关键词: 分层防砂, 粒度特征值, 神经网络, 伽马密度测井, 样本库

Abstract:

According to researches at home and abroad，sand control design is based on reservoir particle size characteristic
value. LDA and SA are the conventional methods used to analyze particle size distributions. Both methods requires data through
core particle size testing. But sand control design can only use test well data，because no core at actual producing position can
be used when sand control measure is established，which can result in major errors. This article elaborates the relevance about
median grain size and gamma ray logging or density logging through researches on reservoir particle size and variety of log
curve response relation. And then through establishing sample pool of gamma ray logging or density logging and characteristic
value，and by neural network technology we trained learning network satisfing engineering requirements. Then the particle
size longitudinal distribution profile can be established according to development well logging data. This profile supplied data
basis for sand control layering design. At present，this method has been successfully used in several Chinese offshore oil field
in sand control optimization with errors below 10%.

Key words: layered sand control, characteristic value of particle size, neural network, gamma and density logging, sample
pool