Petroleum Science >2023,??Issue6:??- DOI: https://doi.org/10.1016/j.petsci.2023.06.005
Risk pre-assessment method for regional drilling engineering based on deep learning and multi-source data Open?Access
文章信息
作者：Yu-Qiang Xu, Kuan Liu, Bao-Lun He, Tatiana Pinyaeva, Bing-Shuo Li, Yu-Cong Wang, Jia-Jun Nie, Lei Yang, Fu-Xiang Li
作者單位：
投稿時(shí)間：
引用方式：Yu-Qiang Xu, Kuan Liu, Bao-Lun He, Tatiana Pinyaeva, Bing-Shuo Li, Yu-Cong Wang, Jia-Jun Nie, Lei Yang, Fu-Xiang Li, Risk pre-assessment method for regional drilling engineering based on deep learning and multi-source data, Petroleum Science, Volume 20, Issue 6, 2023, https://doi.org/10.1016/j.petsci.2023.06.005.
文章摘要
Abstract: Accurately predicting downhole risk before drilling in new exploration areas is one of the difficulties. Using intelligent algorithms to explore the complex relationship between multi-source data and downhole risk is a hot research topic and frontier in this field. However, due to the small number and uneven distribution of drilled wells in new exploration areas and the lack of sample data related to risk, the training model has insufficient generalization ability, and thus the prediction is not effective. In this paper, a drilling risk profile (depth domain) rich in geological and engineering information is constructed by introducing a quantitative evaluation method for drilling risk of drilled wells, which can provide sufficient risk sample data for model training and thus solve the small sample problem. For the problem of uneven distribution of drilling wells in new exploration areas, the concept of virtual wells and their deployment methods were proposed. Besides, two methods for calculating rock mechanical parameters of virtual wells were proposed, and the accuracy and applicability of the two methods are analyzed. The LSTM deep learning model was optimized to tap the quantitative relationship between drilling risk profiles and multi-source data (e.g., seismic, logging, and rock mechanical parameters). The model was validated to have an average relative error of 9.19%. The quantitative prediction of the drilling risk profile of the virtual well was achieved using the trained LSTM model and the calculation of the relevant parameters of the virtual well. Finally, based on the sequential Gaussian simulation method and the risk distribution of drilled and virtual wells, a regional 3D drilling risk model was constructed. The analysis of real cases shows that the addition of virtual wells can significantly improve the identification of regional drilling risks and the prediction accuracy of pre-drill drilling risks in unexplored areas can be improved by up to 21% compared with the 3D risk model constructed based on drilled wells only.
關(guān)鍵詞
-
Keywords: Pre-drill risk assessment; Risk samples; Deep learning; LSTM neural network; 3D model