On increasing the productive time of drilling oil and gas wells using machine learning methods

Abstract

The article is devoted to the development of a hybrid method for predicting and preventing the development of troubles in the process of drilling wells based on machine learning methods and modern neural network models. Troubles during the drilling process, such as filtrate leakoff; gas, oil and water shows and sticking, lead to an increase in unproductive time, i.e. time that is not technically necessary for well construction and is caused by various violations of the production process. Several different approaches have been considered, including based on the regression model for predicting the indicator function, which reflects an approach to a developing trouble, as well as anomaly extraction models built both on basic machine learning algorithms and using the neural network model of deep learning. Showing visualized examples of the work of the developed methods on simulation and real data. Intelligent analysis of Big Geodata from geological and technological measurement stations is based on well-proven machine learning algorithms. Based on these data, a neural network model was proposed to prevent troubles and emergencies during the construction of wells. The use of this method will minimize unproductive drilling time.

Using Supervised Machine Learning Algorithms for Kick Detection During Managed Pressure Drilling

“…Помимо теоретической базы в работах [4][5][6] отражены результаты применения современных методов машинного обучения для выявления различных осложнений и аварий в процессе бурения, в том числе ГНВП. В работах отражена статистика по метрикам качества выявления описанных инцидентов, что немаловажно, результаты получены на основании данных с реально пробуренных скважин, что позволяет с большей уверенностью полагаться на них.…”

A Survey on Industry 4.0 for the Oil and Gas Industry: Upstream Sector

“…The use of AI techniques such as artificial neural networks, ANN, radial basis function, RBF, fuzzy logic, FL, support vector machine, SVM, and functional networks (FN) have been explored in the prediction of pore pressure while drilling [119], drilling optimization [120], forecasting of gas-to-oil ratio (GOR) from a generic hydraulically fractured reservoir [121], selection of drill bits [122], hole cleaning in horizontal wells [123] and condition-based maintenance systems for downhole tools [124]. Other areas of application such as the use of AI in the detection and mitigation of lost circulation incidents during drilling [125]- [127] and prediction of drilling problems [128], [129] have shown promising results. This helps to increase the productive time of drilling in O&G wells.…”

The Influence of Work Period and Work Location of Workers with Understanding of Corporate Life Saving Rules (CLSR) at Oil and Gas Fuel Terminal Companies in Indonesia

“…Life saving rules are one of the occupational safety and health cultures through periodic intervention, if it is not maximized with a lack of management commitment and poor leadership in safety at work in a company, it is necessary to create awareness of the occupational health and safety management system in the company and knowledge of workers to achieve goals. work accident prevention (Abanum et al, 2020;Walker et al, 2020) Workers in the oil and gas sector are exposed to hazardous conditions and are always involved in high-risk activities, with the possibility of work accidents with the socialization of life saving rules on a regular basis with the aim of improving work safety to protect workers from all kinds of incidents (Dmitrievsky et al, 2020) Therefore, studies in this sector are imperative to increase knowledge among workers, which is very important for workers' awareness in securing energy assets, maintaining worker safety, and a green environment (Industri et al, 2021;Raut et al, 2018).…”