Abstract
In gas drilling operations, the rate of penetration (ROP) parameter has an important influence on drilling costs. Prediction of ROP can optimize the drilling operational parameters and reduce its overall cost. To predict ROP with satisfactory precision, a stacked generalization ensemble model is developed in this paper. Drilling data were collected from a shale gas survey well in Xinjiang, northwestern China. First, Pearson correlation analysis is used for feature selection. Then, a Savitzky-Golay smoothing filter is used to reduce noise in the dataset. In the next stage, we propose a stacked generalization ensemble model that combines six machine learning models: support vector regression (SVR), extremely randomized trees (ET), random forest (RF), gradient boosting machine (GB), light gradient boosting machine (LightGBM) and extreme gradient boosting (XGB). The stacked model generates meta-data from the five models (SVR, ET, RF, GB, LightGBM) to compute ROP predictions using an XGB model. Then, the leave-one-out method is used to verify modeling performance. The performance of the stacked model is better than each single model, with R2 = 0.9568 and root mean square error = 0.4853 m/h achieved on the testing dataset. Hence, the proposed approach will be useful in optimizing gas drilling. Finally, the particle swarm optimization (PSO) algorithm is used to optimize the relevant ROP parameters.
Highlights
IntroductionAs it can reduce the overall costs of drilling
Drilling optimization is important, as it can reduce the overall costs of drilling
Six machine learning models are introduced according to their particular architecture: support vector regression (SVR), random forest (RF), extremely randomized trees (ET), gradient boosting machine (GB), LightGBM and XGB
Summary
As it can reduce the overall costs of drilling. Increasing the rate of penetration (ROP) is one optimization method. The ROP is affected by various interconnected factors (operational parameters, drill bit characteristics, and formation properties). Some physical and mathematical models were established to predict ROP (Maurer 1962; Bingham 1965; Bourgoyne and Young 1974; Warren 1987; Hareland and Rampersad 1994; Motahhari 2008; Motahhari et al 2010). The Bourgoyne and Young model considers a variety of influencing factors—mechanical parameters, hydraulic parameters, and formation parameters—and has been widely used in the prediction of ROP (Bahari and Baradaran Seyed 2007; Bahari et al 2009; Hua 2010; Rahimzadeh et al 2011; Nascimento et al 2015; Ahmed and Ibrahim 2019). The Bourgoyne and Young model considers a variety of influencing factors—mechanical parameters, hydraulic parameters, and formation parameters—and has been widely used in the prediction of ROP (Bahari and Baradaran Seyed 2007; Bahari et al 2009; Hua 2010; Rahimzadeh et al 2011; Nascimento et al 2015; Ahmed and Ibrahim 2019). Soares et al (2016) compared Hareland and Rampersad’s model (Hareland and Rampersad 1994) and Motahhari’s model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Petroleum Exploration and Production Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
