Research on the Rate of Penetration Prediction Method Based on Stacking Ensemble Learning. (14th March 2023)

• Record Type: Journal Article
• Authors: Ren, Yangfeng; Lu, Baoping; Zheng, Shuangjin; Bai, Kai; Cheng, Lin; Yan, Hao; Wang, Gan
• Other Names: Wang Zhiyuan Academic Editor.
• Is Part Of: Geofluids. Volume 2023(2023)
• Publication Date: 2023-03-14
• Subjects: Hydrogeology -- Periodicals; Sedimentary basins -- Periodicals; Fluids -- Migration -- Periodicals; Groundwater flow -- Periodicals; Geothermal resources -- Periodicals; Fluid dynamics -- Periodicals; Earth -- Crust -- Periodicals; 551.49
• DOI: 10.1155/2023/6645604
• Languages: English
• ISSNs: 1468-8115

Abstract

Abstract : ROP is an important index to evaluate the efficiency of oil and gas drilling. In order to accurately predict the ROP of an oilfield in Xinjiang working area, a ROP prediction model based on the historical drilling data of this working area was established based on stacking ensemble learning. This model integrates the K -nearest neighbor algorithm and support vector machine algorithm by stacking ensemble strategy and uses genetic algorithm to optimize model parameters, forming a new method of ROP prediction suitable for this oilfield. The prediction results show that the accuracy of ROP prediction by this method is up to 92.5%, and the performance is stable, which can provide reference for the optimization of drilling parameters in this oilfield and has specific guiding significance for improving the efficiency of drilling operations.