Asphaltene deposition is a significant flow assurance challenge in Abu Dhabi with over 100 onshore wells impacted. Until recently, there had been no applicable IoT device in the industry for direct measurement of the problem, which prompted the national oil company to sponsor a real-time sensor for asphaltene quantification. A second generation of that device is now available with enhanced capabilities and has been delivered in country, with preparation now ongoing for deployment across multiple onshore wells. Current ways of identifying asphaltene problems via accessibility checks with slickline are reactive, often too late, and thereby increase cost of clean-up and production losses. By quantifying in real-time the asphaltene as it flows through the wellhead, much earlier problem detection is made feasible. Such quantification has been made possible by resonating asphaltene molecules in applied magnetic and GHz fields as those molecules flow through the wellhead. The peak of the resonant signal is directly proportional to the asphaltene in the crude, with decrease in signal indicating potential deposition. Adding cloud-based, machine-learning to the system allows local in-country team to make efficient use of the data. First deployment of the resonant system in Abu Dhabi demonstrated the resolution of asphaltene signature was better than 0.1% when measured at atmospheric pressure and temperature. Subsequent testing in pressure vessels has shown remarkable independence to fluid pressure, even up to 2000 psi. Original system had a sensitivity sufficient to detect only the asphaltene peak. New system reveals multiple smaller peaks in the spectra which can be used for other flow assurance applications - for example, vanadyl porphyrins display a unique characteristic. By mixing solvents and precipitants with crude oil, we have confirmed that the asphaltene peak measures same value whether the asphaltene is in, or out, of solution which is precisely the feature that allows surface data to be representative of the cumulative precipitation downhole. The main advance, however, is that the system data will now be available on multiple wells in the field, which allows Operator to compare and contrast different flow assurance optimizations. This should lead to substantial cost savings in addition to minimizing well downtime and potential loss of production, all in alignment with the Operator’s 2030 "Smart Growth" strategy. The additional spectral information also allows spectrometer use for real-time analysis of water properties (dissolved solids) and rock typing (geochemistry). More generally, the system becomes a real-time platform for advanced chemical analysis at the wellhead. The result is an industrial Internet of Things (IoT) real-time monitoring device, the first of its kind, that not just detects asphaltene deposition but also makes possible the optimization of chemical programs by incorporating surface data into an integrated flow assurance management system.
Mature field operators collect log data for tens of years. Collection of log dataset include various generation and multiple vintages of logging tool from multiple vendors. Standard approach is to correct the logs for various artefacts and normalize the logs over a field scale. Manually conducting this routine is time consuming and subjective. The objective of the study was to create a machine learning (ML) assisted tool for logs in a giant Lower Cretaceous Carbonate Onshore field in Abu Dhabi, UAE to automatically perform data QC, bad data identification and log reconstruction (correcting for borehole effects, filling gaps, cleaning spikes, etc.) of Quad Combo well logs. The study targets Quad Combo logs acquired since mid-60's. Machine learning algorithm was trained on 50 vertical wells, spread throughout the structure of the field. The workflow solution consists of several advanced algorithms guided by domain knowledge and physics based well logs correlation, all embedded in an ML-data-driven environment. The methodology consists of the following steps: oOutliers detection and complete data clustering.oSupervised ML to map outliers to clusters.oRandom Forest based ML training by clusters, by logs combination on complete data.oSaved models are applied back to the whole data including outliers and sections with one or several logs missing.oValidation and Blind test of results.oModels can be stored and re-used for prediction on new data. The ML tool demonstrated its effectiveness while correcting logs for outliers’ like Depth Offsets between logs, identifying Erroneous readings, logs prediction for absent data and Synthetic logs corrections. The tool has a tendency to harmonize logs. First test demonstrated robustness of the selected algorithm for outliers’ detection. It cleaned data from most of contamination, while keeping good but statistically underrepresented logs readings. Clustering algorithm was enhanced to supplement cluster assignment by extraction of the corresponding probabilities that were used as a cut-off value and utilized for a mixture of different ML models results. This application made results more realistic in the intervals where clustering was problematic and at the transition between different clusters. Several intervals of bad and depth shifted logs corrections were noticed. Outliers’ corrections for these logs was performed the way that at Neutron-Density or Neutron-Sonic cross-plots points were moved towards expected lithology lines. Algorithm could pick-up hidden outliers (such as synthetic logs) and edited the logs to make it look intuitively natural to a human analyst. The work successfully demonstrated effectiveness of ML tool for log editing in a complex environment working on a big dataset that was subject of manual editing and has number of hidden outliers. This strong log quality assurance further assisted in building Rock Typing based Static Model in complex and diagenetically altered Carbonates.
ADNOC is continuously enhancing its capabilities to manage its oil and fields efficiently by better planning, execution and operations that drives field development decisions, well performance, and safe operations. In this regard, ADNOC envisages to leverage the evolving Oil and Gas 4.0 technologies to enhance the well planning decisions of the sub-surface and drilling team through data-driven and AI methods. Effective well planning and operations require collaboration between different subsurface teams and drilling team leveraging multidisciplinary data, historical events and risks and constructing integrated drilling and sub-surface model for collaborative planning and keeping the model live. This requires having a live sub-surface model that is kept close to the field reality while reducing uncertainties. However, extracting key learnings, knowledge and experience from a variety of sources and reports is intense and requires lot of manual processing of data. An AI-based solution leveraging data analytics, natural language processing and machine learning algorithms is developed to automatically extract knowledge from a variety of data sources and unstructured data in building a live intelligent model that enables effective well planning, predicting operational hazards and plan mitigation. The solution systematically extracts, collects, validates, integrates, and processes a variety of data in different formats such as well trajectory, completion, historical events, risk offset well information, petrophysical data, geo-mechanical data, and technical reports. Newly acquired data comprising drilling events, geological and reservoir properties are integrated continuously to keep the model live and digital representation.
Asphaltene deposition has been identified as one of the top flow assurance challenges in a number of onshore fields in Abu Dhabi with over 100 wells impacted. There was no device in the industry for direct measurement of asphaltene deposition, so the national oil company sponsored an R&D project to develop a sensor that could quantify the percentage of asphaltene in the flowing oil. Current ways of identifying an asphaltene problem rely upon accessibility checks with slickline units and hence clean-up operations are reactive and are often too late. In order to detect the problem earlier, an asphaltene specific real-time sensor would be required. The sensor design selected built on the concept of Electron Paramagnetic Resonance (EPR), wherein free-radicals in the asphaltene are resonated by an external magnetic field. The EPR signal is directly proportional to the amount of asphaltene in the crude, with a signal drop indicating potential deposition upstream of the sensor. By focusing on the asphaltene free-radical response, rather than looking for a broad range of molecules, it proved possible to miniaturize and ruggedize a device for oilfield applications. It remained important to prove that this modification did not casuse a loss of resolution. For the first field trial in these onshore fields, instead of having the device installed directly into one well, the system was tested off-line so that daily analysis from 15 different wells could be achieved and device resolution could be tested. The resolution proved to be better than 0.1%. Moreover, some wells showed nearly 5% variation from one day to the next while other wells showed barely 1% variation. The wells with the higher standard deviation were those which had historically seen more asphaltene problems. Results from these 15 wells exceeded expectations, so a decision was taken to launch a second field trial with the device now able to be mounted inline at the wellhead for real-time continuous monitoring. It is anticipated that the application of this system will help plan clean-up jobs before a well gets totally plugged. This should lead to substantial cost savings in addition to minimizing well downtime and loss of production. This paper presents a novel solution that was developed from inception or "ideation" all the way to commercialization through a research collaboration between a national oil company, a university and a start-up technology provider. The outcome is an industrial Internet of Things (IoT) real-time monitoring device, the first of its kind, that detects asphaltene deposition and makes it possible to optimize chemical programs by incorporating surface data into an integrated flow assurance management system.
Objectives/Scope Majority of the world's gas lifted wells are under-optimized owing to changing reservoir conditions and fluid composition. The gas lift valve (GLV) calibration is required with changing conditions. Apart from that, an allowance needs to be kept so that the valve change remains valid for longer time. Compounding this, when adjusting gas lift parameters, it was not easy for the gas lift operator to make data-driven decisions to assure continuous maximized production. These challenges are further amplified with dual completion strings: fluctuating casing pressure; unpredictable temperatures due to the proximity of the two strings; and inability to individually control the injection rates to each string. String dedicated to the formation with lower productivity and reservoir pressure tends to "rob" gas from other string. Operating philosophy in such cases end up producing from one string. Production optimization in such cases requires frequent intervention with attendant costs and risks thus presents an opportunity to re-imagine gas lift well design. Methods, Procedures, Process ADNOC in collaboration with Silverwell developed a Digital Intelligent Artificial Lift (DIAL) system, which consists of multiple port mandrels to be placed at GLV depths. These mandrels are connetced to the surface operating system with a single electrical cable. The ports can be selectively opened or closed by sending an electric signal from the surface unit. In addition, pressure and temperature sensors are also placed which help record these parameters in real time. Such a system enables the choice of depth, injection rate, loading and unloading sequence controlled from the surface. Realtime optimization is possible as pressure/temperature data helps draw accurate gradient curves. This system makes gas lift optimization possible in dual gas lift wells. Results, Observations, Conclusions It has been estimated that this technology delivers a production increase approaching 20% for single completion wells, and exceeding 40% for dual-string gas lifted wells. Recognizing this opportunity, a business case and implementation plan were developed to pilot a dual-string digitally controlled gas lift optimization system. Novel/Additive Information This paper will describe, the screening phase, business case preparation, risk assessment and validation process, leading to this 1st worldwide implementation of a fully optimized dual completion gas lifted well. Implementation plan of novel digital gas lift production optimization technology in an onshore dual completion well. The completely original approach increases safety, efficiency, operability and surveillance.
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.