Application of Evolutionary Neural Networks for Well-logging Recognition in Petroleum Reservoir

摘要

A critical task of well-logging interpretation is to differentiate oil-gas-water layers. Other approaches based on data exploration and low recognition rate are difficult to generalize oil-gas-water layers identification because of the high moisture content in the later period of development. In this research we utilize evolutionary neural networks to build the interpreting model of oil-gas-water layers and extracting well-logging parameters. By using an evolutionary neural network method to recognize reservoir stratum, it can efficiently distinguish oil-gas-water layers.