Machine Learning Assisted Approach for Water Leaks Detection
- Resource Type
- Conference
- Authors
- Badar, Sara; Labghough, Souad; Al-Abdulghani, Almaha; Mohammed, Eiman; Bouhali, Othmane; Qaraqe, Khalid A.
- Source
- 2023 International Conference on Information Networking (ICOIN) Information Networking (ICOIN), 2023 International Conference on. :433-437 Jan, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Pressure sensors
Machine learning algorithms
Pipelines
Boosting
Prediction algorithms
Sensor systems
Leak detection
KNN
ANN
XGBoost
Gradient Boosting
- Language
This study examines the use of machine learning algorithms to detect water leaks in water pipes. Multiple types of sensors have been used in a water-bed system that simulates water pipelines and leaks while gathering data. Both pressure sensors and flow sensors are employed. The obtained data is then utilized to develop an AI algorithm that can detect whether a leak occurred within the pipes based on the acquired data. We tested a number of machine learning methods to train the data and use it. These tests were conducted to evaluate the accuracy of each algorithm and determine the most effective method for predicting leaks.