Intelligent leak detection method for low-pressure gas pipeline inside buildings based on pressure fluctuation identification

• Published in: Journal of civil structural health monitoring 2022-10, Vol.12 (5), p.1191-1208
• Main Authors: Tian, Xinghao, Jiao, Wenling, Liu, Tianjie
• Format: Article
• Language: English
• Subjects: Buildings; Civil Engineering; Control; Data acquisition; Dynamic pressure; Dynamical Systems; Elastic waves; Engineering; Flow velocity; Gas pipelines; Hydraulic properties; Leak detection; Low pressure gases; Measurement Science and Instrumentation; Natural gas; Neural networks; Original Paper; Pipelines; Pressure pipes; Radial basis function; Steady state; Vibration; Wave reflection
• ISSN: 2190-5452; 2190-5479
• DOI: 10.1007/s13349-022-00607-y

The low-pressure pipe network inside buildings without effective leak detection means has become the most vulnerable link in the urban gas infrastructure network. Once the low-pressure gas pipeline fails and causes leakage, it is more likely to cause explosion and structural collapse. Considering the characteristics of low-pressure gas pipeline inside the building, the main difficulty in leakage identification comes from the pressure fluctuations caused by the gas usage in the pipeline. Based on steady-state calculation, we analyzed the steady-state hydraulic properties of the leakage and gas usage conditions. When the flow rates of the two conditions are close, the leakage fluctuation cannot be effectively identified based on the steady-state characteristics. We used Flowmaster to conduct transient hydraulic analysis under two conditions and found that the transient barotropic reflection wave caused by burner structure can be used as the basis for leakage detection. We built a simulation test system of low-pressure gas system for data acquisition and theoretical verification. On this basis, we proposed a set of intelligent low-pressure gas pipeline leak detection methods. The pressure signal was converted into a dynamic pressure signal, which can fully express the transient characteristics of pressure fluctuation and reduce the influence of steady-state characteristics. Wavelet packet and radial basis function neural network can intelligently learn the characteristics of dynamic pressure waves. When the leakage flow is the same as that of gas usage, the accuracy of leak detection can still be stabilized above 82.5%.