PDF(5877 KB)
Research and application of automatic adjustment method of stratigraphic model while drilling
QiFeng SUN, HuaMin GUO, XiZhou YUE, PengYun ZHANG, ChengLiang HU
Prog Geophy ›› 2025, Vol. 40 ›› Issue (5) : 1977-1986.
PDF(5877 KB)
PDF(5877 KB)
Research and application of automatic adjustment method of stratigraphic model while drilling
In the process of horizontal well drilling, timely adjustment of the stratigraphic model based on Logging While Drilling (LWD) data is crucial for optimizing the drilling process and improving efficiency. In this paper, we propose an automatic adjustment method for the stratigraphic model while drilling. The method establishes an initial geological model based on pilot well logging data and extracts logging response characteristics between formations. During the drilling process, wavelet transform is used to segment the real-time logging response curves. The logging curves are reconstructed by integrating multiple types of information from time series, and then the Dynamic Time Warping(DTW) lower bound function and fastDTW algorithm based on early abandonment are applied to quickly search for the optimal matching segment within the constructed candidate sequence dataset, achieving formation comparison between the horizontal well and the pilot well. Finally, the stratigraphic model is adjusted based on the results of the formation comparison, thereby obtaining the true subsurface geological structure. The application results show that after adjustment using the method proposed in this paper, the morphological trend changes of the measured and simulated curves on the horizontal channel match closely, meeting the accuracy and real-time requirements for stratigraphic model adjustment while drilling.
Logging curve / Wavelet transform / Dynamic Time Warping(DTW) / Stratigraphic correlation / Stratigraphic model adjustment
|
|
|
|
|
|
|
Geler Z, Kurbalija V, Ivanovi c ′ M, et al. 2019. Dynamic time warping: Itakura vs Sakoe-Chiba. //2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA). Sofia: IEEE, 1-6, doi: 10.1109/INISTA.2019.8778300.
|
|
|
|
|
|
|
|
|
|
|
|
Li J C. 2020. Research on the stratigraphic correlation method of logging curve based on vortex search algorithm [Master's thesis](in Chinese). Daqing: Northeast Petroleum University, doi: 10.26995/d.cnki.gdqsc.2020.000732.
|
|
|
|
|
|
Rakthanmanon T, Campana B, Mueen A, et al. 2012. Searching and mining trillions of time series subsequences under dynamic time warping. //Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Beijing: ACM, 262-270, doi: 10.1145/2339530.2339576.
|
|
|
|
|
|
Shen J Y. 2017. A novel similarity measure model for multivariate time series based on LMNN and DTW [Master's thesis](in Chinese). Hangzhou: Zhejiang University.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
李金成. 2020. 基于涡流优化算法的测井曲线地层对比方法研究[硕士论文]. 大庆: 东北石油大学, doi: 10.26995/d.cnki.gdqsc.2020.000732.
|
|
|
|
|
|
沈静逸. 2017. 基于DTW和LMNN的多维时间序列相似性分析方法[硕士论文]. 杭州: 浙江大学.
|
|
|
|
|
|
|
|
|
|
|
感谢审稿专家提出的修改意见和编辑部的大力支持!
/
| 〈 |
|
〉 |