Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method

Abstract

The main purpose of this study was to investigate whether machine learning can be used to detect leak sounds in the field. A method for detecting water leaks was developed using a convolutional neural network (CNN), after taking recurrence plots and visualising the time series as input data. In collaboration with a pipeline restoration company, 20 acoustic datasets of leak sounds were recorded by sensors at 10 leak sites. The detection ability of the constructed CNN model was tested using the hold-out method for the 20 cases: 19 showed more than 70% accuracy, of which 15 showed more than 80%. HIGHLIGHTS We are introducing a next-generation leak detection technique.; We are targeting the analysis of actual leaks, not virtual.; We visualised the inherent characteristics of water leak sound.; This study introduces leak detection techniques through artificial intelligence technology.; The leak detection model proposed in this study has been proven to have sufficient reliability.;

Keywords

• actual leaks
• convolutional neural network
• hold-out method
• recurrence plot
• water leak detection
• water pipeline