CAJ | 학술논문

合理确定地层岩性对合理选择钻头类型、快速建立岩性剖面、及时发现油气层和卡准取心层位有着重要意义。以录井资料为基础，结合已钻井的测井资料，根据BP神经网络和人工蜂群算法，建立基于BP神经网络算法的人工蜂群算法模型。应用该模型在青海油田某区块进行地层岩性随钻识别试验，试验结果与测井资料解释结果相比，符合率可达91．35％。
합리학정지층암성대합리선택찬두류형、쾌속건립암성부면、급시발현유기층화잡준취심층위유착중요의의。이록정자료위기출，결합이찬정적측정자료，근거BP신경망락화인공봉군산법，건립기우BP신경망락산법적인공봉군산법모형。응용해모형재청해유전모구괴진행지층암성수찬식별시험，시험결과여측정자료해석결과상비，부합솔가체91．35％。
During the drilling process, it is very important to identify formation lithology in order to select bit types, quickly establish the lithology section, discover the oil and gas layers in time, and locate the coring layer exactly. Based on the mud logging data and combining with the logging data of the drilled wells, an artificial bee colony algorithm based on BP neural network is established for lithology identification. This model was verified in Qinghai oilfield. Compared with the geological explanation of logging data, the prediction result of the model is much better than ever before and the efficiency coefficient can reach as high as about 91.35%.