Flow assurance is a term generally used to describe the processes that may lead to fluid flow restriction in production, processing and transportation systems, and also the comprehensive management of the processes and operations to ensure effective and efficient production and delivery of oil and gas from the reservoir to the refinery. Often, the flow assurance issues are largely associated with hydrates, organic waxes and asphaltenes deposition due to changes in fluid composition, pressure and temperature conditions. Organic wax starts to precipitate from oil when temperature falls below the cloud point. The focus of this research is to characterize Malaysian crude oils from Dulang, Tapis, Miri, Dubai, and Arab fields to evaluate their tendency to precipitate wax and/or asphaltene. The oils were characterized by conducting SARA analysis with high-performance liquid chromatography (HPLC), while carbon distribution of the oils was determined by gas chromatography mass spectrometry (GC-MS). Differential scanning calorimetry (DSC) and density meter were used to measure the WAT of waxy oils and the colloidal instability index (CII) was calculated to evaluate asphaltene deposition potential. The effect of continuous carbon dioxide (CO 2 ) injection on WAT was also investigated. Results show that crude oils with higher paraffinic content exhibit higher WAT and precipitated wax. Continuous gas injection was found to lower the WAT, thus reducing the risk of wax precipitation. Tapis oil with highest CII (5.05) is the most susceptible to asphaltenes deposition, while Arab oil with CII of 1.21 has the least tendency to cause asphaltenes deposition problems.
Stuck pipe is one of the leading causes of non-productive time (NPT) while drilling. Machine learning (ML) techniques can be used to predict and avoid stuck pipe issues. In this paper, a model based on ML to predict and prevent stuck pipe related to differential sticking (DS) is presented. The stuck pipe indicator is established by detecting and predicting abnormalities in the drag signatures during tripping and drilling activities. The solution focuses on detecting differential sticking risk via assessing hookload signatures, based on previous experience from historical wells. Therefore, selecting the proper training set has proven to be a crucial stage of model development, especially considering the challenges in data quality. The model is trained with historical wells with and without differential sticking issues. The solution is based on the Artificial Neural Network (ANN) approach. The model is designed to provide users, i.e., driller or monitoring specialist, a warning whenever a risk is identified. Since multi-step forecasting is used, the warning is given with enough time for the driller or monitoring specialist to evaluate which preventative action or intervention is necessary. The warnings are provided typically between 30 minutes and 4 hours ahead. The model validation includes the performance metrics and a confusion matrix. Practical cases with real-time wells are also provided. The ML model was proven robust and practical with our data sets, for both historical and live wells. The huge amount of data produced while drilling holds valuable information and when smartly fed into an Artificial Intelligence (AI) model, it can prevent NPT such as stuck pipe events as demonstrated in this paper.
Wellbore geometry stuck pipe mechanism occurs when the string and the well are incompatible with each other. This issue is commonly related to changes in hole diameter, angle, and direction associated with symptoms such as mobile/swelling formation, undergauged hole, key seating, ledges, and high doglegs. An internal study identified that many stuck pipe incidents were associated with mechanical sticking, specifically wellbore geometry sticking with high-cost impact, which warrants proactive prevention. Throughout this paper, we provide and demonstrate how machine learning solutions can foresee the potential stuck pipe related to wellbore geometry issues based on two signs: hookload signature and dogleg severity. The application is based on the Artificial Neural Network (ANN) approach that reads the surface parameters sequence of hookload real-time data and learns with historical wells data. Machine learning (ML) then determines how the hookload behaves for each type of activity (tripping and drilling). The machine learning predictions can then be streamed on a web-based application accessible to the operations and project team. The neural network design for hookload prediction while tripping in/out considers a drag when the string moves towards a region with doglegs severity higher than the threshold chosen based on engineering judgment. This paper also discusses applications beyond real-time estimation, such as predicting the trend of the few subsequent expected hook loads up to 6 to 10 stands ahead based on case studies from previous live wells obtained from the real-time monitoring center where the product is used. The output from the machine learning solution provided a basis for risk identification and further analysis by the monitoring specialist in a proactive intervention effort to prevent stuck pipe incidents. The implementation of applications described in this paper could detect an early symptom of wellbore geometry issue; hence proactive action can be taken to avoid a potential stuck pipe event.
Despite many drilling technology improvements during recent years, hole cleaning remains a significant challenge. The variation of equivalent circulation density (ECD) is a symptom of borehole instability. Therefore, the ability to accurately estimate ECD is a key consideration for preventing hole cleaning problems that may lead to a stuck pipe, and well pressure management more generally. In this work, we demonstrate a Machine Learning approach to estimating downhole ECD in real-time using a deep neural network. Surface measurements that are widely available from most rigs are used as the model inputs, hence less configuration information is required relative to hydraulic simulations for pressure loss. Mean Absolute Errors of ~0.3-0.4 ppg were achieved on 16 validation wells and 7 holdout wells (blind test); these wells were independent of those in the training data. Prediction errors often reflect offsets between reference and predicted values; however, even with these offsets, trends in ECD behavior can still be captured correctly. The model shows promise for real-time ECD monitoring purposes to complement existing numerical methods and downhole tools. Beyond real-time estimation, other applications could include forecasting ECD a short time ahead to provide early indications of hole cleaning issues; case studies obtained from a real-time monitoring centre where this approach is used are presented as part of this work. The software tool was capable of detecting such symptoms in advance, giving the driller opportunity to take preventive actions to avoid a potential stuck pipe.
Drilling rate of penetration (ROP) is a major contributor to drilling costs. ROP is influenced by many different controllable and uncontrollable factors that are difficult to distinguish with the naked eye. Thus, machine learning (ML) models such as neural networks (NN) have gained momentum in the drilling industry. Existing models were either field-based or tool-based, which impacted the accuracy outside of the trained field. This work aims to develop one generally applicable global ROP model, reducing the effort needed to re-develop models for every application. A drilling dataset was gathered from exploration and development wells in both onshore and offshore operations from a variety of fields and regions. The wells were curated to have different water depths, down hole drive such as Rotary Steerable System (RSS), PDM, Standard Rotary, bit types (Mill Tooth, TCI, PDC) and inclinations (vertical or deviated). A deep neural network was used for modelling the relationship between ROP and inputs taken from real-time surface data, such as Torque, Weight-on-Bit (WOB), rotary speed (RPM), flow and pressure measurements. The performance of the ROP model was analyzed using historical data via summary statistics such as Mean Absolute Percentage Error, as well as graphical results such as residuals distributions, cumulative distribution functions of errors, and plots of ROP vs depth for independent holdout testing wells not included in the model fitting process. Analysis was done both in aggregate, and for each specific well. The ROP model was demonstrated to generalize effectively in all cases, with only minor increases in error metrics for the holdout test wells, where the Mean Absolute Percentage Error averaged across wells was ~20%, compared to 17.5% averaged across training wells. Furthermore, residuals distributions were centered close to zero, indicating low systematic error. This work proves the case for a "global" ROP prediction model applicable "out-of-the-box" to a broad set of drilling operations. A global ROP model has the potential to eliminate learning curves, reducing time and costs associated with having to develop a new model for every field. Furthermore, a model that effectively captures the relationships between parameters controllable by drillers and ROP can be used for automatically identifying drilling parameters that improve ROP. Preliminary field-testing of the ROP optimization system yielded positive results, with many examples of increased ROP realized after following drilling parameter recommendations provided by the software.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.