Deteksi Kebocoran Pipa Air Menggunakan Machine Learning dengan Jaringan Nirkabel IEEE 802.15.4

Kurniawan Saputra(1), M. Udin Harun Al Rasyid(2*), Muh. Zen Samsono Hadi(3)

(1) 
(2) Politeknik Elektronika Negeri Surabaya (PENS)
(3) 
(*) Corresponding Author

Abstract


Pipa adalah cara paling ekonomis dan paling aman dalam mendistribusikan hasil produk seperti air, petrokimia, gas, dan cairan lainnya. Terlepas dari manfaat tersebut, ternyata pipa memiliki ancaman yaitu potensi kebocoran. Artikel ini membahas pendeteksian kebocoran pipa air menggunakan parameter debit aliran. Pengujian dilakukan pada dua format dataset, menggunakan raw dataset dan process dataset menggunakan metode volume balance. Pada proses pembelajaran ada beberapa hal yang perlu disoroti seperti pemilihan tipe dataset, pre-processing dengan menormalisasi dataset, dan menerapkan metode fungsi kernel untuk meningkatkan kinerja akurasi prediksi ukuran dan lokasi kebocoran pipa. Dataset dilatih menggunakan algortima SVM untuk mengklasifikasikan ukuran dan lokasi kebocoran pipa. Hasil klasfikasi ukuran kebocoran dengan fungsi kernel polynomial pada raw dataset mencapai akurasi sebesar 98,25%, recall 99,1%, presisi 99,8%, dan F-measure 99,5%. Sedangkan fungsi kernel Radial Basis Function pada process dataset mencapai akurasi tertinggi sebesar 89,7%, recall 94,4%, presisi 95,4%,  dan F-measure 94,6%. Dalam hal mengidentifkasikan lokasi kebocoran, fungsi kernel polynomial pada raw dataset meningkatkan akurasi sebesar 88,96%, recall 94,7%, presisi 91,5%, dan F-measure 92,8%. Sedangkan fungsi kernel polynomial pada process dataset mencapai akurasi sebesar 74,42%, recall 74,1%, presisi 72,8%, dan F-measure 71,3%.

Article metrics

Abstract views : 717 | views : 82

Full Text:

PDF (Bahasa Indonesia)

References


S. K. Mandal, F. T. S. Chan, and M. K. Tiwari, “Leak detection of pipeline: An integrated approach of rough set theory and artificial bee colony trained SVM,” Expert Systems with Applications, vol. 39, no. 3, pp. 3071–3080, 2012, doi: 10.1016/j.eswa.2011.08.170.

J. Mashford, D. de Silva, D. Marney, and S. Burn, “An approach to leak detection in pipe networks using analysis of monitored pressure values by support vector machine,” NSS 2009 - Network and System Security, pp. 534–539, 2009, doi: 10.1109/NSS.2009.38.

N. Mashhadi, I. Shahrour, N. Attoue, J. el Khattabi, and A. Aljer, “Use of machine learning for leak detection and localization in water distribution systems,” Smart Cities, vol. 4, no. 4, pp. 1293–1315, Dec. 2021, doi: 10.3390/smartcities4040069.

H. W. Li, J. L. Yan, W. Wu, and L. Mou, “Research on water leakage prediction of urban water supply network based on grey GM (0, N) model,” 2011 International Conference on Networking, Sensing and Control, ICNSC 2011, no. April, pp. 388–392, 2011, doi: 10.1109/ICNSC.2011.5874884.

M. S. Islam, R. Sadiq, M. J. Rodriguez, A. Francisque, H. Najjaran, and M. Hoorfar, “Leakage detection and location in water distribution systems using a fuzzy-based methodology,” Urban Water Journal, vol. 8, no. 6, pp. 351–365, 2011, doi: 10.1080/1573062X.2011.617829.

A. Rojik, Endroyono, and A. N. Irfansyah, “Water Pipe Leak Detection using the k-Nearest Neighbor Method,” Proceedings - 2019 International Seminar on Intelligent Technology and Its Application, ISITIA 2019, pp. 393–398, 2019, doi: 10.1109/ISITIA.2019.8937190.

Y. Liu, X. Ma, Y. Li, Y. Tie, Y. Zhang, and J. Gao, “Water pipeline leakage detection based on machine learning and wireless sensor networks,” Sensors (Switzerland), vol. 19, no. 23, pp. 1–21, 2019, doi: 10.3390/s19235086.

J. C. van der Walt, P. S. Heyns, and D. N. Wilke, “Pipe network leak detection: comparison between statistical and machine learning techniques,” Urban Water Journal, vol. 15, no. 10, pp. 953–960, 2018, doi: 10.1080/1573062X.2019.1597375.

R. H. Y. Perdana, H. Hudiono, and A. F. N. Luqmani, “Water Leak Detection and Shut-Off System on Water Distribution Pipe Network Using Wireless Sensor Network,” in 2019 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation (ICAMIMIA), Oct. 2019, pp. 297–301. doi: 10.1109/ICAMIMIA47173.2019.9223386.

Y. Baiji and P. Sundaravadivel, “ILoLeak-detect: An IoT-based LoRAWAN-enabled oil leak detection system for smart cities,” in Proceedings - 2019 IEEE International Symposium on Smart Electronic Systems, iSES 2019, Dec. 2019, pp. 262–267. doi: 10.1109/iSES47678.2019.00065.

J. Alves Coelho, A. Glória, and P. Sebastião, “Precise Water Leak Detection Using Machine Learning and Real-Time Sensor Data,” IoT, vol. 1, no. 2, pp. 474–493, Dec. 2020, doi: 10.3390/iot1020026.

J. A. Gómez-Camperos, E. E. Espinel-Blanco, and F. J. Regino-Ubarnes, “Diagnosis of horizontal pipe leaks using neural networks,” Journal of Physics: Conference Series, vol. 1388, no. 1, 2019, doi: 10.1088/1742-6596/1388/1/012032.

M. Henrie, P. Carpenter, and R. E. Nicholas, Real-Time Transient Model–Based Leak Detection. 2016. doi: 10.1016/b978-0-12-802240-5.00004-2.

G. Geiger, “State-of-the-art in leak detection and localization,” Erdoel Erdgas Kohle, vol. 122, no. 12, pp. 193–198, 2006.

Z. X. Yang and J. H. Zhong, “A hybrid EEMD-based SampEn and SVD for acoustic signal processing and fault diagnosis,” Entropy, vol. 18, no. 4, Apr. 2016, doi: 10.3390/e18040112.

S. Bakheet, “An SVM framework for malignant melanoma detection based on optimized HOG features,” Computation, vol. 5, no. 1, Mar. 2017, doi: 10.3390/computation5010004.

J. A. Coelho and A. Glória, “IoT Learning and Real-Time Sensor Data,” pp. 474–493, 2020, doi: 10.3390/iot1020026.

Scikit-Learn, “scikit-learn Machine Learning in Python,” 2022.




DOI: https://doi.org/10.35314/isi.v7i1.2360

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

This Journal has been listed and indexed in :

Crossref logo Find in a library with WorldCat

Copyright of Jurnal Inovtek Polbeng - Seri Informatika (ISSN: 2527-9866)

Creative Commons License
ISI: Inovtek Polbeng Seri Informatikan is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Editorial Office :
Pusat Penelitian dan Pengabdian kepada Masyarakat
 Politeknik Negeri Bengkalis 
Jl. Bathin alam, Sungai Alam Bengkalis-Riau 28711 
E-mail: jurnalinformatika@polbeng.ac.id
www.polbeng.ac.id

Web Analytics
View My Stats