Comprehensive Framework for Leak Detection in Water Distribution Systems: A Vibration Signal Processing and Machine learning Approach
DOI:
https://doi.org/10.58564/IJSER.4.2.2025.313Keywords:
Pipeline leak detection, Vibration signal processing, Machine learning, Random ForestAbstract
This study provides a new approach for identifying water distribution system leaks. It blends vibration signal processing with machine learning. The system is based on vibration signals from accelerometers for pipeline observation through non-invasive methods and real-time. Based on a Random Forest classifier, the system is able to differentiate between different leak scenarios from no-leak cases with an accuracy of 97.3%. We validated the findings using a confusion matrix, which confirmed some cases of misclassification, indicating there is still much scope for improvement. We identified key statistical features such as RMS, kurtosis, and variance as being of prime importance for leak identification using feature importance analysis. These features enable capturing the specific vibration patterns of diverse leaks, allowing for accurate identification. This is an improvement over conventional leak detection techniques, offering a more reliable and efficient method for pipeline observation. The study also discusses how the procedure could make water distribution systems sustainable and operationally efficient for application in the real world.
References
1. Lee S, Kim B (2023) Machine Learning Model for Leak Detection Using Water Pipeline Vibration Sensor. Sensors 23.
2. Mahdi NM, Jassim AH, Abulqasim SA, et al. (2024) Leak detection and localization in water distribution systems using advanced feature analysis and an Artificial Neural Network. Desalination Water Treat 320: 100685.
3. Martini A, Troncossi M, Rivola A (2017) Leak Detection in Water-Filled Small-Diameter Polyethylene Pipes by Means of Acoustic Emission Measurements. Applied Sciences 7.
4. Zhang Chi, Alexander Bradley J, Stephens Mark L, et al. (2022) A convolutional neural network for pipe crack and leak detection in smart water network. Struct Health Monit 22: 232–244.
5. Zhu Lijuan, Wang Dongmei, Yue Jikang, et al. (2022) Leakage detection method of natural gas pipeline combining improved variational mode decomposition and Lempel–Ziv complexity analysis. Transactions of the Institute of Measurement and Control 44: 2865–2876.
6. Rajabi MM, Komeilian P, Wan X, et al. (2023) Leak detection and localization in water distribution networks using conditional deep convolutional generative adversarial networks. Water Res 238: 120012.
7. Gao L, Dong L, Cao J, et al. (2020) Acoustic Emission-Based Small Leak Detection of Propulsion System Pipeline of Sounding Rocket. Shock and Vibration 2020: 8875939.
8. Ismail MIM, Dziyauddin RA, Salleh NAA, et al. (2019) A Review of Vibration Detection Methods Using Accelerometer Sensors for Water Pipeline Leakage. IEEE Access 7: 51965–51981.
9. Choi J, Im S (2023) Application of CNN Models to Detect and Classify Leakages in Water Pipelines Using Magnitude Spectra of Vibration Sound. Applied Sciences 13.
10. Yu T, Chen X, Yan W, et al. (2023) Leak detection in water distribution systems by classifying vibration signals. Mech Syst Signal Process 185: 109810.
11. Ogaili AAF, AbdulhadyJaber A, Hamzah MN (2023) Statistically Optimal Vibration Feature Selection for Fault Diagnosis in Wind Turbine Blade. International Journal of Renewable Energy Research 13: 1082–1092.
12. Ogaili AAF, Jaber AA, Hamzah MN (2023) Wind turbine blades fault diagnosis based on vibration dataset analysis. Data Brief 49: 109414.
13. Ogaili AAF, Jaber AA, Hamzah MN (2023) A methodological approach for detecting multiple faults in wind turbine blades based on vibration signals and machine learning. 10.
14. Ogaili AAF, Hamzah MN, Jaber AA (2024) Enhanced Fault Detection of Wind Turbine Using eXtreme Gradient Boosting Technique Based on Nonstationary Vibration Analysis. Journal of Failure Analysis and Prevention.
15. Kang J, Park Y-J, Lee J, et al. (2018) Novel Leakage Detection by Ensemble CNN-SVM and Graph-Based Localization in Water Distribution Systems. IEEE Transactions on Industrial Electronics 65: 4279–4289.
16. Yussif A-M, Sadeghi H, Zayed T (2023) Application of Machine Learning for Leak Localization in Water Supply Networks. Buildings 13.
17. Xiao R, Hu Q, Li J (2019) Leak detection of gas pipelines using acoustic signals based on wavelet transform and Support Vector Machine. Measurement 146: 479–489.
18. Ogaili AAF, Mohammed KA, Jaber AA, et al. (2024) Automated wind turbines gearbox condition monitoring: A comparative study of machine learning techniques based on vibration analysis. FME Transactions 52: 471–485.
19. Ogaili AAF, Al-Sharify ZT, Abdulhady A, et al. (2024) Vibration-based fault detection and classification in ball bearings using statistical analysis and random forest, Fifth International Conference on Green Energy, Environment, and Sustainable Development (GEESD 2024), SPIE, 518–526.
20. Ogaili AAF, Al-Sharify ZT, Jaber AA, et al. (2024) Effective Ball Bearing Fault Diagnosis Leveraging ANN and Statistical Feature Integration.
21. Sarow SA, Flayyih HA, Bazerkan M, et al. (2024) Advancing sustainable renewable energy: XGBoost algorithm for the prediction of water yield in hemispherical solar stills. Discover Sustainability 5: 510.
22. Mejbel BG, Sarow SA, Al-Sharify MT, et al. (2024) A Data Fusion Analysis and Random Forest Learning for Enhanced Control and Failure Diagnosis in Rotating Machinery. Journal of Failure Analysis and Prevention.
23. Al-Haddad LA, Jaber AA, Mahdi NM, et al. (2024) Protocol for UAV fault diagnosis using signal processing and machine learning. STAR Protoc 5: 103351.
24. Metteb ZW, Ogaili AAF, Mohammed KA, et al. (2025) Optimization of Hybrid Core Designs in 3D-Printed PLA+ Sandwich Structures: An Experimental, Statistical, and Computational Investigation Completed with Bibliometric Literature Review. Indonesian Journal of Science and Technology 10: 207–236.
25. W. Abduljaleel Y, Al-Obaidi B, M. Khattab M, et al. (2024) Compressive Strength Prediction of Recycled Aggregate Concrete Based on Different Machine Learning Algorithms. Al-Iraqia Journal for Scientific Engineering Research 3: 25–36.
26. Aghashahi M, Sela L, Banks MK (2023) Benchmarking dataset for leak detection and localization in water distribution systems. Data Brief 48: 109148.
27. Abdulla FA, Hamid KL, Ogaili AAF, et al. (2020) Experimental study of Wear Rate Behavior for Composite Materials under Hygrothermal Effect, IOP Conference Series: Materials Science and Engineering, IOP Publishing, 022009.
28. Khulief YA, Khalifa A, Ben MR, et al. (2012) Acoustic Detection of Leaks in Water Pipelines Using Measurements inside Pipe. J Pipeline Syst Eng Pract 3: 47–54.
29. Colombo AF, Lee P, Karney BW (2009) A selective literature review of transient-based leak detection methods. Journal of Hydro-environment Research 2: 212–227.
30. Puust R, Z. K, D. A. S, et al. (2010) A review of methods for leakage management in pipe networks. Urban Water J 7: 25–45.
31. Tsai Y-L, Chang H-C, Lin S-N, et al. (2022) Using Convolutional Neural Networks in the Development of a Water Pipe Leakage and Location Identification System. Applied Sciences 12.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Hayder Wthaij, Ajeel Al Ghasheem
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
