Pengembangan Sistem Deteksi Kebocoran Air Berbasis Support Vector Machine Pada Jaringan Distribusi Air Di Perumda Air Minum Tugu Tirta Malang

Wicaksana, Farhan Arief (2024) Pengembangan Sistem Deteksi Kebocoran Air Berbasis Support Vector Machine Pada Jaringan Distribusi Air Di Perumda Air Minum Tugu Tirta Malang. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5009201173-Undergraduate_Thesis.pdf] Text
5009201173-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2026.

Download (5MB) | Request a copy

Abstract

Di Indonesia, PDAM (Perusahaan Daerah Air Minum) mendistribusikan air minum kepada masyarakat melalui jaringan pipa. Pada penggunaan jaringan pipa, seringkali pipa ditempatkan di bawah tanah di area luas, menyulitkan operator untuk memantau aliran air dan kondisi pipa karena keterbatasan peralatan dan tenaga. Oleh karena itu, penelitian ini menggunakan Artificial Intelligence sebagai opsi metode deteksi kebocoran air dengan memprediksi tekanan yang tercatat pada datalogger DMA(District Meter Area). Algoritma SVM (Support Vector Machine) yang digunakan sendiri untuk memprediksi hasil tekanan pada DMA yang dianalisis. Dalam penelitian tugas akhir ini, setelah melalui studi literatur dan lapangan, kemudian hasil dari software tersebut akan dimasukkan kedalam algoritma SVM. Hasil menunjukkan untuk perfomansi algoritma pada ukuran kebocoran pada DMA TL 2.2I memiliki nilai akurasi sebesar 93.5% dan F1 score sebesar 93.25% dan untuk perfomansi algoritma pada lokalisasi area kebocoran memiliki nilai akurasi sebesar 93.30% dan F1 score sebesar 93.80%. Kemudian untuk perbedaan perfomansi menggunakan data lapangan memiliki perbedaan nilai, untuk nilai akurasi dari pemodelan ukuran kebocoran menggunakan data lapangan yaitu sebesar 82.10% dan F1 score 90% serta untuk pemodelan lokalisasi area kebocoran yaitu memiliki nilai akurasi sebesar 85.71% dan F1 score 92 %. Dengan nilai perfomansi seperti yang ditunjukan pada pemodelan, maka dapat disimpulkan algoritma SVM dapat digunakan untuk mendeteksi adanya kebocoran air pada jaringan distribusi air.
====================================================================================================================================
In Indonesia, PDAMs (Regional Water Supply Companies) distribute drinking water to the public through pipelines. In the use of pipelines, pipes are often placed underground in large areas, making it difficult for operators to monitor water flow and pipe conditions due to limited equipment and manpower. Therefore, this research uses Artificial Intelligence as an option for water leak detection methods by predicting the pressure recorded in the DMA (District Meter Area) datalogger. The SVM (Support Vector Machine) algorithm is used alone to predict the pressure results on the analyzed DMA. In this final project research, after going through literature and field studies, then the results of the software will be entered into the SVM algorithm. The results show that the algorithm performance on leakage size in DMA TL 2.2I has an accuracy value of 93.5% and F1 score of 93.25% and for the algorithm performance on leakage area localization has an accuracy value of 93.30% and F1 score of 93.80%. Then for the difference in performance using acquisition data has a difference in value, for the accuracy value of the leak size modeling using acquisition data is 82.10% and F1 score 90% and for modeling the leak area localization which has an accuracy value of 85.71% and F1 score 92%. With the performance value as shown in the modeling, it can be concluded that the SVM algorithm can be used to detect water leaks in the water distribution network.

Item Type: Thesis (Other)
Uncontrolled Keywords: Artificial Intelligence, SVM (Support Vector Machine), DMA (District Meter Area), Artificial Intelligence, SVM (Support Vector Machine), DMA (District Meter Area)
Subjects: T Technology > T Technology (General) > T57.5 Data Processing
T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
T Technology > TD Environmental technology. Sanitary engineering
T Technology > TD Environmental technology. Sanitary engineering > TD481 Water distribution systems
Divisions: Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User: Farhan Arief Wicaksana
Date Deposited: 29 Jul 2024 06:58
Last Modified: 29 Jul 2024 06:58
URI: http://repository.its.ac.id/id/eprint/109411

Actions (login required)

View Item View Item