Well logging curve reconstruction based on kernel ridge regression

被引：34

作者：

Fan P. ^{[1
]}

Deng R. ^{[1
]}

Qiu J. ^{[2
]}

Zhao Z. ^{[2
]}

Wu S. ^{[2
]}

机构：

[1] Key Laboratory of Oil and Gas Resources and Exploration Technology of Ministry of Education, Yangtze University, Wuhan

[2] Well Testing Company, Qinghai Oilfield, Mangya

来源：

Arabian Journal of Geosciences | 2021年 / 14卷 / 16期

关键词：

Kernel ridge regression method; Logging interpretation; Methodological comparison; Multiple nonlinear regression; The logging curve reconstruction; The ordinary least squares;

D O I：

10.1007/s12517-021-07792-y

中图分类号：

学科分类号：

摘要：

The logging curve is the most basic and important part of the petroleum industry. It plays an incomparable role in identifying of rock and oil-gas layers, and analyzing the geological structure of the formation. It also can be used to calculate porosity, permeability, and saturation. The quality of logging curve is the premise to ensure the reliability of logging interpretation results. However, in the actual application of logging data, it is often occurred that the logging curve is distorted or missing in some well segments due to tool measurement or wellbore reasons, which affects the accuracy of logging results. At present, the conventional linear fitting and statistical analysis has been difficult to satisfy the requirements for ultra-fine reservoir analysis and evaluation. Kernel ridge regression is a multivariate nonlinear regression analysis method. It combines kernel function and least square regression analysis. This method is used to reconstruct the acoustic curve of 20 wells in the study area and explain it finely. The results show that the kernel ridge regression method can be used for multivariate nonlinear regression analysis. The curve predicted by this method has high accuracy and is worthy of popularization and use in oil fields. © 2021, Saudi Society for Geosciences.

引用

共 37 条

[1]

Cao Y.Q., Xie S.H., Image denoising algorithm for specific categories based on grid search, Comput Sci, 47, 11, pp. 168-173, (2020)

[2]

Deng R., Zhang Y., Huang Y.M., Meng F.S., Numerical modeling of borehole-to-surface logging technology based on incomplete Cholesky conjugate gradient, Arab J Geosci, 6, 7, pp. 2237-2243, (2013)

[3]

Deng R., Guo H.M., Xiao C.W., Apply array induction logging to study the low-resistivity belt zone identification method, Arab J Geosci, 7, 9, pp. 3409-3416, (2014)

[4]

Deng R., Wu D., Zhao S.Z., Numerical simulation of ground and groundwater factors affecting NMR probe, Desalin Water Treat, 125, pp. 118-125, (2018)

[5]

Du C., Shao J.H., Yang W., Wang Z.S., Deng L.J., Shen H.J., Support vector machine indoor visible light positioning optimized by grid search method, Laser J, 42, 3, pp. 104-109, (2021)

[6]

Fan Y.R., Li H., Cong Y.H., Huang R., Applicability analysis and optimization strategy of logging data standardization method, Spec Reserv, 20, 2, pp. 8-11+151, (2013)

[7]

Hoerl A.E., Kennard R.W., Ridge regression: application for non-orthogonal problems, Technometrics, 12, 1, pp. 69-82, (1970)

[8]

Hu Y.Z., Li L.Y., Comprehensive positioning of actuator end based on multilayer perceptual artificial neural network, J Agric Eng, 32, 1, pp. 22-29, (2016)

[9]

Kamyar A., Mohammad A.R., Mousavi M.A., Well logs reconstruction by DCT based IPRM and genetic algorithm, J Pet Sci Eng, (2020)

[10]

Liang Q., Tian J., Wang F., Zhang X., Soft-Sediment deformation structures and sand body architecture in the chang 6 oil member of the upper triassic yanchang formation, southwestern ordos basin, China, Earth Sci Res J, 23, pp. 119-126, (2019)

← 1 2 3 4 →