learning. Sensors 2022, 22, 1562.
  19. Xu, W.; Fan, S.; Wang, C.; Wu, J.; Yao, Y.; Wu, J. Leakage identification in water pipes using explainable ensemble tree model of vibration signals. Measurement 2022, 194, 110996.
  20. Fu, G.; Jin, Y.; Sun, S.; Yuan, Z.; Butler, D. The role of deep learning in urban water management: A critical review. Water Res. 2022, 223, 118973.
  21. Yu, T.; Chen, X.; Yan, W.; Xu, Z.; Ye, M. Leak detection in water distribution systems by classifying vibration signals. Mech. Syst. Signal Process. 2023, 185, 109810.
  22. Zhang, C.; Alexander, B.J.; Stephens, M.L.; Lambert, M.F.; Gong, J. A convolutional neural network for pipe crack and leak detection in smart water network. Struct. Health Monit. 2023, 22, 232–244.
  23. Vanijjirattikhan, R.; Khomsay, S.; Kitbutrawat, N.; Khomsay, K.; Supakchukul, U.; Udomsuk, S.; Suwatthikul, J.; Oumtrakul, N.; Anusart, K. AI-based acoustic leak detection in water distribution systems. Results Eng. 2022, 15, 100557.
  24. Choudhary, P.; Botre, B.A.; Akbar, S.A. 1-D convolution neural network based leak detection, location and size estimation in smart water grid. Urban Water J. 2023, 20, 341–351.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
ScholarVision Creations
Feedback