Research On Fusion Algorithms In The Recognition Of Well Logs

Daqing changyuan oilfield has accumulated large numbers of logging curves and it is a good way to efficiently and economically analyze the sedimentary environment of oil reservoir according to the abundant logging curves, and to instruct the exploration and development of oilfield, which is significant in identifying and studying the distribution of sedimentary environments, sedimentary facies, microfacies and water-out layers.This paper studies and analyzes the characteristics of sednimeatary microfacies from logging curves and water-out layers, as well as the relation between logging curve response features. We have established a database connection according to the extracted eigenvalues. We used improved algorithm Rs-Ga-LVQ which is based on Rs-LVQ to respectively identify the 340 sedimentary microfacies and the 550 thin, poor water-out layers. The result shows that the improved algorithm has the highest recognition rate. Results from 261 of the sedimentary microfacies and 407 of the water-out layers are compatible to thoe in the parctice. Proved the adaptation of Rs-Ga-LVQ fusion algorithm for well logging curve identify, which is better than the Rs-LVQ fusion algorithm.