Continuous Small Leakage Identification Method of Urban Pipeline Based on Improved MVMD Fusion Machine Learning
Source abstract
Abstract
Abstract To address the challenge that continuous small leakage signals are easily disrupted by noise, resulting in a low recognition rate for urban pipeline leakage, we propose an improved multivariate variational mode decomposition (IMVMD) fusion machine learning method specifically for the recognition of continuous small leakages in urban pipelines. Building upon the preliminary time-frequency assessment of the original leakage signal, we enhance the MVMD by incorporating the correlation coefficient and normalized Shannon entropy, enabling adaptive decomposition and reconstruction of the leakage signals. We establish a BP neural network based on the IMVMD and a SVM leakage recognition model also based on IMVMD. Random forest (RF) evaluation is employed to identify the signal feature inputs. The results indicate that the signal-to-noise ratio of the reconstructed signal using IMVMD is 55.42% higher than that of the original signal, demonstrating a superior decomposition effect compared to traditional MVMD EMD and VMD. RF is utilized to reduce the dimensionality of signal characteristics under various leakage conditions, resulting in the selection of four representative features: root mean square, short-term energy, margin factor, and waveform factor, which serve as inputs for the BP neural network and SVM leakage recognition model based on IMVMD. The accuracy of signal recognition reaches 98.22% and 97.22%, respectively. Compared to the traditional MVMD decomposition recognition model, this method improves accuracy by 10.72% and 10.22%, respectively, thereby providing reliable support for the detection and precise localization of continuous small leakages in urban pipelines.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Water Systems and Optimization · Machine Fault Diagnosis Techniques · Structural Integrity and Reliability Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Adegboye, M.A., Fung, W.-K., Karnik, A.: Recent advances in pipeline monitoring and oil leakage detection technologies: principles and approaches. Sensors (2019). https://doi.org/10.3390/s1911254810.3390/s19112548 ↗
2. Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/A:101093340432410.1023/A:1010933404324 ↗
3. Cao, P., Wang, H., Zhou, K.: Multichannel signal denoising using multivariate variational mode decomposition with subspace projection. IEEE Access 8, 74039–74047 (2020). https://doi.org/10.1109/access.2020.298855210.1109/access.2020.2988552 ↗
4. Cao, Y., Liu, T., Song, G., Zhou, W., Han, H., Li, Y., Hu, Q., Jing, R.: Investigation of pipeline CO(2) leakage and diffusion on offshore platforms based on numerical simulation. ACS Omega 9(25), 27537–27548 (2024). https://doi.org/10.1021/acsomega.4c0300210.1021/acsomega.4c03002 ↗
5. Diro, A., Kaisar, S., Vasilakos, A.V., Anwar, A., Nasirian, A., Olani, G.: Anomaly detection for space information networks: a survey of challenges, techniques, and future directions. Comput. Secur. (2024). https://doi.org/10.1016/j.cose.2024.10370510.1016/j.cose.2024.103705 ↗
6. Dovedi, T., Upadhyay, R., Kumar, V.: Multivariate variational mode decomposition & phase space reconstruction based motor imagery EEG classification. Comput. Electr. Eng. (2023). https://doi.org/10.1016/j.compeleceng.2023.10873710.1016/j.compeleceng.2023.108737 ↗
7. Dragomiretskiy, K., Zosso, D.: Variational mode decomposition. IEEE Trans. Signal Process. 62(3), 531–544 (2013)10.1109/TSP.2013.2288675 ↗
8. Ethem, A.: Introduction to Machine Learning, Second Edition. Adaptive Computation & Machine Learning. (2010)
9. Fang, D.Z.A.G.X.G.: Shannon entropy improved variational mode decomposition and fault features extraction. Mech Sci Technol Aerospace Eng 39(7), 1022–1027 (2020). https://doi.org/10.13433/j.cnki.1003-8728.2019023310.13433/j.cnki.1003-8728.20190233 ↗
10. Granata, F., Di Nunno, F., de Marinis, G.: Advanced evapotranspiration forecasting in Central Italy: stacked MLP-RF algorithm and correlated Nystrom views with feature selection strategies. Comput. Electron. Agric. (2024). https://doi.org/10.1016/j.compag.2024.10888710.1016/j.compag.2024.108887 ↗
11. Li, G., Wang, C., Zhang, D., Yang, G.: An improved feature selection method based on random forest algorithm for wind turbine condition monitoring. Sensors (2021). https://doi.org/10.3390/s2116565410.3390/s21165654 ↗
12. Li, H., Liu, T., Wu, X., Chen, Q.: An optimized VMD method and its applications in bearing fault diagnosis. Measurement 166, 108185 (2020)10.1016/j.measurement.2020.108185 ↗
13. Liu, B., Jiang, Z., Nie, W., Ran, Y., Lin, H.: Research on leak location method of water supply pipeline based on negative pressure wave technology and VMD algorithm. Measurement (2021). https://doi.org/10.1016/j.measurement.2021.11023510.1016/j.measurement.2021.110235 ↗
14. Luo, S., Wei, B., Chen, L.: Multi-point deformation monitoring model of concrete arch dam based on MVMD and 3D-CNN. Appl. Math. Model. 125, 812–826 (2024). https://doi.org/10.1016/j.apm.2023.10.03010.1016/j.apm.2023.10.030 ↗
15. Lyu, J., Yang, Y., Zong, Y., Leng, Y., Zheng, W., Ge, S.: Novel sinusoidal signal assisted multivariate variational mode decomposition combined with task-related component analysis for enhancing SSVEP-based BCI performance. IEEE J. Biomed. Health Inform. 28(11), 6474–6485 (2024). https://doi.org/10.1109/jbhi.2024.343939110.1109/jbhi.2024.3439391 ↗
16. Ma, Q., Tian, G., Zeng, Y., Li, R., Song, H., Wang, Z., Gao, B., Zeng, K.: Pipeline in-line inspection method, instrumentation and data management. Sensors (2021). https://doi.org/10.3390/s2111386210.3390/s21113862 ↗
17. Meng, Q., Lang, X., Lin, M., Cai, Z., Zheng, H., Song, H., Liu, W.: Leak localization of gas pipeline based on the combination of EEMD and cross-spectrum analysis. IEEE Trans. Instrum. Meas. 71, 1–9 (2021)
18. Miao, X., Zhao, H., Xiang, Z.: Leakage detection in natural gas pipeline based on unsupervised learning and stress perception. Process. Saf. Environ. Prot. 170, 76–88 (2023). https://doi.org/10.1016/j.psep.2022.12.00110.1016/j.psep.2022.12.001 ↗
19. Ni, L., Gu, W., Zhou, T., Hao, P., Jiang, J.: Leak aperture recognition of natural gas pipeline based on variational mode decomposition and mutual information. Measurement (2025). https://doi.org/10.1016/j.measurement.2024.11601710.1016/j.measurement.2024.116017 ↗
20. Qu, Z., Feng, H., Zeng, Z., Zhuge, J., Jin, S.: A SVM-based pipeline leakage detection and pre-warning system. Measurement 43(4), 513–519 (2010). https://doi.org/10.1016/j.measurement.2009.12.02210.1016/j.measurement.2009.12.022 ↗
21. Rehman, Nu., Aftab, H.: Multivariate variational mode decomposition. IEEE Trans. Signal Process. 67(23), 6039–6052 (2019). https://doi.org/10.1109/tsp.2019.295122310.1109/tsp.2019.2951223 ↗
22. Saleem, F., Ahmad, Z., Siddique, M.F., Umar, M., Kim, J.-M.: Acoustic emission-based pipeline leak detection and size identification using a customized one-dimensional DenseNet. Sensors (2025). https://doi.org/10.3390/s2504111210.3390/s25041112 ↗
23. Seifi, A., Pourebrahim, S., Ehteram, M., Shabanian, H.: A robust multi-model framework for groundwater level prediction: the BFSA-MVMD-GRU-RVM model. Results Eng. (2024). https://doi.org/10.1016/j.rineng.2024.10325010.1016/j.rineng.2024.103250 ↗
24. Shi, R., Wang, B., Wang, Z., Liu, J., Feng, X., Dong, L.: Research on fault diagnosis of rolling bearings based on variational mode decomposition improved by the niche genetic algorithm. Entropy (2022). https://doi.org/10.3390/e2406082510.3390/e24060825 ↗
25. Siddique, M.F., Ullah, N., Kim, J.M.: Comprehensive pipeline leak detection using induced-leak enhanced scalogram analysis and deep learning. 2023 IEEE International Conference on High Performance Computing & Communications, Data Science & Systems, Smart City & Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). (2023, 17–21 Dec. 2023)10.1109/HPCC-DSS-SmartCity-DependSys60770.2023.00127 ↗
26. Siddique, M.F., Ullah, S., Kim, J.-M.: A deep learning approach for fault diagnosis in centrifugal pumps through wavelet coherent analysis and S-transform scalograms with CNN-KAN. Comput. Mater. Contin. 84(2), 3577–3603 (2025). https://doi.org/10.32604/cmc.2025.06532610.32604/cmc.2025.065326 ↗
27. Song, L., Cui, X., Han, X., Gao, Y., Liu, F., Yu, Y., Yuan, Y.: A non-metallic pipeline leak size recognition method based on CWT acoustic image transformation and CNN. Appl. Acoust. (2024). https://doi.org/10.1016/j.apacoust.2024.11018010.1016/j.apacoust.2024.110180 ↗
28. Song, M., Wang, J., Zhao, H., Li, Y.: Bearing failure of reciprocating compressor sub-health recognition based on CAGOA-VMD and GRCMDE. Adv. Mech. Eng. 14(3), 16878132221082976 (2022)10.1177/16878132221082975 ↗
29. Wang, H., Wang, J., Yang, Q., Zhang, X., Gao, P., Xu, S., Sun, X., Wang, Y.: Synthesis of a novel nitronyl nitroxide radical and determination of its protective effects against infrasound-induced injury. Neurochem. Res. 40(7), 1526–1536 (2015). https://doi.org/10.1007/s11064-015-1602-510.1007/s11064-015-1602-5 ↗
30. Wang, W., Gao, Y.: Pipeline leak detection method based on acoustic-pressure information fusion. Measurement (2023). https://doi.org/10.1016/j.measurement.2023.11269110.1016/j.measurement.2023.112691 ↗
31. Wang, Z., He, X., Shen, H., Fan, S., Zeng, Y.: Multi-source information fusion to identify water supply pipe leakage based on SVM and VMD. Inf. Process. Manag. (2022). https://doi.org/10.1016/j.ipm.2021.10281910.1016/j.ipm.2021.102819 ↗
32. Wu, F., Jiang, X.P., Yu, H.W., Xiu, L.C.: Application of empirical mode decomposition and independent component analysis for the interpretation of rock-mineral spectrum. Guang Pu Xue Yu Guang Pu Fen Xi 36(5), 1592–1597 (2016)
33. Wu, G., Liu, G., Wang, J., Fan, P.: Seismic random noise denoising using mini-batch multivariate variational mode decomposition. Comput. Intell. Neurosci. 2022, 2132732 (2022). https://doi.org/10.1155/2022/213273210.1155/2022/2132732 ↗
34. Xiao, R., Li, J.: Evaluation of acoustic techniques for leak detection in a complex low-pressure gas pipeline network. Eng. Fail. Anal. (2023). https://doi.org/10.1016/j.engfailanal.2022.10689710.1016/j.engfailanal.2022.106897 ↗
35. Xu, T., Zeng, Z., Huang, X., Li, J., Feng, H.: Pipeline leak detection based on variational mode decomposition and support vector machine using an interior spherical detector. Process. Saf. Environ. Prot. 153, 167–177 (2021). https://doi.org/10.1016/j.psep.2021.07.02410.1016/j.psep.2021.07.024 ↗
36. Xu, Z., Liu, H., Fu, G., Zeng, Y., Li, Y.: Feature selection of acoustic signals for leak detection in water pipelines. Tunnell. Underground Space Technol. (2024). https://doi.org/10.1016/j.tust.2024.10594510.1016/j.tust.2024.105945 ↗
37. Yan, Z., Cui, X., Gao, Y.: Acoustic injection method based on weak echo signals for leak detection and localization in gas pipelines. Appl. Acoust. (2023). https://doi.org/10.1016/j.apacoust.2023.10957710.1016/j.apacoust.2023.109577 ↗
38. Yi, W., Feng, X., Juan, Y.: Acoustic feature extraction of divers based on multivariate variational mode decomposition with low signal-to-noise ratio. ACTA ACUSTICA. 49(02), (2024). https://doi.org/10.12395/0371-0025.202214910.12395/0371-0025.2022149 ↗
39. Zaman, W., Siddique, M.F., Khan, S.U., Kim, J.-M.: A new dual-input CNN for multimodal fault classification using acoustic emission and vibration signals. Eng. Fail. Anal. (2025). https://doi.org/10.1016/j.engfailanal.2025.10978710.1016/j.engfailanal.2025.109787 ↗
40. Zhao, X., Li, W., Du, K., Sun, Y., Yang, W., Wang, Y.: Research Progress of Proton Transfer Reaction Mass Spectrometry in the Field of Breathing Gas Detection. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi 32(6), 1374–1379 (2015)
41. Zhou, J., Lin, H., Li, S., Jin, H., Zhao, B., Liu, S.: Leakage diagnosis and localization of the gas extraction pipeline based on SA-PSO BP neural network. Reliab. Eng. Syst. Saf. (2023). https://doi.org/10.1016/j.ress.2022.10905110.1016/j.ress.2022.109051 ↗