Comprehensive Framework for Leak Detection in Water Distribution Systems: A Vibration Signal Processing and Machine learning Approach

This study provides a new approach for identifying water distribution ‎system leaks. It blends vibration signal processing with machine learning. The ‎system is based on vibration signals from accelerometers for pipeline observation ‎through non-invasive methods and real-time. Based on a Random Forest classifier, the ‎system is able to differentiate between different leak scenarios from no-leak cases with an accuracy of 97.3%. We validated the findings using a confusion matrix, which confirmed some cases of misclassification, indicating there is still much scope for improvement. We identified key statistical features such as RMS, kurtosis, and variance as being of prime ‎importance for leak identification using feature importance analysis. These features enable capturing the specific vibration patterns of diverse leaks, ‎allowing for accurate identification. This is an improvement over conventional ‎leak detection techniques, offering a more reliable and efficient method for ‎pipeline observation. The study also discusses how the procedure could make ‎water distribution systems sustainable and operationally efficient for ‎application in the real world.‎