Feature extraction and identification of leak acoustic signal in water supply pipelines using correlation analysis and Lyapunov exponent

The leakage of water supply pipeline is a common problem in the world. Timely discovery and treatment of leakage can avoid drinking water pollution, save water resources or avoid road collapse accidents. Therefore, it is of great practical significance to study pipeline leak detection methods. In this experiment, piezoelectric acceleration sensors were placed in different locations of a leak pipe to acquire the leakage signals. According to the generation mechanism of leak acoustic signals, the unpredictability characteristics of leak signal are investigated. The autocorrelation function is used to describe the unpredictability of the leak signal because it has the ability to analyze the coherent structure of time series, and the Lyapunov exponent can describe its complexity. The autocorrelation function sequence is used as featured extraction object. The Lyapunov exponent of this sequence is used to quantify the signal characteristics. By this method, the leakage can be effectively identified.