Article
Automation & Control Systems
Farouk Said Boukredera, Mohamed Riad Youcefi, Ahmed Hadjadj, Chinedu Pascal Ezenkwu, Vahid Vaziri, Sumeet S. Aphale
Summary: This article presents a novel AI workflow to enhance drilling performance by mitigating drill-string vibrations. The study uses supervised machine learning algorithms to train models and a digital twin for validation. Simulation results show significant improvement in drilling efficiency through optimized parameter selection.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Chao Gan, Wei-Hua Cao, Kang-Zhi Liu, Min Wu
Summary: In this article, a dynamic optimization-based intelligent control system for maximizing drilling efficiency by optimizing rate of penetration (ROP) is proposed. The system utilizes a moving window strategy to establish a model between rotation speed, weight on bit, depth, and ROP, and employs a hybrid bat algorithm for parameter search. Comparison results with other methods demonstrate the effectiveness of the proposed system.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Chao Gan, Wei-Hua Cao, Lu-Zhao Wang, Kang-Zhi Liu, Min Wu
Summary: This article presents an improved dynamic optimization control system for the rate of penetration (ROP) in drilling process, which successfully improves drilling efficiency and safety. The system utilizes a three-layer framework and employs if-then strategy to identify drilling conditions and a moving window strategy to establish a dynamic ROP model. The Jaya algorithm is introduced to solve the dynamic ROP optimization issue. Simulation and industrial application results show that the proposed system significantly enhances drilling efficiency and safety.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Engineering, Geological
Abidhan Bardhan, Navid Kardani, Anasua GuhaRay, Avijit Burman, Pijush Samui, Yanmei Zhang
Summary: This study successfully predicts the rate of penetration of TBM using a hybrid ensemble machine learning method, demonstrating its feasibility in a rock environment. By constructing and validating multiple models, a hybrid ensemble model superior to others was developed.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Mohsen Riazi, Hossein Mehrjoo, Reza Nakhaei, Hossein Jalalifar, Mohammadhadi Shateri, Masoud Riazi, Mehdi Ostadhassan, Abdolhossein Hemmati-Sarapardeh
Summary: One of the most important problems that the drilling industry faces is drilling cost. This study proposes smart models and a correlation to predict the rate of penetration (ROP) in order to optimize drilling time and reduce costs. Different algorithms were evaluated, and a simple empirical correlation was also found to be accurate.
SCIENTIFIC REPORTS
(2022)
Article
Energy & Fuels
Ehsan Brenjkar, Ebrahim Biniaz Delijani
Summary: ROP prediction is crucial for drilling operations and cost reduction. Machine learning models outperformed traditional models, especially when combined with metaheuristic algorithms like PSO. The study provides practical guidance for future well drilling management and planning.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Ehsan Brenjkar, Ebrahim Biniaz Delijani, Kasra Karroubi
Summary: The study aims to develop three computational intelligence-based models to estimate the rate of penetration, which are proven to be more accurate than conventional models through data preprocessing and feature selection.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2021)
Article
Energy & Fuels
Kingsley Amadi, Ibiye Iyalla, Radhakrishna Prabhu, Mortadha Alsaba, Marwa Waly
Summary: The growing global energy demand and strict environmental policies drive the adoption of technology and performance improvement techniques in drilling operations. This paper proposes a predictive optimization model for autonomous drilling systems and conducts a comparative study of surface operating parameters to evaluate optimized operating procedures. The results show that derived variables (DMSE, FET) provide higher prediction accuracy compared to surface operating parameters (WOB, RPM). The model output offers parameter optimization and adaptive control for autonomous drilling systems.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Li Yang, Tianyi Liu, Weijian Ren, Wenfeng Sun
Summary: The study applied random forest algorithm and fuzzy neural network to address the coupling problem of rate of penetration prediction in drilling engineering. By using K-means to divide data into fuzzy sets, the fuzzy neural network was trained with improved effectiveness.
Article
Energy & Fuels
Jialin Tian, Lei Tang, Yinglin Yang, Liming Dai, Changqing Xiong
Summary: This study proposes a novel drilling tool that generates constant torque and reduces stick-slip. Mathematical models are established to investigate the dynamics of the drill string system. Field tests and comparisons confirm the tool's effectiveness in increasing the rate of penetration and reducing drill bit wear.
PETROLEUM SCIENCE AND TECHNOLOGY
(2022)
Article
Energy & Fuels
Haodong Chen, Yan Jin, Wandong Zhang, Junfeng Zhang, Lei Ma, Yunhu Lu
Summary: This study focuses on characterizing the formation using acoustic transit time and establishing a data-driven ROP prediction model based on deep neural network approach. By training and testing with the exploratory well data, the established model achieves a matching degree of 82% with real data. Additionally, a drilling parameter optimization process is developed based on the ROP prediction model, which is applicable to other formations and fields.
Article
Energy & Fuels
Ibrahim Sobhi, Abdelmadjid Dobbi, Oussama Hachana
Summary: Optimizing ROP is crucial for improving drilling efficiency, with the selection of drilling bits and parameters playing a significant role. This study explored different ROP models, algorithms, and objective functions, confirming the superiority of the B&Y model in prediction and providing simple and effective optimization techniques.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Hongtao Liu, Yan Jin, Xianzhi Song, Zhijun Pei
Summary: This study proposes an intelligent prediction model based on LSTM-FNN for ROP prediction in ultra-deep wells. The results show that this model outperforms traditional FNN and LSTM models in terms of accuracy and has good generalization performance for adjacent wells.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Environmental
Utku Sakiz, Hamit Aydin, Olgay Yarali
Summary: This study investigates the impact of operational machine parameters and rock properties on drilling performance parameters for rotary core drilling conditions. The experiments reveal a strong inverse relationship between specific drilling energy and penetration rate, and a strong correlation between specific energy (470 rpm and 70 kg load) and rock sample properties. The optimal drilling performance is achieved when the penetration rate reaches 1 m/h.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2022)
Article
Energy & Fuels
Mohamed Arbi Ben Aoun, Tamas Madarasz
Summary: This article introduces a data-driven approach for predicting the rate of penetration (ROP) using machine learning and deep learning algorithms to predict the nonlinear behavior of ROP. The method has a small error in field applications and can help engineers choose the best drilling parameters to improve ROP.