Application of machine learning and artificial intelligence in oil and gas industry

Abstract Corrosion under insulation (CUI) is a critical challenge that affects the integrity of assets where the oil and gas industry is not immune. Its severity arises due to its hidden nature as it can often times go unnoticed. CUI is stimulated, in principle, by moisture ingress through the insulation layers to the surface of the pipeline. This Artificial Intelligence (AI)-powered detection technology stemmed from an urgent need to detect the presence of these corrosion types. The new approach is based on a Cyber Physical (CP) system that maximizes the potential of thermographic imaging by using a Machine Learning application of Artificial Intelligence. In this work, we describe how common image processing techniques from infra-red images of assets can be enhanced using a machine learning approach allowing the detection of locations highly vulnerable to corrosion through pinpointing locations of CUI anomalies and areas of concern. The machine learning is examining the progression of thermal images, captured over time, corrosion and factors that cause this degradation are predicted by extracting thermal anomaly features and correlating them with corrosion and irregularities in the structural integrity of assets verified visually during the initial learning phase of the ML algorithm. The ML classifier has shown outstanding results in predicting CUI anomalies with a predictive accuracy in the range of 85 – 90% projected from 185 real field assets. Also, IR imaging by itself is subjective and operator dependent, however with this cyber physical transfer learning approach, such dependency has been eliminated. The results and conclusions of this work on real field assets in operation demonstrate the feasibility of this technique to predict and detect thermal anomalies directly correlated to CUI. This innovative work has led to the development of a cyber-physical that meets the demands of inspection units across the oil and gas industry, providing a real-time system and online assessment tool to monitor the presence of CUI enhancing the output from thermography technologies, using Artificial Intelligence (AI) and machine learning technology. Additional benefits of this approach include safety enhancement through non-contact online inspection and cost savings by reducing the associated scaffolding and downtime.

Download Full-text

Guest Editorial: Artificial Intelligence in the E&P Industry: What Have We Learned So Far and Where to Next?

Journal of Petroleum Technology ◽

10.2118/0121-0012-jpt ◽

2021 ◽

Vol 73 (01) ◽

pp. 12-13

Author(s):

Manas Pathak ◽

Tonya Cosby ◽

Robert K. Perrons

Keyword(s):

Artificial Intelligence ◽

Science Fiction ◽

Oil Recovery ◽

Oil And Gas ◽

Autonomous Systems ◽

Oil And Gas Industry ◽

Human Judgment ◽

Gas Industry ◽

The Media ◽

And Function

Artificial intelligence (AI) has captivated the imagination of science-fiction movie audiences for many years and has been used in the upstream oil and gas industry for more than a decade (Mohaghegh 2005, 2011). But few industries evolve more quickly than those from Silicon Valley, and it accordingly follows that the technology has grown and changed considerably since this discussion began. The oil and gas industry, therefore, is at a point where it would be prudent to take stock of what has been achieved with AI in the sector, to provide a sober assessment of what has delivered value and what has not among the myriad implementations made so far, and to figure out how best to leverage this technology in the future in light of these learnings. When one looks at the long arc of AI in the oil and gas industry, a few important truths emerge. First among these is the fact that not all AI is the same. There is a spectrum of technological sophistication. Hollywood and the media have always been fascinated by the idea of artificial superintelligence and general intelligence systems capable of mimicking the actions and behaviors of real people. Those kinds of systems would have the ability to learn, perceive, understand, and function in human-like ways (Joshi 2019). As alluring as these types of AI are, however, they bear little resemblance to what actually has been delivered to the upstream industry. Instead, we mostly have seen much less ambitious “narrow AI” applications that very capably handle a specific task, such as quickly digesting thousands of pages of historical reports (Kimbleton and Matson 2018), detecting potential failures in progressive cavity pumps (Jacobs 2018), predicting oil and gas exports (Windarto et al. 2017), offering improvements for reservoir models (Mohaghegh 2011), or estimating oil-recovery factors (Mahmoud et al. 2019). But let’s face it: As impressive and commendable as these applications have been, they fall far short of the ambitious vision of highly autonomous systems that are capable of thinking about things outside of the narrow range of tasks explicitly handed to them. What is more, many of these narrow AI applications have tended to be modified versions of fairly generic solutions that were originally designed for other industries and that were then usefully extended to the oil and gas industry with a modest amount of tailoring. In other words, relatively little AI has been occurring in a way that had the oil and gas sector in mind from the outset. The second important truth is that human judgment still matters. What some technology vendors have referred to as “augmented intelligence” (Kimbleton and Matson 2018), whereby AI supplements human judgment rather than sup-plants it, is not merely an alternative way of approaching AI; rather, it is coming into focus that this is probably the most sensible way forward for this technology.

Download Full-text

Artificial Intelligence and Robotics in the Oil Industry: Will it Take My Job?

10.2118/204643-ms ◽

2021 ◽

Author(s):

Armstrong Lee Agbaji

Keyword(s):

Artificial Intelligence ◽

Oil And Gas ◽

New Technologies ◽

Oil Industry ◽

Oil And Gas Industry ◽

Human Robot Interaction ◽

Gas Industry ◽

Deep Dive ◽

The Future ◽

And Robotics

Abstract Historically, the oil and gas industry has been slow and extremely cautious to adopt emerging technologies. But in the Age of Artificial Intelligence (AI), the industry has broken from tradition. It has not only embraced AI; it is leading the pack. AI has not only changed what it now means to work in the oil industry, it has changed how companies create, capture, and deliver value. Thanks, or no thanks to automation, traditional oil industry skills and talents are now being threatened, and in most cases, rendered obsolete. Oil and gas industry day-to-day work is progressively gravitating towards software and algorithms, and today’s workers are resigning themselves to the fact that computers and robots will one day "take over" and do much of their work. The adoption of AI and how it might affect career prospects is currently causing a lot of anxiety among industry professionals. This paper details how artificial intelligence, automation, and robotics has redefined what it now means to work in the oil industry, as well as the new challenges and responsibilities that the AI revolution presents. It takes a deep-dive into human-robot interaction, and underscores what AI can, and cannot do. It also identifies several traditional oilfield positions that have become endangered by automation, addresses the premonitions of professionals in these endangered roles, and lays out a roadmap on how to survive and thrive in a digitally transformed world. The future of work is evolving, and new technologies are changing how talent is acquired, developed, and retained. That robots will someday "take our jobs" is not an impossible possibility. It is more of a reality than an exaggeration. Automation in the oil industry has achieved outcomes that go beyond human capabilities. In fact, the odds are overwhelming that AI that functions at a comparable level to humans will soon become ubiquitous in the industry. The big question is: How long will it take? The oil industry of the future will not need large office complexes or a large workforce. Most of the work will be automated. Drilling rigs, production platforms, refineries, and petrochemical plants will not go away, but how work is done at these locations will be totally different. While the industry will never entirely lose its human touch, AI will be the foundation of the workforce of the future. How we react to the AI revolution today will shape the industry for generations to come. What should we do when AI changes our job functions and workforce? Should we be training AI, or should we be training humans?

Download Full-text

Machine Learning and Data Science in the Oil and Gas Industry

10.1016/c2019-0-02033-x ◽

2021 ◽

Keyword(s):

Machine Learning ◽

Data Science ◽

Oil And Gas ◽

Oil And Gas Industry ◽

Gas Industry

Download Full-text

Evaluation of Machine-Learning Tools for Predicting Sand Production

10.2118/207193-ms ◽

2021 ◽

Author(s):

Afungchwi Ronald Ngwashi ◽

David O. Ogbe ◽

Dickson O. Udebhulu

Keyword(s):

Machine Learning ◽

Niger Delta ◽

Oil And Gas ◽

Back Propagation ◽

Oil And Gas Industry ◽

Learning Tools ◽

Sand Production ◽

Data Set ◽

Test Set ◽

Gas Industry

Abstract Data analytics has only recently picked the interest of the oil and gas industry as it has made data visualization much simpler, faster, and cost-effective. This is driven by the promising innovative techniques in developing artificial intelligence and machine-learning tools to provide sustainable solutions to ever-increasing problems of the petroleum industry activities. Sand production is one of these real issues faced by the oil and gas industry. Understanding whether a well will produce sand or not is the foundation of every completion job in sandstone formations. The Niger Delta Province is a region characterized by friable and unconsolidated sandstones, therefore it's more prone to sanding. It is economically unattractive in this region to design sand equipment for a well that will not produce sand. This paper is aimed at developing a fast and more accurate machine-learning algorithm to predict sanding in sandstone formations. A two-layered Artificial Neural Network (ANN) with back-propagation algorithm was developed using PYTHON programming language. The algorithm uses 11 geological and reservoir parameters that are associated with the onset of sanding. These parameters include depth, overburden, pore pressure, maximum and minimum horizontal stresses, well azimuth, well inclination, Poisson's ratio, Young's Modulus, friction angle, and shale content. Data typical of the Niger Delta were collected to validate the algorithm. The data was further split into a training set (70%) and a test set (30%). Statistical analyses of the data yielded correlations between the parameters and were plotted for better visualization. The accuracy of the ANN algorithm is found to depend on the number of parameters, number of epochs, and the size of the data set. For a completion engineer, the answer to the question of whether or not a well will require sand production control is binary-either a well will produce sand or it does not. Support vector machines (SVM) are known to be better suited as the machine-learning tools for binary identification. This study also presents a comparative analysis between ANN and SVM models as tools for predicting sand production. Analysis of the Niger Delta data set indicated that SVM outperformed ANN model even when the training data set is sparse. Using the 30% test set, ANN gives an accuracy, precision, recall, and F1 - Score of about 80% while the SVM performance was 100% for the four metrics. It is then concluded that machine learning tools such as ANN with back-propagation and SVM are simple, accurate, and easy-to-use tools for effectively predicting sand production.

Download Full-text

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

Fluids ◽

10.3390/fluids4010044 ◽

2019 ◽

Vol 4 (1) ◽

pp. 44 ◽

Cited By ~ 5

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.

Download Full-text

Electrical Submersible Pump Prognostics and Health Monitoring Using Machine Learning and Natural Language Processing

10.2118/208649-ms ◽

2021 ◽

Author(s):

Rajeev Ranjan Sinha ◽

Supriya Gupta ◽

Praprut Songchitruksa ◽

Saniya Karnik ◽

Amey Ambade

Keyword(s):

Machine Learning ◽

Language Processing ◽

Oil And Gas ◽

Oil And Gas Industry ◽

Operating Conditions ◽

Learning Approaches ◽

Submersible Pump ◽

Gas Industry ◽

Electrical Submersible Pump ◽

Low Efficiency

Abstract Electrical Submersible Pump (ESP) systems efficiently pump high volumes of production fluids from the wellbore to the surface. They are extensively used in the oil and gas industry due to their adaptability, low maintenance, safety and relatively low environmental impact. They require specific operating conditions with respect to the power, fluid level and fluid content. Oilfield operation workflows often require extensive surveillance and monitoring by subject-matter experts (SMEs). Detecting issues like formation of unwanted gas and emulsions in ESPs requires constant analysis of downhole data by SMEs. The lack of adequate and accurate monitoring of the downhole pumps can lead to low efficiency, high lifting costs, and frequent repair and replacements. There are 3 workflows described in the paper which demonstrate that the maintenance costs of the ESPs can be significantly reduced, and production optimized with the augmentation of machine learning approaches typically unused in ESP surveillance and failure analysis.

Download Full-text

Machine Learning as Accelerating Tool in Remote Operation Realisation through Monitoring Oil and Gas Equipments and Identifying its Failure Mode

10.2523/iptc-21493-ms ◽

2021 ◽

Author(s):

Ahmad Naufal Naufal ◽

Samy Abdelhamid Samy ◽

Nenisurya Hashim Nenisurya ◽

Zaharuddin Muhammad Zaharuddin ◽

Eddy Damsuri Eddy ◽

...

Keyword(s):

Machine Learning ◽

Failure Mode ◽

Oil And Gas ◽

Oil And Gas Industry ◽

Support Vector ◽

Environmental Damage ◽

Equipment Failure ◽

Statistical Regression ◽

Gas Industry ◽

Plant Equipment

Abstract Equipment failure, unplanned downtime operation, and environmental damage cost represent critical challenges in overall oil and gas business from well reservoir identification and drilling strategy to production and processing. Identifying and managing the risks around assets that could fail and cause redundant and expensive downtime are the core of plant reliability in oil and gas industry. In the current digital era; there is an essential need of innovative data-driven solutions to address these challenges, especially, monitoring and diagnosis of plant equipment operations, recognize equipment failure; avoid unplanned downtime; repair costs and potential environmental damage; maintaining reliable production, and identifying equipment failures. Machine learning-artificial intelligence application is being studied to develop predictive maintenance (PdM) models as innovative analytics solution based on real-data streaming to get to an elevated level of situational intelligence to guide actions and provide early warnings of impending asset failure that previously remained undetected. This paper proposes novel machine learning predictive models based on extreme learning/support vector machines (ELM-SVM) to predict the time to failure (TTF) and when a plant equipment(s) will fail; so maintenance can be planned well ahead of time to minimize disruption. Proper visualization with deep-insights (training and validation) processes of the available mountains of historian and real-time data are carried out. Comparative studies of ELM-SVM techniques versus the most common physical-statistical regression techniques using available rotating equipment-compressors and time-failure mode data. Results are presented and it is promising to show that the new machine learning (ELM-SVM) techniques outperforms physical-statistics techniques with reliable and high accurate predictions; which have a high impact on the future ROI of oil and gas industry.

Download Full-text