Related references
Note: Only part of the references are listed.
Article
Computer Science, Interdisciplinary Applications
Mohammad Reza Delavar et al.
Summary: This study proposes a hybrid machine learning approach using random forest and multi-objective particle swarm optimization to optimize drilling factors. By constructing a dataset and using RF learning, models related to ROP and TOB were obtained and optimization was achieved by defining constraints and cost functions. The results show that the proposed method can significantly improve drilling performance and optimize actual drilling factors.
COMPUTERS & GEOSCIENCES
(2023)
Article
Engineering, Marine
Ali Shahsavari et al.
Summary: This study shows that applying a superhydrophobic coating on the entire surface of a hydrofoil is not always beneficial for hydrodynamic performance. Depending on the angle of attack, Reynolds number, and slip length, certain regions on the hydrofoil surface should be left uncoated to achieve the optimal superhydrophobic pattern. By using a genetic algorithm combined with a two-dimensional RANS solver, the optimum superhydrophobic pattern was determined.
Article
Engineering, Marine
Zhiming Yin et al.
Summary: Offshore drilling in deepwater faces difficulties such as harsh operating environments and complex downhole geological conditions. Dual gradient drilling technology manages wellbore pressure by applying multiple pressure gradients in the annulus, allowing for the application of managed pressure drilling technology in deepwater conditions. However, decision-making for deepwater dual gradient drilling schemes is influenced by many factors, bringing confusion to scheme optimization. This study uses the fuzzy comprehensive evaluation method to determine the most effective dual gradient drilling technology based on drilling capacities and equipment requirements in a specific scenario, and results suggest that the subsea mud lifting pump system has better applicability in this case.
Article
Engineering, Marine
Xuyue Chen et al.
Summary: In this study, a ROP prediction method for offshore large-scale cluster ERWs drilling based on machine learning and big-data techniques is proposed. A total of 9,193,408 data points of 27 input parameters affecting ROP are collected from China Bohai Oilfield. 12 kinds of ROP prediction models based on various machine learning algorithms are established, and the RNN model with LSTM as neuron structure shows the best prediction accuracy.
Article
Energy & Fuels
Fengtao Qu et al.
Summary: The optimization of drilling parameters has been a topic of research interest for many years due to the potential cost-saving benefits. However, achieving highly accurate and optimized drilling parameters with rapid and cost-effective simulation runs is challenging. This study proposes a multiobjective optimization model for predicting drilling parameters, considering ROP, UDC, and MSE as objective functions, and WOB and RPM as optimization variables. The model shows promising results in optimizing WOB and RPM to achieve higher ROP and lower MSE and UDC when drilling is free of complications.
GEOENERGY SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Marine
Yuki Obara et al.
Summary: This study evaluated the prediction of significant wave height using transfer learning in long short-term memory networks. The results showed that transfer learning improved the accuracy of the prediction and transferring all layers was more effective than transferring only part of the layers.
Article
Energy & Fuels
Fengcai Huo et al.
Summary: This paper proposes a new hybrid deep learning model for predicting reservoir evaluation parameters in low permeability oilfield. The model is constructed based on TCN and LSTM networks, and utilizes particle swarm optimization for optimizing hyperparameters. The results demonstrate that the model improves the prediction accuracy of evaluation parameters.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Review
Geology
Behnam Sadeghi
Summary: This article introduces commonly used correlation coefficient (CC) methods in geochemical studies and discusses their advantages and limitations when dealing with different types of data. It then introduces a new correlation method, Chatterjee CC (CCC), which is simple, computationally efficient, and robust to various types of data. A Python package called TripleCpy was developed to apply CCC to datasets and its efficiency was demonstrated compared to traditional methods.
ORE GEOLOGY REVIEWS
(2022)
Article
Thermodynamics
Xuyue Chen et al.
Summary: This study proposes an innovative method for developing offshore natural gas hydrate (NGH) from existing oil & gas platforms and investigates its recovery performance through numerical simulation. The results show that this method can significantly reduce NGH concentration and produce a large amount of natural gas, with bottom hole pressure and formation temperature being the key controlling factors, and the production mode of continuous injection-intermittent production being the most effective.
Article
Energy & Fuels
Mahdi Bajolvand et al.
Summary: Drilling optimization is essential in the oil and gas industry, and this study proposes a geomechanics-based workflow to optimize controllable drilling parameters. By developing geomechanical models and utilizing intelligent prediction models, the study successfully optimized parameters such as drilling rate and torque. Real-time optimization of the best parameters was achieved using an optimization algorithm. The results showed significant improvements in drilling time and mechanical specific energy.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Shaoqun Dong et al.
Summary: This study establishes an intelligent prediction method for fractures in tight carbonate reservoirs using artificial intelligence. By utilizing multi-source isomerous data and coupling single-well fracture identification and interwell fracture trends, the method reduces uncertainties in fracture prediction. It also improves fracture identification accuracy and fracture trend prediction by incorporating artificial intelligence techniques and seismic attributes. The proposed method demonstrates significant improvements in accuracy compared to conventional methods.
PETROLEUM EXPLORATION AND DEVELOPMENT
(2022)
Article
Energy & Fuels
Bingjie Cheng et al.
Summary: This paper proposes a machine learning-based method for predicting favorable reservoirs in deep shale gas. The method combines parameter correlation analysis, dimension reduction, and integrated characterization to accurately predict the spatial distribution of reservoirs. This method provides valuable support for the exploration and development of shale gas.
PETROLEUM EXPLORATION AND DEVELOPMENT
(2022)
Article
Energy & Fuels
Jiang Guancheng et al.
Summary: This article reviews the current status of drilling fluid technologies with primary intelligence features at home and abroad, elaborates on the development background and intelligent response mechanisms of drilling fluid technologies, and proposes three development suggestions.
PETROLEUM EXPLORATION AND DEVELOPMENT
(2022)
Article
Energy & Fuels
Mikkel Leite Arno et al.
Summary: A novel streaming learning approach is proposed, utilizing a deep neural network to estimate at-bit density using drilling parameters and continuously updating the model during operation, outperforming a standard deep learning approach. Statistical analyses and data visualizations confirm the variations in the relationship between drilling parameters and density log among different wellbores, highlighting the need for a streaming learning approach.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2021)
Review
Computer Science, Interdisciplinary Applications
Wei Li et al.
Summary: This paper comprehensively discusses learning-based intelligent optimization algorithms (LIOAs), including statistical analysis, classification of learning methods, applications in various scenarios, and engineering applications, as well as future insights and development directions.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2021)
Article
Energy & Fuels
Rahman Ashena et al.
Summary: Proper selection of drilling parameters and dynamic behavior is crucial for improving drilling performance. Development of an efficient AI method to predict control parameters is critical for drilling optimization. The AI approach presented in the paper utilizes optimized ANNs to model non-linear, multi-input/output drilling system behavior, providing quantified recommendations on optimal drilling parameters.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2021)
Article
Energy & Fuels
Yan Tie et al.
Summary: The study developed a new drill bit selection method using grey relational analysis theory and absolute ideal solution construction, which is simple to calculate and suitable for dynamic drill bit databases. This method can improve drilling efficiency, extend drill bit lifespan, and demonstrate good economic benefits and compatibility in actual drilling operations.
PETROLEUM EXPLORATION AND DEVELOPMENT
(2021)
Article
Energy & Fuels
Kuang Lichun et al.
Summary: This paper describes the research progress and application of artificial intelligence in petroleum exploration and development, covering machine learning, computer vision, and deep learning technology. The potential development directions of artificial intelligence in petroleum exploration and development include intelligent production equipment, automatic processing and interpretation, and professional software platform.
PETROLEUM EXPLORATION AND DEVELOPMENT
(2021)
Article
Energy & Fuels
Mayowa Oyedere et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2020)
Review
Green & Sustainable Science & Technology
Xuyue Chen et al.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2020)
Article
Energy & Fuels
Chiranth Hegde et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2019)
Review
Energy & Fuels
Rudolf Suppes et al.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2019)
Article
Engineering, Petroleum
Xuyue Chen et al.
Article
Energy & Fuels
Chiranth Hegde et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2018)
Article
Energy & Fuels
Chiranth Hegde et al.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2017)
Article
Energy & Fuels
Chiranth Hegde et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2017)
Article
Energy & Fuels
Xuyue Chen et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2016)
Article
Energy & Fuels
Gao Deli et al.
