1. Home
  2. Vol 10, No 7 (2024)
  3. Ladino-Moreno

Leak Detection in Urban Hydraulic Systems Using the K-BiLSTM-Monte Carlo Dropout Model

Edgar Orlando Ladino-Moreno, César Augusto García-Ubaque

Abstract


Utility companies lose approximately 35 liters of water for every 100 produced due to incorrect, illegal connections and the poor condition of pipes. This study develops an intelligent model to detect leaks using the Kalman filter, BiLSTM neural networks, and the Monte Carlo Dropout algorithm. Using data from the Empresa de Acueductos y Alcantarillados de Bogotá (EAAB), Colombia, autocorrelation analysis, PCA, cluster analysis, ADF and Durbin-Watson tests, Hurst exponent, spectral analysis, and wavelet transform were performed. Then, Kalman filtering techniques were applied, and a BiLSTM architecture controlled with Monte Carlo dropout was implemented. The results showed an accuracy of 87.48% in training and 80.48% in validation. Temporal analysis revealed a stationary behavior in the flow series, and the decrease in spectral intensity around 0.25 Hz was related to pressure perturbations caused by leaks. A detailed evaluation of pressure and flow signals identified leak patterns with high precision, demonstrating the effectiveness of the wavelet spectrogram in detecting energy disturbances. The novelty of the study lies in the integration of advanced artificial intelligence and combinatorial optimization techniques to improve water resource management, allowing early and accurate detection of leaks, significantly improving compared to traditional methods.

 

Doi: 10.28991/CEJ-2024-010-07-01

Full Text: PDF


Keywords


BiLSTM; Kalman Filtering; Leak; Monte Carlo Dropout; Public Utility Management; Spectral Analysis; Wavelet Transform.

References


Yang, L., & Zhao, Q. (2022). A BiLSTM Based Pipeline Leak Detection and Disturbance Assisted Localization Method. IEEE Sensors Journal, 22(1), 611–620. doi.:10.1109/jsen.2021.3128816.

Zhang, X., Shi, J., Yang, M., Huang, X., Usmani, A. S., Chen, G., Fu, J., Huang, J., & Li, J. (2023). Real-time pipeline leak detection and localization using an attention-based LSTM approach. Process Safety and Environmental Protection, 174, 460–472. doi:10.1016/j.psep.2023.04.020.

Yang, L., & Zhao, Q. (2020). A Novel PPA Method for Fluid Pipeline Leak Detection Based on OPELM and Bidirectional LSTM. IEEE Access, 8, 107185–107199. doi:10.1109/ACCESS.2020.3000960.

Wang, L., Hu, C., Ma, T., Yang, Z., Guo, W., Mao, Z., Guo, J., & Li, H. (2024). GTFE-Net-BiLSTM-AM: An intelligent feature recognition method for natural gas pipelines. Gas Science and Engineering, 125. doi:10.1016/j.jgsce.2024.205311.

Gao, Y., Piltan, F., & Kim, J.-M. (2022). A Hybrid Leak Localization Approach Using Acoustic Emission for Industrial Pipelines. Sensors, 22(10), 3963. doi:10.3390/s22103963.

Guo, X. L., Yang, K. L., & Guo, Y. X. (2012). Leak detection in pipelines by exclusively frequency domain method. Science China Technological Sciences, 55(3), 743–752. doi:10.1007/s11431-011-4707-3.

Ullah, N., Ahmed, Z., & Kim, J.-M. (2023). Pipeline Leakage Detection Using Acoustic Emission and Machine Learning Algorithms. Sensors, 23(6), 3226. doi:10.3390/s23063226.

Shen, Y., & Cheng, W. (2022). A Tree-Based Machine Learning Method for Pipeline Leakage Detection. Water, 14(18), 2833. doi:10.3390/w14182833.

Acharya, T., Annamalai, A., & Chouikha, M. F. (2023). Efficacy of Bidirectional LSTM Model for Network-Based Anomaly Detection. 2023 IEEE 13th Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia. doi:10.1109/iscaie57739.2023.10165336.

Lee, S., & Kim, B. (2023). Machine Learning Model for Leak Detection Using Water Pipeline Vibration Sensor. Sensors (Basel, Switzerland), 23(21), 8935. doi:10.3390/s23218935.

Chumchu, P. (2021). A Leak Detection in Water Pipelines Using Discrete Wavelet Decomposition and Artificial Neural Network. Advances in Signal Processing and Intelligent Recognition Systems, 49–65. doi:10.1007/978-981-16-0425-6_4.

Barandouzi, M. A., Mahinthakumar, G., Ranjithan, R., & Brill, E. D. (2012). Probabilistic Mapping of Water Leakage Characterizations Using a Bayesian Approach. World Environmental and Water Resources Congress 2012. doi:10.1061/9780784412312.326.

Proença, M., Paschoalini, A. T., & Obata, D. H. S. (2023). Prediction of the probabilistic water leak location in underground pipelines using Monte Carlo simulation. Water Practice and Technology, 18(3), 522–535. doi:10.2166/wpt.2023.026.

Zhang, Z., & Lv, M. (2022). Leakage prediction of water supply network based on SAA-SVM model. Journal of Physics: Conference Series, 2202(1), 012014. doi:10.1088/1742-6596/2202/1/012014.

Zhang, P., He, J., Huang, W., Zhang, J., Yuan, Y., Chen, B., Yang, Z., Xiao, Y., Yuan, Y., Wu, C., Cui, H., & Zhang, L. (2023). Water Pipeline Leak Detection Based on a Pseudo-Siamese Convolutional Neural Network: Integrating Handcrafted Features and Deep Representations. Water, 15(6), 1088. doi:10.3390/w15061088.

Abdul, Z. K., & Al-Talabani, A. K. (2022). Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10, 122136-122158. doi:10.1109/ACCESS.2022.3223444.

Koolagudi, S. G., Rastogi, D., & Rao, K. S. (2012). Identification of language using mel-frequency cepstral coefficients (MFCC). Procedia Engineering, 38, 3391-3398. doi:10.1016/j.proeng.2012.06.392.

Koutsoyiannis, D. (2012). A Monte Carlo approach to water management. Proceedings of the Geophysical Research Abstracts, European Geosciences Union General Assembly, 22-27 April, 2012, Vienna, Austria.

Thu, S., Aung, N., & Ko, K. (2023). A Calibration Technique for Water Flow Sensor YF-S201 1. International Journal of Trend in Research and Development, 5(5), 152–154.

Zahran, A., Hassan Rabie Sakr, L., Shabaka, I., & Mansour, M. (2020). Performance of an Orifice Meter Handling Two-Phase (Gas-Liquid) Flow.(Dept. M). Mansoura Engineering Journal, 45(3), 29–38. doi:10.21608/bfemu.2020.114002.

Wu, Y., Liu, S., Smith, K., & Wang, X. (2018). Using Correlation between Data from Multiple Monitoring Sensors to Detect Bursts in Water Distribution Systems. Journal of Water Resources Planning and Management, 144(2), 04017084. doi:10.1061/(asce)wr.1943-5452.0000870.

Shao, Y., Li, X., Zhang, T., Chu, S., & Liu, X. (2019). Time-series-based leakage detection using multiple pressure sensors in water distribution systems. Sensors (Switzerland), 19(14), 3070. doi:10.3390/s19143070.

Sun, Q., Zhang, Y., Lu, B., & Liu, H. (2022). Flow Measurement-Based Self-Adaptive Line Segment Clustering Model for Leakage Detection in Water Distribution Networks. IEEE Transactions on Instrumentation and Measurement, 71, 1–13,. doi:10.1109/TIM.2022.3165258.

Turkowski, M., Bratek, A., & Ostapkowicz, P. (2016). Uncertainty Analysis as the Tool to Assess the Quality of Leak Detection and Localization Systems. Recent Global Research and Education: Technological Challenges, 469–475, Springer, Cham, Switzerland. doi:10.1007/978-3-319-46490-9_62.

Perez, R., Cuguero, J., Blesa, J., Cuguero, M. A., & Sanz, G. (2016). Uncertainty effect on leak localisation in a DMA. 2016 3rd Conference on Control and Fault-Tolerant Systems (SysTol), Barcelona, Spain. doi:10.1109/systol.2016.7739770.

Lu, H., Iseley, T., Behbahani, S., & Fu, L. (2020). Leakage detection techniques for oil and gas pipelines: State-of-the-art. Tunnelling and Underground Space Technology, 98, 103249. doi:10.1016/j.tust.2019.103249.

Kopbayev, A., Khan, F., Yang, M., & Halim, S. Z. (2022). Gas leakage detection using spatial and temporal neural network model. Process Safety and Environmental Protection, 160, 968–975. doi:10.1016/j.psep.2022.03.002.

Amora, D. J. A., Janapin, M. A. V., Calayag, B. A. M., Rioflorido, C. L. P. P., Estur, N. M., & Villegas, P. A. L. (2022). Design of a Household Consumption based Water Leak Detection System Utilizing Machine Learning Algorithm. 2022 IET International Conference on Engineering Technologies and Applications (IET-ICETA), Changhua, Taiwan. doi:10.1109/iet-iceta56553.2022.9971564.

Tornyeviadzi, H. M., Mohammed, H., & Seidu, R. (2023). Robust night flow analysis in water distribution networks: A BiLSTM deep autoencoder approach. Advanced Engineering Informatics, 58, 102135. doi:10.1016/j.aei.2023.102135.

Hao, J., Jin, M., Li, Y., Piao, T., Hu, H., Xi, X., & Chen, J. (2023). Power Data Traceability Mechanism Based on Data Processing Unit. 2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China. doi:10.1109/itaic58329.2023.10408832.


Full Text: PDF

DOI: 10.28991/CEJ-2024-010-07-01

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Copyright (c) 2024 Edgar Orlando Ladino

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
x
Message