A Workflow for Intelligent Data-driven Analytics Software Development in Oil and Gas Industry

2014 ◽  
Author(s):  
Serkan Dursun ◽  
Kaan Duman ◽  
Tayfun Tuna ◽  
Mamta Abbas ◽  
James Ding
Keyword(s):  
Software Development ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Data Driven ◽  
Gas Industry

Status of Data-Driven Methods and their Applications in Oil and Gas Industry

2018 ◽  
Author(s):  
Karthik Balaji ◽  
Minou Rabiei ◽  
Vural Suicmez ◽  
Celal Hakan Canbaz ◽  
Zinyat Agharzeyva ◽  
...  
Keyword(s):  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Data Driven ◽  
Gas Industry

scholarly journals Predicting the Dynamic Parameters of Multiphase Flow in CFD (Dam-Break Simulation) Using Artificial Intelligence-(Cascading Deployment)

Fluids ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 44 ◽  
Author(s):  
S. Hosseini Boosari
Keyword(s):  
Artificial Intelligence ◽  
Numerical Simulation ◽  
Multiphase Flow ◽  
Fast Track ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Dam Break ◽  
Data Driven ◽  
Time Step ◽  
Gas Industry

Multiphase flow of oil, gas, and water occurs in a reservoir’s underground formation and also within the associated downstream pipeline and structures. Computer simulations of such phenomena are essential in order to achieve the behavior of parameters including but not limited to evolution of phase fractions, temperature, velocity, pressure, and flow regimes. However, within the oil and gas industry, due to the highly complex nature of such phenomena seen in unconventional assets, an accurate and fast calculation of the aforementioned parameters has not been successful using numerical simulation techniques, i.e., computational fluid dynamic (CFD). In this study, a fast-track data-driven method based on artificial intelligence (AI) is designed, applied, and investigated in one of the most well-known multiphase flow problems. This problem is a two-dimensional dam-break that consists of a rectangular tank with the fluid column at the left side of the tank behind the gate. Initially, the gate is opened, which leads to the collapse of the column of fluid and generates a complex flow structure, including water and captured bubbles. The necessary data were obtained from the experience and partially used in our fast-track data-driven model. We built our models using Levenberg Marquardt algorithm in a feed-forward back propagation technique. We combined our model with stochastic optimization in a way that it decreased the absolute error accumulated in following time-steps compared to numerical computation. First, we observed that our models predicted the dynamic behavior of multiphase flow at each time-step with higher speed, and hence lowered the run time when compared to the CFD numerical simulation. To be exact, the computations of our models were more than one hundred times faster than the CFD model, an order of 8 h to minutes using our models. Second, the accuracy of our predictions was within the limit of 10% in cascading condition compared to the numerical simulation. This was acceptable considering its application in underground formations with highly complex fluid flow phenomena. Our models help all engineering aspects of the oil and gas industry from drilling and well design to the future prediction of an efficient production.

scholarly journals The data-driving management in oil and gas industry: examples and opportunities

2021 ◽  
Vol 6 (4) ◽  
pp. 137-146
Author(s):  
Andrey S. Bochkov ◽  
Mariia G. Dymochkina
Keyword(s):  
Decision Making ◽  
Best Practices ◽  
Business Processes ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Data Driven ◽  
Management Approach ◽  
Gas Industry ◽  
Data Driven Approach ◽  
Using Data

Background. Decision-making process in the oil and gas industry, traditionally extremely expensive, should be based on the point of maximizing the business value. Forecasting the effectiveness of investments of any business unit in oil and gas should be based on a data-driven management approach. The purpose of this article — to study methods and best practices of applying a data — driven approach to decision-making and analyze the possibility of scaling methods of best practices in the processes in oil and gas company. Materials and methods. Research a various case with data-driven management shows that using data-driven approach allows solving several tasks at once: to make a fast and quality decisions based on data that can always be checked, and the result can be analyzed; to reduce the costs by eliminating inefficient steps and increase the flexibility of the process; to form the correct attitude to data (data culture) and prepare for the implementation of the technologies of Industry 4.0. Analyze cases revealed two common and important things: engineering of business processes from the key performance indicators and the technological development. Results. In article discusses the topic of applying a data-driven decision-making approach in oil and gas companies using several examples of Gazprom Neft. These examples shows that better effect from the using of data-driven management is achieved by consistently modeling business processes for achieving maximum values; highlighting and fixing key business performance indicators and creating a digital monitoring of these indicators, which allows you to the achievement of goals. Conclusions. In the conclusion of the article there are recommendation about using data-driven management approach for various processes of an oil and gas company.

Applications of AI and Data-Driven Modeling in Energy Production and Marketing Processes

2021 ◽  
Author(s):  
Joy Ugoyah ◽  
Anita Mary Igbine
Keyword(s):  
Artificial Intelligence ◽  
Oil And Gas ◽  
Health And Safety ◽  
Oil And Gas Industry ◽  
Data Driven ◽  
Gas Industry ◽  
Energy Needs ◽  
Safety Risks ◽  
Data Driven Modeling ◽  
Applications Of Ai

Abstract Faster and more accurate decisions are what the Oil and Gas industry needs with the world's fast-evolving energy needs and economy. The area of Artificial intelligence and Data-driven modelling is relatively new and has not found popular application in the industry. AI is an emerging technology that can be used to predict event outcomes and automate anomaly-detection processes. The various applications of AI in different industries were researched into. This paper highlighted important processes that can be improved with the application of Artificial Intelligence through data-driven modelling. It also highlights areas in the various industries where AI intelligence is already being applied and ways it can be improved. AI and data-driven modelling has the potential to improve exploration accuracy, reduce production down-time, reduce cost of maintenance, and reduce health and safety risks. This body of information can serve as a guideline for adopting AI in the oil and gas industry. A trend of industry-tailored intelligence solutions would be more effective in the evolving energy industry.

Data-Driven PHM Solution for Health Monitoring of Mud Motor Power Sections While Drilling

2021 ◽  
Author(s):  
Dmitry Belov ◽  
Samba BA ◽  
Ji Tang Liu ◽  
Anton Kolyshkin ◽  
Sergio Daniel Rocchio
Keyword(s):  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Data Driven ◽  
Maintenance Cost ◽  
High Fidelity ◽  
Great Success ◽  
Motor Power ◽  
Gas Industry

Abstract Mud motors are widely used for directional and performance drilling. Due to the extremely challenging operating conditions, they are prone to failures, resulting in unnecessary maintenance repair costs as well as unpredictable and very costly drilling failure. Until now, the oil and gas industry has lacked reliable procedures to monitor and maintain the health of the mud motor power sections. Recently, we systematically addressed this problem with an industry unique prognostic health management solution, which not only tracks remaining useful life (RUL), but also creates a new failure prevention scheme for operators. The key objective of this solution is to reduce maintenance costs and improve mud motor fleet reliability. It's based on a high-fidelity model and uses a hybrid approach by combining a high-fidelity physics-based model of a power section and data-driven approaches with machine learning techniques for real-time applications. The new methodology was tested in the field with great success. The verification of the created solution was completed based on numerous field data from Saudi Arabia and Argentina. Comparison of the predicted mud motor fatigue values with the actual observed post-job conditions and job failures demonstrated high fidelity of the developed models. The whole solution is currently being integrated into a drilling platform including the maintenance system, the well construction planning, and the execution. The first application of the workflow was deployed in the field in Colombia targeting reduction of maintenance cost and failure avoidance. The result was outstanding, with the initial deployment bringing about 27% of projected yearly maintenance savings and 10% of projected yearly failure reduction. It enables using the equipment to the full extent with increased drilling performance without sacrificing reliability. In addition, it optimizes the entire fleet management with reduced cost of logistics and maintenance. The findings of this paper demonstrate the value of the mud motor PHM solution for the oil and gas industry by providing accurate prognosis of power section health, leading to reduced costs, minimized NPT, and increased operational reliability.

Data-driven failure analysis of emergency shutdown systems in oil and gas industry

2019 ◽  
Vol 26 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Pengyu Zhu ◽  
Jayantha Liyanage ◽  
Simon Jeeves
Keyword(s):  
Failure Analysis ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Data Driven ◽  
Gas Industry ◽  
Content Type ◽  
Analysis Process ◽  
Emergency Shutdown ◽  
Data Driven Approach ◽  
Logical Data

Purpose Emergency shutdown (ESD) systems play a critical role in ensuring safety and availability of oil and gas production. The systems are operated in on-demand mode, and the detection and prediction of their failures is deemed challenging. The purpose of this paper is to develop a logical data-driven approach to enhance the understanding and detectability of ESD system failures. Design/methodology/approach The study was conducted in close collaboration with the Norwegian oil and gas industry. The study and analyses were supported by industrial data, failure data generated in a test facility in Norway and domain experts. Findings The paper demonstrated that there is a considerable potential to improve the decision process and to reduce the workload related to ESD systems by means of a logical data-driven approach. The results showed that the failure analysis process can be executed with more clarity and efficiency. Common cause failures could also be identified based on the suggested approach. The study further underlined the requirements regarding relevant data, new competence and technical supports in order to improve the current practice. Originality/value The paper leveraged the value of real-time data in identifying failures through mapping of the interrelationships between data, failure mechanisms and decisions. The failure analysis process was re-designed, and the understanding and decision making related to the system was improved as a result. The process developed for ESDs can further be adapted as a common practice for other low-demand systems.

Sign in / Sign up

Export Citation Format

Share Document