Cement evaluation data acquired in oil and gas wells for confirmation of zonal isolation, channeling in cement behind casing and well integrity. All available technologies for cement evaluations are primarily measurements of acoustic parameters like amplitude of first arrival, full waveform recording of refracted wave, impedance and attenuation or there a combination. Generally, operationsPetrophysicist, petroleum engineer or service providers are responsible for evaluation of cement bond logs and propose remedial jobs if required. This cement bond log interpretation is quite subjective if performed through pure visual interpretation and its accuracy depends on objective of well, work pressure and experience of interpreter. This paper talks about how ADNOC Onshore has leveraged machine learning (ML) for interpretation of various cement bond logs from several service providers. In green fields, cement evaluation is very important in all new wells to ensure good cement quality and zonal isolation and it is also equally important in in brown fields where 1000s of wells were drilled where well integrity issues are of common occurrence. Major challenges in evaluation are inconsistency and human bias in interpretation and as a result, interpretation may vary from one interpreter to the other. Authors have tested different ML techniques (Random Forest Classification & Neural Net) and smart way of data training. Final recommendation is to use nested models instead of single model. In this technique, input measurements and required solutions will be classified and divided into different classes, a separate ML model will be built for each class and combine all the models to get final cement evaluation and recommendations. Final results include data quality flags, cement bond quality, zonal isolation, channeling, micro annuals, areal cement map (if analyzed field wise), anomaly maps (if analyzed data from offset wells at different times), and recommendation. In this project, a simple easy to use user interface has been developed to browse the cement logs and use the trained ML models to predict the cement evaluations with a click of a button. This ML based cement bond evaluation is proved to be very effective and saved 75% of efforts by operational Petrophysicists. The interpretation accuracy has been significantly improved. This method has potential to be used at rig site. These models are very cost effective with, minimum human bias, and improves consistency as well as independent of wells or type of reservoirs. These models are tested across ADNOC Onshore Wells and can be extended to any well irrespective of geographic locations. This paper discusses machine-learning approach, evaluation of various algorithms and testing results for cement evaluation log from various service providers.
Carbonates exhibits diverse flow characteristics at pore scale. Petrographic study reveals micro-level heterogeneities. Thin sections are key to assess reservoir quality although these are images and interpretations in text format. Thin section microscopic analysis is descriptive and subjective. To an extent, optical point counting is routinely used quantitatively to estimate porosity, cement, and granular features. Overall, thin section descriptions require specialist human skill and an extensive effort, as it is repetitive and time consuming. Thus, a manual process limits the overall progress of rock quality assessment. There is no recognized method to handle thin sections for direct input with conventional core data due to its image and descriptive nature of data. An automated image processing is one of the emerging concepts designed in this paper to batch process thin sections for digital reservoir descriptions and cross correlating the results with conventional core analysis data. Thin section images are photomicrographs under plane polarized light. Initially, denoise and image enhancement techniques were implemented to preserve elemental boundaries. Computational algorithms mainly, multilevel thresholding and pixel intensity clustering algorithms were programmed to segment images for extracting elements from segmented regions. The extracted elements were compared with original image for labeling. The labeled elements are interpreted for geological elements such as matrix, pores, cement, and other granular content. The interpreted geological elements are then measured for their physical properties like area, equivalent diameter, perimeter, solidity, eccentricity, and entropy. 2D-Porosity, polymodal pore size distribution, mean pore size, cement and granular contents were then derived for each thin section image. The estimated properties were compared with conventional core after calibrating with laboratory NMR data. The whole process is automated in a batch process for a specific reservoir type and computational cost is analyzed for optimization. 2D-porosity is in excellent agreement with core porosity, thus reducing uncertainty that arises from visual estimations. Scale related issues were highlighted between 2D porosity and core porosity for some samples. Polymodal pore size distributions are in good correlation with NMR T2 distribution compared to MICP distributions. The correlation coefficient was understood to be equivalent to surface relaxivity. A digital dataset consisting of 2D porosity, eccentricity, entropy, mean pore size, cement and grain contents is automatically extracted in csv format. The digital dataset, which was previously in text format in conventional analysis, is now a rich quantitative dataset. This paper demonstrated a unique and customized solution to extract digital reservoir descriptions for geoscience applications. This significantly reduced the subjectivity in visual descriptions. The solution presented is scalable to large number of samples with significant reduction in turnaround and effort compared to conventional techniques. Additional merit is that the result from this method has direct correlation to conventional core data for improving rock typing workflows. This paper presents a novel means to use thin section images directly in digital format in geoscience applications.
Well Candidate Recognition (WCR) data analytics solution was developed to expedite the process of identifying unhealthy wells that may require rig/rigless interventions based on data integration, automation, and advanced data-driven models. The solution expedites well performance review process to pinpoint candidates for stimulation, N2 lift, Gas lift conversion, Water/Gas shutoff, etc. It provides a flexible visualization platform to highlight hidden well performance insight, prioritizing well intervention activities. Before the solution was in place, a time-consuming well performance review's process was performed well by well bases. All petroleum engineers were involved in the process that takes months to compile a solid list of opportunities for production enhancement. In addition, each engineer utilized their own process to assess well performance using partially company best recommended practices. It was notice that most expensive field activities were the ones with lowest success performance indicators, pushing the asset to review, standardize and automate the process of well intervention candidate's selection. The solution enforced best reservoir management practices for reservoir/well surveillance and optimization, identifying opportunities to align reservoir management goals with short term production optimization and sustainable reservoir development, adopting new data driven technologies for improving reservoir recovery/management for cost rationalization. The implementation of this solution permitted to identify 20 hidden opportunities for production improvement to support production target achievement with an actual gain of 20MBOPD. On the other hand, all well interventions were successful executed with and avg. success factor of 103%, exceeding in most cases the expected gain, compared with previous years avg. success factor of 32%. The substantial increment in the success factor of the most expensive field activities had a favorable impact over asset UTC. WCR's Dashboards leveraged legacy data, models and smart field capabilities, using advance visualization feature to identifying unhealthy wells, that may require rig/rigless intervention based on best reservoir management practices, providing an efficient/automated well performance review saving 70% of the petroleum engineer's time. Opportunities are assessed and ranked based on expected gain via intelligent action tracking system to ensure action completion and production contribution, perusing higher recovery while delivering consistent results. It also offers: GIS Map capability to identify localized poor properties or issues; pressure data and automated well model update to identify high drawdown (Skin), reservoir pressure decline and actual well capacity with automated peer comparison to support production optimization workflow; ability for quick Identification of erroneous data loaded in official data sources; well intervention dashboard to assess success of actual/previous Rig/Rigless jobs.
As hydrocarbon fields are maturing, field sustainable oil production rate (FSOPR) assurance is a challenge for operators to deliver the demands while adhering reservoir management guidelines after accounting for all well & facility downtimes and system inefficiencies. As part of digital transformation journey, ADNOC Onshore has embarked on an initiative to automate FSOPR forecast while eliminating inefficiencies in current process, standardization, leveraging robust data integration and analytics. FSOPR forecast is probably the most complex task performed by oil companies as involved the orchestration of all support and technical departments from the field to the terminal. Effective FSOPR estimation is an integrated effort from reservoir/petroleum engineering, drilling/well services, operations, oil movement, planning, maintenance, engineering and reliability teams. The assurance process requires a structured and integrated approach of data gathering, review, and simulations to produce a reliable forecasts. Before, data/process integration and reporting was time-consuming representing a real challenge as it was managed through manual data-loading in spreadsheets & emails with low visibility to all stakeholders. Now FSOPR is estimated using up-to-date well/network models, including contribution from newly drilled & well reactivation plans, well-performance deterioration and production restoration from field activities. Similarly planned/unplanned losses from reservoir management (RM), field activities & facility maintenance jobs are optimized through the solution, offering integration with reliability models. The automated web-page solution leverages business process engine enabled by intelligent data integration from various workflow elements and allows all stakeholders to collaborate in one portal to have on single version of the truth. The data abstraction layer retrieves information and presented in the solution from legacy systems, production modelling workflows and SAP. The base plan & optimization cases are tracked by process health KPIs and approved using Business process management workflow. FSOPR automation system has been successfully piloted in one ADNOC Onshore assets. This automation was an enabler for better planning and scheduling of maintenance and RM activities and also provides assurance of monthly oil quota achievement by highlighting early potential threats that can hinder the realization of the FSOPR plan, thus corrective action can be taken on time considering best RM practices. The whole process of data gathering, planning, activity scheduling, optimization and approval has been reduced by 60% along with a more rigorous and errorless process. The added value besides enhancing efficiency, it has minimized well downtime and production deferment avoidance of 1-2%. This automation paved the path for FSOPR assurance process standardization across company portfolio of assets. The initiative is aligned with ADNOC digital transformation roadmap to leverage industry 4.0 technologies and digitalization of key upstream business processes in a consistent, integrated and uniform manner. This paper talks about transformation, FSOPR elements, low code solution & integration architecture, analytics, change adoption and benefits realization.
Digital oil fields have seen major advancements over the past ten years, with the goal of integrating and optimizing the loops of production operation, production optimization, well and reservoir surveillance based on real-time data and model-based workflow automation capabilities. This paper discusses how ADNOC onshore has successfully implemented model-based digital oil field workflows in all its producing fields and describes the process of migrating these workflows to a data-driven platform for improved decision making. In the existing workflows, data-driven diagnostic analytics are applied to validate well performance and accelerate the process of identifying underperforming wells and inefficiencies. These data-driven diagnostic analytics were implemented on a digital oilfield workflow platform where data is aggregated from disparate data sources consisting of non-real time well data, well events, well test history, MPFM, interpreted PTA, reservoir simulation, well integrity and wells tie-in data, along with continuous real-time sensor and model-generated data. The analytics are mapped with workflows and asset hierarchy. The linear regression method is used to forecast trends for water cut and GOR based on historical data. Diagnostic analytics have been successfully configured for a giant onshore field having more than a thousand wells and multiple reservoirs. The alarm diagnostic map is generated based on tolerance and difference with exceptions. The solution framework has a common data abstraction layer and integration. A built-in visualization engine allows customization based on user preferences, linking multiple screens and analytics. Well test validations are improved for non-instrumented wells by using diagnostic based on more than 10 years of well test history. Well level allocation analytics allow comparisons between real-time export meter and terminal figures at the same timestamp, based on well models. For model calibration, wellhead pressure estimation from the last valid model was introduced. Well surveillance and management diagnostic analyze wells which are operating on critical/sub-critical condition and increasing water cut based on models and measured data. The combination of reservoir simulation data, PTA, bottom-hole surveys and estimated data from well models provides insights to validate quality of simulation data and reduce uncertainty in well models. Compartment and reservoir-wise VRR diagnostic enable asset operators to take faster remedial actions for reservoir performance management. These analytics complemented traditional model-based automated workflows for identifying wells for optimization. A digital oilfield solution platform has been leveraged to implement diagnostic analytics in the first phase and to provide a road map to migrate it to next-generation data-driven platform that has more predictive capabilities. This paper discusses solutions and data integration frameworks, analytics visualization, integration with model-based workflows, value cases and the road map ahead.
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.