Water Pipeline Leakage Detection Based on Machine Learning and Wireless Sensor Networks

Authors

Yang Liu, Inner Mongolia UniversityFollow
Xuehui Ma, Inner Mongolia UniversityFollow
Yong Tie, Inner Mongolia UniversityFollow
Yinghui Zhang, Inner Mongolia University & University of Nebraska-LincolnFollow
Jing Gao, Tianjin Normal UniversityFollow

ORCID IDs

https://orcid.org/0000-0001-5743-9610

Document Type

Article

Date of this Version

11-12-2019

Citation

2019 by the authors

Comments

Sensors 2019, 19, 5086; doi:10.3390/s19235086

www.mdpi.com/journal/sensors

Abstract

The detection of water pipeline leakage is important to ensure that water supply networks can operate safely and conserve water resources. To address the lack of intelligent and the low efficiency of conventional leakage detection methods, this paper designs a leakage detection method based on machine learning and wireless sensor networks (WSNs). The system employs wireless sensors installed on pipelines to collect data and utilizes the 4G network to perform remote data transmission. A leakage triggered networking method is proposed to reduce the wireless sensor network’s energy consumption and prolong the system life cycle effectively. To enhance the precision and intelligence of leakage detection, we propose a leakage identification method that employs the intrinsic mode function, approximate entropy, and principal component analysis to construct a signal feature set and that uses a support vector machine (SVM) as a classifier to perform leakage detection. Simulation analysis and experimental results indicate that the proposed leakage identification method can effectively identify the water pipeline leakage and has lower energy consumption than the networking methods used in conventional wireless sensor networks.