Pipe feature classification using support vector machine based on time-domain feature extraction
DOI:
https://doi.org/10.15282/ijame.23.2.2026.13.1032Keywords:
Non-revenue water, Transient reflection method, Minimized classification error, Support vector machines, Feature selectionAbstract
Water infrastructure deterioration threatens global water security, with utilities losing over $14 billion annually due to non-revenue water (NRW). Malaysia reported 37.1% NRW in 2023, significantly exceeding international benchmarks. This study develops an automated pipeline monitoring system integrating pressure transient analysis with machine learning for leak detection in water distribution networks. Three feature selection methods (minimum classification error, minimum redundancy maximum relevance, and sequential forward selection) were systematically evaluated to optimize classification performance. The proposed minimised classification error-surface vector machine model (MCE-SVM), which is based on two time-domain features slope sign change and integrated EMG to characterize three pipeline conditions, including elbow, junction, and leak, attained a test accuracy of 87.4%, substantially higher than those achieved by Minimum redundancy maximum relevance- surface vector machine (77.3%) and sequential forward selection-surface vector machine (65.8%), demonstrating the effectiveness of the minimised classification error based method in selecting highly discriminatory features with a minimal feature set. Moreover, the suggested system is capable of fast processing of the signal, which highlights the appropriateness of the proposed system to the report on near real-time monitoring of pipelines. The controlled laboratory experiments were conducted using 300 transient pressure signals recorded with one configuration under 4 bar in one pipe setup (63 mm medium-density polyethene).
References
[1] M. Ghazi, E. Aweng, and N. Farhana, “Assessing the implementation of non-revenue water (NRW) management efficiency based on economic indicators: Case of Bechah Tendong, Kelantan, Malaysia,” AIP Confrence Proceeding, vol. 2544, no. 1, p. 050010, 2023. https://doi.org/10.1063/5.0117268
[2] H. T. AbuEltayef, K. S. AbuAlhin, and K. M. Alastal, “Addressing non-revenue water as a global problem and its interlinkages with sustainable development goals,” Water Practice & Technology, vol. 18, no. 12, pp. 3175-3202, 2023. https://doi.org/10.2166/wpt.2023.157
[3] B. Charalambous, D. Foufeas, and N. Petroulias, “Leak detection and water loss management,” Water Utility Journal, vol. 8, no. 3, pp. 25-30, 2014.
[4] S. Meniconi, C. Capponi, M. Frisinghelli, and B. Brunone, “Leak detection in a real transmission main through transient tests: Deeds and misdeeds,” Water Resources Research, vol. 57, no. 3, p. e2020WR027838, 2021. https://doi.org/10.1029/2020WR027838
[5] Y. Zhang, H. F. Duan, A. Keramat, and T. C. Che, “On the leak-induced transient wave reflection and dominance analysis in water pipelines,” Mechanical Systems and Signal Processing, vol. 167, p. 108512, 2022. https://doi.org/10.1016/j.ymssp.2021.108512
[6] J. K. Jatavallabhula, V. R. Veeredhi, G. S. Reddy, R. R. Baridula, and V. V. Satyanarayana, “Machine learning-based prediction of impact toughness in AISI 430–AISI 304 Friction-Welded joints,” International Journal of Automotive and Mechanical Engineering, vol. 22, no. 1, pp. 12118-12132, 2025. https://doi.org/10.15282/ijame.22.1.2025.13.0930
[7] N. D. Tue, and V. Van An, “Machine learning-based prediction of the coefficient of performance for low global warming potential refrigerants in a vapor compression system,” International Journal of Automotive and Mechanical Engineering, vol. 23, no. 1, pp. 13405-13418, 2026.
[8] N. Jain, and S. Mittal, “Review of computational techniques for modelling eco-safe driving behavior,” International Journal of Automotive and Mechanical Engineering, vol. 20, no. 2, pp. 10422-10440, 2023. https://doi.org/10.15282/ijame.20.2.2023.08.0806
[9] Z. Qu, H. Feng, Z. Zeng, J. Zhuge, S. Jin, “A SVM-based pipeline leakage detection and pre-warning system,” Measurement, vol. 43, no. 4, pp. 513-519, 2010. https://doi.org/10.1016/j.measurement.2009.12.022
[10] T. Xu, Z. Zeng, X. Huang, J. Li, H. Feng, “Pipeline leak detection based on variational mode decomposition and support vector machine using an interior spherical detector,” Process Safety and Environmental Protection, vol. 153, pp. 167-177, 2021. https://doi.org/10.1016/j.psep.2021.07.024
[11] E. McDermott, and S. Katagiri, “A derivation of minimum classification error from the theoretical classification risk using Parzen estimation,” Computer Speech & Language, vol. 18, no. 2, pp. 107-122, 2004. https://doi.org/10.1016/S0885-2308(03)00037-8
[12] S. Pitta, R. J. Ginka, and B. Banavathu, “Risk-aware buckling design of functionally graded porous beams via machine-learning surrogates and reliability analysis,” International Journal of Automotive and Mechanical Engineering, vol. 23, no. 1, pp. 13367-13392, 2026. https://doi.org/10.15282/ijame.23.1.2026.16.1014
[13] M. A. Islam, M. R. Mahmud, A. H. Sakib, M. I. H. Siddiqui, and H. Fardin, “Time domain feature analysis for gas pipeline fault detection using LSTM,” International Journal of Science and Research Archive, pp. 1769-77, 2025. https://doi.org/10.30574/ijsra.2025.15.1.1158
[14] B. Nayana, and P. Geethanjali, “Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal,” IEEE Sensors Journal, vol. 17, no. 17, pp. 5618-5625, 2017. https://doi.org/10.1109/JSEN.2017.2727638
[15] X. Wang, K .K. Paliwal, “A modified minimum classification error (MCE) training algorithm for dimensionality reduction,” Journal of VLSI Signal Processing Systems for signal, Image and Video Technology, vol. 32, no. 1, pp. 19-28, 2002. https://doi.org/10.1023/A:1016307200123
[16] H. R. Al-Bugharbee, H. Samaka, and S. L. Zubaidi, “Diagnosis of air compressor condition using minimum redundancy maximum relevance (MRMR) algorithm and distance metric-based classification,” Diagnostyka, vol. 22, no. 4, pp. 25-32, 2021. https://doi.org/10.29354/diag/143762
[17] P. Singla, H. Garg, A. Pathak, and S. P. Singh, “Privacy Enhancement in Internet of Things (IoT) via mRMR for prevention and avoidance of data leakage,” Computers and Electrical Engineering, vol. 116, p. 109151, 2024. https://doi.org/10.1016/j.compeleceng.2024.109151
[18] R. Taiwo, M. E. A. Ben Seghier, and T. Zayed, “Toward sustainable water infrastructure: the state‐of‐the‐art for modeling the failure probability of water pipes,” Water Resources Research, vol. 59, no. 4, p. e2022WR033256, 2023. https://doi.org/10.1029/2022WR033256
[19] K. Yan, L. Ma, Y. Dai, W. Shen, Z. Ji, and D. Xie, “Cost-sensitive and sequential feature selection for chiller fault detection and diagnosis,” International Journal of Refrigeration, vol. 86, pp. 401-409, 2018. https://doi.org/10.1016/j.ijrefrig.2017.11.003
[20] Z. Liao, H. Yan, Z. Tang, X. Chu, and T. Tao, “Deep learning identifies leak in water pipeline system using transient frequency response,” Process Safety and Environmental Protection, vol. 155, pp. 355-365, 2021. https://doi.org/10.1016/j.psep.2021.09.033
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
