Application of machine learning and artificial intelligence in oil and gas industry
TL;DR: This paper provides a comprehensive state-of-art review in the field of machine learning and artificial intelligence to solve oil and gas industry problems and narrates the various types of machine teaching techniques which can be used for data processing and interpretation in different sectors of upstream oil andgas industries.
About: This article is published in Petroleum Research.The article was published on 2021-06-04 and is currently open access. It has received 102 citations till now. The article focuses on the topics: Upstream (petroleum industry) & Applications of artificial intelligence.
Citations
More filters
21 citations
TL;DR: Research is presented at developing an indirect method for determining the formation pressure without shutting down the wells for investigation, which enables to determine its value at any time.
Abstract: Determining formation pressure in the well extraction zones is a key task in monitoring the development of hydrocarbon fields. Direct measurements of formation pressure require prolonged well shutdowns, resulting in underproduction and the possibility of technical problems with the subsequent start-up of wells. The impossibility of simultaneous shutdown of all wells of the pool makes it difficult to assess the real energy state of the deposit. This article presents research aimed at developing an indirect method for determining the formation pressure without shutting down the wells for investigation, which enables to determine its value at any time. As a mathematical basis, two artificial intelligence methods are used – multidimensional regression analysis and a neural network. The technique based on the construction of multiple regression equations shows sufficient performance, but high sensitivity to the input data. This technique enables to study the process of formation pressure establishment during different periods of deposit development. Its application is expedient in case of regular actual determinations of indicators used as input data. The technique based on the artificial neural network enables to reliably determine formation pressure even with a minimal set of input data and is implemented as a specially designed software product. The relevant task of continuing the research is to evaluate promising prognostic features of artificial intelligence methods for assessing the energy state of deposits in hydrocarbon extraction zones.
18 citations
TL;DR: In this article, the benefits and challenges of the adoption of industry 4.0 technologies in the O&G upstream sector have been investigated and a framework for the implementation of I4.0 in the upstream sector has been proposed.
Abstract: The market volatility in the oil and gas (O&G) sector, the dwindling demand for oil due to the impact of COVID-19, and the push for alternative greener energy are driving the need for innovation and digitization in the O&G industry. This has attracted research interest from academia and the industry in the application of industry 4.0 (I4.0) technologies in the O&G sector. The application of some of these I4.0 technologies has been presented in the literature, but the domain still lacks a comprehensive survey of the application of I4.0 in the O&G upstream sector. This paper investigates the state-of-the-art efforts directed toward I4.0 technologies in the O&G upstream sector. To achieve this, first, an overview of the I4.0 is discussed followed by a systematic literature review from an integrative perspective for publications between 2012–2021 with 223 analyzed documents. The benefits and challenges of the adoption of I4.0 have been identified. Moreover, the paper adds value by proposing a framework for the implementation of I4.0 in the O&G upstream sector. Finally, future directions and research opportunities such as framework, edge computing, quantum computing, communication technologies, standardization, and innovative areas related to the implementation of I4.0 in the upstream sector are presented. The findings from this review show that I4.0 technologies are currently being explored and deployed for various aspects of the upstream sector. However, some of the I4.0 technologies like additive manufacturing and virtual reality are least explored.
17 citations
11 citations
TL;DR: In this paper , a data-driven approach to enhance the accuracy of petrophysical rock typing via a combination of supervised and unsupervised machine learning methods was proposed, where the authors used a modified formation zone index (FZIM*) to accurately estimate permeability.
Abstract: Petrophysical rock typing (PRT) and permeability prediction are of great significance for various disciplines of oil and gas industry. This study offers a novel, explainable data-driven approach to enhance the accuracy of petrophysical rock typing via a combination of supervised and unsupervised machine learning methods. 128 core data, including porosity, permeability, connate water saturation (Swc), and radius of pore throats at 35% mercury injection (R35) were obtained from a heterogeneous carbonate reservoir in Iran and used to train a supervised machine learning algorithm called Extreme Gradient Boosting (XGB). The algorithm output was a modified formation zone index (FZIM*), which was used to accurately estimate permeability (R2 = 0.97) and R35 (R2 = 0.95). Moreover, FZIM* was combined with an unsupervised machine learning algorithm (K-means clustering) to find the optimum number of PRTs. 4 petrophysical rock types (PRTs) were identified via this method, and the range of their properties was discussed. Lastly, shapely values and parameter importance analysis were conducted to explain the correlation between each input parameter and the output and the contribution of each parameter on the value of FZIM*. Permeability and R35 were found to be most influential parameters, where Swc had the lowest impact on FZIM*.
10 citations
References
More filters
309 citations
01 Jan 2016
TL;DR: This chapter provides an application oriented view towards concept drift research, with a focus on supervised learning tasks, and constructs a reference framework for positioning application tasks within a spectrum of problems related to concept drift.
Abstract: In most challenging data analysis applications, data evolve over time and must be analyzed in near real time. Patterns and relations in such data often evolve over time, thus, models built for analyzing such data quickly become obsolete over time. In machine learning and data mining this phenomenon is referred to as concept drift. The objective is to deploy models that would diagnose themselves and adapt to changing data over time. This chapter provides an application oriented view towards concept drift research, with a focus on supervised learning tasks. First we overview and categorize application tasks for which the problem of concept drift is particularly relevant. Then we construct a reference framework for positioning application tasks within a spectrum of problems related to concept drift. Finally, we discuss some promising research directions from the application perspective, and present recommendations for application driven concept drift research and development.
274 citations
TL;DR: In this article, the authors applied the Bayesian Network (BN) to conduct a dynamic safety analysis of deepwater Managed Pressure Drilling Operations (MPD) and Underbalanced Drilling (UBD) operations.
Abstract: Deepwater drilling is one of the high-risk operations in the oil and gas sector due to large uncertainties and extreme operating conditions. In the last few decades Managed Pressure Drilling Operations (MPD) and Underbalanced Drilling (UBD) have become increasingly used as alternatives to conventional drilling operations such as Overbalanced Drilling (OVD) technology. These newer techniques provide several advantages however the blowout risk during these operations is still not fully understood. Blowout is regarded as one of the most catastrophic events in offshore drilling operations; therefore implementation and maintenance of safety measures is essential to maintain risk below the acceptance criteria. This study is aimed at applying the Bayesian Network (BN) to conduct a dynamic safety analysis of deepwater MPD and UBD operations. It investigates different risk factors associated with MPD and UBD technologies, which could lead to a blowout accident. Blowout accident scenarios are investigated and the BNs are developed for MPD and UBD technologies in order to predict the probability of blowout occurrence. The main objective of this paper is to understand MPD and UBD technologies, to identify hazardous events during MPD and UBD operations, to perform failure analysis (modelling) of blowout events and to evaluate plus compare risk. Importance factor analysis in drilling operations is performed to assess contribution of each root cause to the potential accident; the results show that UBD has a higher occurrence probability of kick and blowout compared to MPD technology. The Rotating Control Devices (RCD) failure in MPD technology and increase in flow-through annulus in UBD technology are the most critical situations for kick and blowout.
164 citations
TL;DR: This paper first presents the relevant theories and core technologies of the blockchain, and then describes how the blockchain is applied to the oil and gas industry from four aspects: trading, management and decision making, supervision, and cyber security.
Abstract: Blockchain technology has been developed for more than ten years and has become a trend in various industries As the oil and gas industry is gradually shifting toward intelligence and digitalization, many large oil and gas companies were working on blockchain technology in the past two years because of it can significantly improve the management level, efficiency, and data security of the oil and gas industry This paper aims to let more people in the oil and gas industry understand the blockchain and lead more thinking about how to apply the blockchain technology To the best of our knowledge, this is one of the earliest papers on the review of the blockchain system in the oil and gas industry This paper first presents the relevant theories and core technologies of the blockchain, and then describes how the blockchain is applied to the oil and gas industry from four aspects: trading, management and decision making, supervision, and cyber security Finally, the application status, the understanding level of the blockchain in the oil and gas industry, opportunities, challenges, and risks and development trends are analyzed The main conclusions are as follows: 1) at present, Europe and Asia have the fastest pace of developing the application of blockchain in the oil and gas industry, but there are still few oil and gas blockchain projects in operation or testing worldwide; 2) nowadays, the understanding of blockchain in the oil and gas industry is not sufficiently enough, the application is still in the experimental stage, and the investment is not enough; and (3) blockchain can bring many opportunities to the oil and gas industry, such as reducing transaction costs and improving transparency and efficiency However, since it is still in the early stage of the application, there are still many challenges, primarily technological, and regulatory and system transformation The development of blockchains in the oil and gas industry will move toward hybrid blockchain architecture, multi-technology combination, cross-chain, hybrid consensus mechanisms, and more interdisciplinary professionals
158 citations
TL;DR: In this article, two models are presented based on Data-Driven Modeling (DDM) techniques (Artificial Neural Network and neuro-fuzzy systems) for more comprehensive and more accurate prediction of the pipe failure rate and an improved assessment of the reliability of pipes.
Abstract: In this paper two models are presented based on Data-Driven Modeling (DDM) techniques (Artificial Neural Network and neuro-fuzzy systems) for more comprehensive and more accurate prediction of the pipe failure rate and an improved assessment of the reliability of pipes. Furthermore, a multivariate regression approach has been developed to enable comparison with the DDM-based methods. Unlike the existing simple regression models for prediction of pipe failure rates in which only few factors of diameter, age and length of pipes are considered, in this paper other parameters such as pressure and pipe depth, are also included. Furthermore, an investigation is carried out on most commonly used mechanical reliability relationships and the results of incorporation of the proposed pipe failure models in the reliability index are compared. The proposed models are applied to a real case study involving a large water distribution network in Iran and the results of model predictions are compared with measured pipe failure data. Compared with the results of neuro-fuzzy and multivariate regression models, the outcomes of the artificial neural network model are more realistic and accurate in the prediction of pipe failure rates and evaluation of mechanical reliability in water distribution networks.
150 citations