Identification of Gas-Water Two-Phase Flow Patterns in Horizontal Wells of Shale Gas Reservoirs Based on Production Logging Data

In order to clarify the gas-water two-phase flow law in horizontal wells and study characteristics wells, firstly, a well is numerically simulated analyzed, pattern distribution under different inclination angles phase separation rates obtained. Secondly, series of production logging instruments including CAT instrument was used conduct experimental research on conditions, measured values each probe were extracted reflect local holdup patterns. Finally, SSA-BP neural network algorithm identify wellbore by using parameters such as center holdup, angle, spinner revolution, measurements. The recognition accuracy improved from 83.75% 91.66%, operation speed accelerated. It provides idea explore wells.