Pipeline Leak Detection in Two Phase Flow Based on Fluctuation Pressure Difference and Artificial Neural Network (ANN)

Pipe network was an important part of the fluid transport infrastructure. On the other hand, the pipeline leak detection in two-phase flow using the flow and pressure parameters is very rarely studied. A system on the basis of the Artificial Neural Network (ANN) was proposed for detecting the pipeline leak for the two-phase plug flow by using the pressure difference measurement. In the present research, water-air mixture flows in pipe horizontal of 24 mm inner diameter. Artificial pipeline leak was modeled with the leak of solenoid valve on the bottom and top of pipe. Differential Pressure Transducer (DPT) was placed after the leak position and connected by the high-speed data acquisition. The fluctuations of the pressure difference signals were recorded as a time series of random data. The data of the combinations of the input flow rate, the pressure difference can be used to identify the pipeline leak in two-phase flow plug by using ANN. The results demonstrated a very good ability to the pipeline leak on two-phase flow.