... of unknown duration between different drilling parameters, a properly designed time series analysis model may be able to capture their relationships and make reasonable predictions. Recurrent Neural Network with long short-term memory (RNN-LSTM) architecture is a deep learning algorithm capable of making...

... Abstract The work we describe here was motivated by the sizable operational difficulties and capital expenditure associated with liquid surging or "surge wave instabilities" frequently encountered in gas condensate fields in late-life production. Predicting and managing surge wave instabilities...

... been employed in recent years to improve the process of lithology prediction, enabling more accurate results at faster rates. Machine learning-based systems incorporate a wide range of indicators such as rock types, mineral composition, sedimentary structures and microfossils for efficient lithology...

... deviation survey. When performing predictions, typical real-time measurements such as downhole and well head pressure/temperature and choke position are utilized. The approach was tested on a well in a nearby field which had more frequent well tests and then extended to the considered field, which had very...

... fluids and materials historical data threshold value false positive spp model plot show japan government drilling operation artificial intelligence incident drilling variable presented data-driven model onepetro situ well prediction stuck risk trq model physics-based model detection...

... concentration upstream oil & gas united states government climate change migration residence time geochemical data sediment co 2 offshore technology conference subsurface storage co2 reservoir seismic data prediction carbon pool carbon reduction sequestration vertical migration...

... models to predict the liquid holdup in gas-liquid stratified flow in pipes: a pure ML and a hybrid model. Their accuracies are benchmarked against an HD stratified flow model. The pure ML model uses a neural network (NN) to predict liquid holdup directly. The hybrid model involves a 1D steady-state...

... Abstract Building a geomechanical model for reservoir rocks is crucial for oil and gas operations. It is essential to solving multiple designs like wellbore stability for drilling operations, hydraulic fracturing, and sand production prediction for production operations. The best method...

... on the labelled data to identify best suitable prediction model. A state-of-the-art temporal fusion transformer model was selected for time series forecasting based on experiments. The real-time and historical data possess noisy signals and skewed distribution depending upon frequency of slug events. The deep...

... model was deployed to an internal web application in which users could get a quick estimation of FPSO topsides weight by providing three features: gas production, oil production and water depth. The 2D and 3D cross plots with historic data and predicted value are also provided in the web-app for better...

...-by-cycle manner, of the axial restraint by the rock berm-pipe-seabed system, allowing the tracking of the axial restraint of the combined system across the operational life. Features of the analytical tool include the prediction of soil volume compaction and downwards displacement of the pipe with cycles...

... Abstract Objectives/Scope: This paper describes a program funded by the National Academy of Sciences, Engineering and Medicine (NASEM) that follows up on 2 (3-year) programs to better predict the behavior of the Gulf Loop Current and its associated eddies, which in some years create havoc...

... reservoir section upstream oil & gas complex reservoir hole size flow rate optimization calibration sensitivity configuration requirement prediction pressure drop workflow trajectory ht risk rpm design optimization offshore technology conference Introduction The Appomattox...

.... In this work, we discuss the development of a model to calculate corrosion rates in CO 2 systems, both pure as well as those containing impurities, with under-saturated water content at dense and supercritical conditions. A new model is developed to predict corrosion rates in CO 2 systems, both in presence...

... Abstract Good knowledge of formation pore pressure is required for the safe and economic drilling of wells. At present, Eaton and Bowers methods are widely used in pore pressure prediction, and the prediction accuracy of these methods is dependent on the accuracy of the underlying formation...

... data. Artificial neural network (ANN) is used to predict the fatigue failure of the cement sheath. The dataset is retrieved from 6 papers of One-Petro, which includes 314 cement fatigue failure cases. Inputs of the ANN were selected to be seven cement parameters (cement material, additive type...

... Abstract Drilling performance is greatly driven by the rate of penetration (ROP) and its optimization. Therefore, accurate prediction of ROP before drilling can help take measures to achieve drilling objectives smoothly. Numerous inter-twined formation and drilling parameters affect the ROP...

... refurbishment by an anti-fouling surface treatment. The thermal sensor intelligence module (TSIM) was designed to be a lightweight and self-contained system, with the ability to be easily deployed on heat transfer equipment. To make accurate and precise predictions for the absence or presence of fouling...

... is to develop several artificial intelligence (AI) agents that accurate predict the asphaltene adsorption produced by different types of nanoparticles. More than 200 experimental data points were used including different types of crude oils (light oils, heavy oils, and extra-heavy oils) combined with different...

... flow prediction of laboratory experiments. Trends of pressure drop dependence on various flow parameters agreed as well. For field data of a large gas-condensate pipeline, the model correctly predicted when hydrates form and when they are absent. These simulations, further, revealed the sensitivity...