Prediction Method of Formation Pressure of Non-Undercom-pacting Glutenite Based on Support Vector Machine:A Case Study of BZ-X Gas Field
DENG Shaoqing
XU Peng
HUA Xiaoli
HE Yu
Abstract：The BZ-X Gas Field located in the Bohai Bay Basin first revealed a fracture-pore glutenite gas reservoir with huge thickness in Paleogene Kongdian Formation,which indicates that the glutenite formation in deep Kongdi-an Formation in Bozhong Sag also has great exploration potential.Meanwhile,drilling studies have confirmed that the abnormal pressure characteristics of the formation are obvious.It is of great significance to obtain accurate pre-drilling pressure prediction results in oil and gas field exploration and development to ensure drilling safety.With the development of the nonlinear mathematical theory of artificial intelligence,the paper introduced the amplitude variation with frequency(AVF)information in frequency division inversion in the research area.By taking the pres-sure measurement data of the drilled cable as the quality control condition,the nonlinear mapping relationship be-tween logging data and different frequency division seismic attributes was established by the support vector machine algorithm in machine learning.This prediction method could accurately reveal the pressure distribution characteris-tics of glutenite formation,and the formation pressure prediction results obtained are more accurate and reliable than the linear statistical method,which also points out a new direction for the prediction of abnormal pressure of special lithologic formation in the Bohai Bay Basin.
Keywords：Glutenite formationFrequency division inversionSupport vector machineFormation pressure predic-tion
Publication Date：2025-06-30
Online Publishing Date：2025-08-25(First online date of this platform, not the publication date of the document)
Pages：10( 182-191 )