Leveraging Online Analytical Processing Cubes in the World's Largest Offshore and Land Drilling Record System
Abstract: The purpose of this paper is to demonstrate the power and business benefits of leveraging online analytical processing (OLAP) cubes in the utilization of high-level data analytics and data dashboards from an established drilling record system (DRS). The DRS contains over 1.4 million wells, including 75,000 offshore wells drilled worldwide since 1980 with nearly 5 million total bottomhole assembly (BHA) runs from over 100 countries. Since 2009, over 1.5 million BHA runs drilling 2.6 billion feet of formation ha… Show more
Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Cited by 4 publications
References 2 publications
How Drilling Fluids Affect Drilling Performance: Big Data Analysis
Cross-domain data analysis is arguably the most important part of oilfield data analytics. While it enables holistic process optimization, it is also challenging to execute. Data are often scattered across different databases making it complex to join and may require multidomain expertise to properly analyze. Here, processing and analysis of data collected by three well construction business lines of the same service company were performed to establish a link between drilling fluid properties and drilling performance. The data engineering workflow starts by taking information from a single service company and combining that information about drilling operations, drill bits, and drilling fluids into a single dataset. Metadata including locations, operators, and wells are then mapped, and overlapping attributes are unified and reconciled. Data is further processed to extract relevant drilling performance metrics and drilling fluid properties and then labeled by well, section, and drilling run. The resultant data workflow enables detailed analysis, focusing on particular locations, drilling practices, hole conditions, and fluids. The joined, cleaned, and processed dataset includes information from thousands of wells drilled globally since 2016. The datasets from different sources differ in the level of detail, but are complementary to each other, providing a broader picture when merged. The data is organized and visualized on dashboards, enabling in-depth analysis through intuitive filtering on a variety of conditions. These conditions may include location, drilling run type, depth, used drill bits and tools, and drilling fluid type and properties. The main drilling performance metrics are distance drilled per run and run duration. These are used to calculate the run average rate of penetration (ROP). Reasons for pulling out of the hole (POOH) and risks for POOH are extracted from text comments of the daily drilling reports. This enables the tracking of abnormal run terminations due to drilling tool failures. It also enables tracking of wellbore integrity, and substandard drilling and hole conditioning practices, especially at section total depth (TD) or because of drilling fluid issues. Aggregated metrics of minimum, maximum, and median are used for high-level data evaluation. Statistical significance of effects and causality are analyzed in detail on selected cases. Based on the data, several examples of such analyses are created that focus on the effects of water-based fluid vs. oil-based fluid, on drilling performance in the major oil fields in the United States. Holistic analysis of the effects of drilling fluids on drilling performance becomes possible through the well construction cross-domain data fusion. The developed workflow enables analysis of drilling fluid-related big data, covering tens of thousands of wells globally. The analysis results are expected to improve drilling efficiency and reliability and ultimately reduce operators' total well expenditures.
How Drilling Fluids Affect Drilling Performance: Big Data Analysis
Cross-domain data analysis is arguably the most important part of oilfield data analytics. While it enables holistic process optimization, it is also challenging to execute. Data are often scattered across different databases making it complex to join and may require multidomain expertise to properly analyze. Here, processing and analysis of data collected by three well construction business lines of the same service company were performed to establish a link between drilling fluid properties and drilling performance. The data engineering workflow starts by taking information from a single service company and combining that information about drilling operations, drill bits, and drilling fluids into a single dataset. Metadata including locations, operators, and wells are then mapped, and overlapping attributes are unified and reconciled. Data is further processed to extract relevant drilling performance metrics and drilling fluid properties and then labeled by well, section, and drilling run. The resultant data workflow enables detailed analysis, focusing on particular locations, drilling practices, hole conditions, and fluids. The joined, cleaned, and processed dataset includes information from thousands of wells drilled globally since 2016. The datasets from different sources differ in the level of detail, but are complementary to each other, providing a broader picture when merged. The data is organized and visualized on dashboards, enabling in-depth analysis through intuitive filtering on a variety of conditions. These conditions may include location, drilling run type, depth, used drill bits and tools, and drilling fluid type and properties. The main drilling performance metrics are distance drilled per run and run duration. These are used to calculate the run average rate of penetration (ROP). Reasons for pulling out of the hole (POOH) and risks for POOH are extracted from text comments of the daily drilling reports. This enables the tracking of abnormal run terminations due to drilling tool failures. It also enables tracking of wellbore integrity, and substandard drilling and hole conditioning practices, especially at section total depth (TD) or because of drilling fluid issues. Aggregated metrics of minimum, maximum, and median are used for high-level data evaluation. Statistical significance of effects and causality are analyzed in detail on selected cases. Based on the data, several examples of such analyses are created that focus on the effects of water-based fluid vs. oil-based fluid, on drilling performance in the major oil fields in the United States. Holistic analysis of the effects of drilling fluids on drilling performance becomes possible through the well construction cross-domain data fusion. The developed workflow enables analysis of drilling fluid-related big data, covering tens of thousands of wells globally. The analysis results are expected to improve drilling efficiency and reliability and ultimately reduce operators' total well expenditures.
Automated Offsets for Drill Bit Performance Evaluation, Analysis, and Monitoring At-Scale
Utilizing big drilling data requires an innovative approach. The service company’s drill bits business is largely based upon an in-house drilling record system (DRS) that captures global bit record performance data. The DRS contains over 1.8 million wells drilled worldwide since 1980 with nearly 5.4 million total BHA runs from over 100 countries. In the last 10 years alone, over 1.4 million bit runs drilling over 2.8 billion ft of formation have been recorded. To utilize this vast amount of data for drill bit performance evaluation, analysis, and monitoring, the innovative approach described in this paper was developed and implemented. Traditionally, the performance of a drill bit run–often measured in terms of drilled footage and ROP–has been evaluated versus similar offset runs. Offset runs are chosen in various ways, but are typically done manually by bit engineers, meaning that offset run selection is subjective based on personal experience and bias. Furthermore, people often only evaluate the performance of test bit designs. Instead, we wanted to analyze and monitor the performance of all drill bit runs. To alleviate these biases and enable a wider breadth of considered runs, an objective offset run selection workflow was developed and implemented within DRS. Offset runs are selected based on a sophisticated filtering and scoring routine that considers many characteristics such as geographic location, time, wellbore and drilling system design, along with lithology. As new data enters DRS continuously, this workflow runs on a regular basis using an automated pipeline. The performance evaluation results of the automated offset selection workflow are available to all data analysts (engineers and salespeople) both inside DRS and extensible applications to aid in performance monitoring and new product development target-setting. Product performance is now objectively evaluated at-scale across geographies and always utilizing apples-to-apples comparisons. The workflow has proven itself quite useful and delivered business value already but also exemplifies the need for both enhanced data quality and improved bit record data capture rate. These are ongoing efforts to further enhance and improve this workflow. Automated workflows like this one can help our industry by eliminating repetitive biased tasks and allowing people to focus on more creative processes leveraging objective data. Developing new drill bit designs, material selections, or component selections to overcome new challenges are creative processes which contribute to increased drilling performance and lower costs for the industry.
Machine Learning-Based Drilling System Recommender: Towards Optimal BHA and Fluid Technology Selection
The energy industry is undergoing a digital transformation, whose goals include increased operational efficiency and reduced energy extraction costs. Data science and machine learning (ML) are enabling the drilling engineering community to contribute to the success of these goals. An ML-based digital solution has been developed to assist the drilling engineer select an optimum bottomhole assembly (BHA) and drilling fluid technology during the well design phase. Traditionally, these selections depended on offset well analysis, which is a manual and time-consuming undertaking. As an alternative, the new digital solution, launched in the form of a web app, automatically selects similar offset wells, and evaluates the available BHA and drilling fluid options from those similar wells. The web app displays these options to the drilling engineer, who is now empowered to make fully informed data-driven decisions. To power the new digital solution, an extensive effort was made to gather, clean, and prepare global operational data into a new database. This operational database includes the selection decisions and performance results of drill bits, motor power sections, rotary steerable systems, BHA configurations, and drilling fluids. After the drilling engineer defines the parameters of the planned drilling run, a multidimensional distance-based approach is used to automatically select the most similar previous drilling runs within the context of the technology selection. The drilling engineer can also fine tune the offset selection based on experience using filters in the web app. Once the most similar offset runs are determined, the technology selection decisions are scored for numerous key performance indicators (KPIs). These KPIs, along with user-defined weights, drive the overall scores. Finally, technology selection recommendations are based on the overall scores and other contextual data such as local availability and cost. The new digital solution has been deployed to a global group of drilling engineers. Feedback sessions are held regularly, and the development team uses this feedback to rapidly iterate and improve user experience. While today's drilling engineers have access to a vast amount of data and information, it often cannot be used in a practical and efficient way. The new solution places all previous drilling system technology selection choices and results into the hands of the drilling engineers, allowing them to make their best decisions. This approach demonstrates how ML and innovative software deployment methods can truly assist the human decision-making process and succeed in accomplishing the goals of digital transformation. To our knowledge, this is a unique approach to drilling system design optimization. Not only is the approach unique, but the database developed as a portion of this effort is likely the largest drilling operations database within the industry. This paper presents all phases of the project, including the details of database creation, data preparation, development of the ML models, and the creation and iteration of the user interface. Finally, this paper presents the future of this effort as part of the company's vision to be our customers’ performance partner of choice.
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.
Contact Info
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Product
Resources
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.
