DOI: 10.36347/sjpms

Pages: 256-259

Data obtained by rock pyrolysis analysis is only part of the hydrocarbon content in the stratum, which will affect the credibility of information and evaluation of oil-gas-water layers. Therefore, it is necessary to restore calibration of parameters for pyrolytic chromatography. This paper selects 5 factors to analyze the geochemical analysis of hydrocarbon loss. History data to establish a neural network to analysis the hydrocarbon loss recovery correction model in this paper, the accuracy of the model meets the requirements, get better correction effect, has the value of application. Keywords: neural network; geochemical analysis; Correction