Django-based framework database for leakage detection using machine learning for water distribution networks

Leakage in water supply pipe networks is a critical issue, with traditional detection methods being inefficient and error-prone. Acoustic-based leak detection often lacks standardized databases, limiting its effectiveness. This study proposes an integrated system using MySQL, Python, and Django for managing and analyzing acoustic leakage data. The system incorporates Variable Modal Decomposition (VMD), Wavelet Threshold Noise Reduction, Feature Extraction, and Support Vector Machine (SVM) for accurate leak detection. Experimentation on 413 labeled acoustic samples achieved classification accuracies of 96. 1% (training set) and 97. 4% (test set). This approach enhances detection precision and offers a scalable solution for real-time monitoring, with significant practical implications for improving water distribution system management and decision-making.

Authors

• Yiwei Xie
• Mengze Gao
• Fan Luo State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA) School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
• Ao Zhou Chongqing University of Posts and Telecommunications
• Yunfeng Yang
• Jian Hu Queen Mary University of London
• Wei Jiang National Key Laboratory for Novel Software Technology, Nanjing University
• Yuanyao Ye

Keywords

• Water supply system
• Database management system
• Django
• Statement analysis
• Leakage prediction