Application of CNN Models to Detect and Classify Leakages in Water Pipelines Using Magnitude Spectra of Vibration Sound
Source abstract
Abstract
Conventional schemes to detect leakage in water pipes require leakage exploration experts. However, to save time and cost, demand for sensor-based leakage detection and automated classification systems is increasing. Therefore, in this study, we propose a convolutional neural network (CNN) model to detect and classify water leakage using vibration data collected by leakage detection sensors installed in water pipes. Experiment results show that the proposed CNN model achieves an F1-score of 94.82% and Matthew’s correlation coefficient of 94.47%, whereas the corresponding values for a support vector machine model are 80.99% and 79.86%, respectively. This study demonstrates the superior performance of the CNN-based leakage detection scheme with vibration sensors. This can help one to save detection time and cost incurred by skilled engineers. In addition, it is possible to develop an intelligent leak detection system based on the proposed one.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Water Systems and Optimization · Infrastructure Maintenance and Monitoring · Water Quality Monitoring Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information and Communication Engineering, Soongsil University, Seoul 06978, Republic of Korea
School of Electronic Engineering, Soongsil University, Seoul 06978, Republic of Korea
Funding
National Research Foundation of Korea
References (40)
Show source-provided references
1. Research Regard to Necessity of Smart Water Management Based on IoT Technology
2. Yoon, D.J., Jeong, J.C., and Lee, Y.S. (2003, January 23–25). Leak detection of waterworks pipeline using acoustic emission and correlation method. Proceedings of the KSME Conference, Busan, Korea.
3. Energy and costs of leaky pipes: Toward comprehensive picture10.1061/(ASCE)0733-9496(2002)128:6(441) ↗
4. Water losses investigation and evaluation in water distribution system—The case of SA city in China10.1080/1573062X.2014.916313 ↗
5. Smart water consumption measurement system for houses using IoT and cloud computing10.1007/s10661-020-08535-4 ↗
6. IoT-Based Solutions to Monitor Water Level, Leakage, and Motor Control for Smart Water Tanks10.3390/w14030309 ↗
7. Rabeek, S.M., Beibei, H., and Chai, K.T. (2019, January 10–13). Design of Wireless IoT Sensor Node & Platform for Water Pipeline Leak Detection. Proceedings of the 2019 IEEE Asia-Pacific Microwave Conference (APMC), Singapore.10.1109/APMC46564.2019.9038809 ↗
8. Wireless Water Leak Detection System Using Sensor Networks
9. Choi, J., Shin, J., Song, C., Han, S., and Park, D.I. (2017). Leak detection and location of water pipes using vibration sensors and modified ML prefilter. Sensors, 17.10.3390/s17092104 ↗
10. Chuang, W.Y., Tsai, Y.L., and Wang, L.H. (2019, January 15–18). Leak detection in water distribution pipes based on CNN with mel frequency cepstral coefficients. Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence, Suzhou, China.10.1145/3319921.3319926 ↗
11. Research of Automatic Water Leak Detection Technology Used on Thermography and Deep Learning
12. Ensemble-based machine learning approach for improved leak detection in water mains10.2166/hydro.2021.093 ↗
13. Machine-learning-based leakage-event identification for smart water supply systems10.1109/JIOT.2019.2958920 ↗
14. Li, J., Liu, Y., Chai, Y., He, H., and Gao, M. (2019, January 5–7). A Small Leakage Detection Approach for Gas Pipelines based on CNN. Proceedings of the 2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Xiamen, China.10.1109/SAFEPROCESS45799.2019.9213371 ↗
15. Enhanced spectrum convolutional neural architecture: An intelligent leak detection method for gas pipeline10.1016/j.psep.2020.12.011 ↗
16. A review of vibration detection methods using accelerometer sensors for water pipeline leakage10.1109/ACCESS.2019.2896302 ↗
17. An in-pipe leak detection robot with a neural-network-based leak verification system10.1109/JSEN.2018.2879248 ↗
18. Ong, K., Png, W., Lin, H., Pua, C., and Rahman, F. (2017, January 18–21). Acoustic vibration sensor based on macro-bend coated fiber for pipeline leakage detection. Proceedings of the 2017 17th International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea.10.23919/ICCAS.2017.8204436 ↗
19. Evaluation of deep learning approaches for oil & gas pipeline leak detection using wireless sensor networks10.1016/j.engappai.2022.104890 ↗
20. A Combined Semi-Supervised Deep Learning Method for Oil Leak Detection in Pipelines Using IIoT at the Edge10.3390/s22114105 ↗
21. A novel oil pipeline leakage detection method based on the sparrow search algorithm and CNN10.1016/j.measurement.2022.112122 ↗
22. Vision-based concrete crack detection using a hybrid framework considering noise effect10.1016/j.jobe.2022.105246 ↗
23. Torsional capacity evaluation of RC beams using an improved bird swarm algorithm optimised 2D convolutional neural network10.1016/j.engstruct.2022.115066 ↗
24. Forecasting monthly gas field production based on the CNN-LSTM model10.1016/j.energy.2022.124889 ↗
25. Leak detection in a real transmission main through transient tests: Deeds and misdeeds10.1029/2020WR027838 ↗
26. A review of physical experiments for leak detection in water pipes through transient tests for addressing future research10.1080/00221686.2022.2067086 ↗
27. An overview of statistical learning theory10.1109/72.788640 ↗
28. Platt, J. (1998). Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines, Microsoft. Technical Report MSR-TR-98-14.
29. Leak detection of pipeline: An integrated approach of rough set theory and artificial bee colony trained SVM10.1016/j.eswa.2011.08.170 ↗
30. Natural gas pipeline small leakage feature extraction and recognition based on LMD envelope spectrum entropy and SVM10.1016/j.measurement.2014.05.012 ↗
31. On the selection of acoustic/vibration sensors for leak detection in plastic water pipes10.1016/j.jsv.2004.05.004 ↗
32. (2022, December 23). AI-Hub, Water and Sewage Data (Water Pipeline Leak Detection). Available online: https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=138.
33. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
34. Han, S., Qubo, C., and Meng, H. (2012, January 24–28). Parameter selection in SVM with RBF kernel function. Proceedings of the World Automation Congress 2012, Puerto Vallarta, Mexico.
35. Powers, D.M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.
36. Grandini, M., Bagli, E., and Visani, G. (2020). Metrics for Multi-Class Classification: An Overview. arXiv.
37. Jeni, L.A., Cohn, J.F., and De La Torre, F. (2013, January 2–5). Facing imbalanced data–recommendations for the use of performance metrics. Proceedings of the 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, Geneva, Switzerland.10.1109/ACII.2013.47 ↗
38. Comparing two K-category assignments by a K-category correlation coefficient10.1016/j.compbiolchem.2004.09.006 ↗
39. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation10.1186/s12864-019-6413-7 ↗
40. The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation10.1186/s13040-021-00244-z ↗