Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Интеллектуальный анализ Ð´Ð°Ð½Ð½Ñ‹Ñ Ð² области нефтяной промышленности

выпускная квалификационная работа магистра

Интеллектуальный анализ Ð´Ð°Ð½Ð½Ñ‹Ñ Ð² области нефтяной промышленности

Abstract

Данная работа посвящена исследованию различных методов машинного обучения для ускорения интерпретации данных геофизических исследований скважин (ГИС). Задачи, которые решались в ходе исследования: 1. Выполнить обзор актуальных для исследования в выбранной области литературных материалов, включая статьи, учебные материалы и пособия. 2. Выполнить обзор задач в нефтяной промышленности, решаемых методами машинного обучения. 3. Провести анализ основных методов интеллектуального анализа данных. 4. Построить модели мультиклассовой и бинарной классификации для интерпретации данных ГИС, применив различные алгоритмы анализа данных. 5. Выполнить анализ результатов применения методов классификации. Был проведен сравнительный анализ методов интеллектуального анализа для классификации горных пород и коллекторов на основании геофизических исследований, проведенных в 20 скважинах норвежского шельфа. Работа проведена с помощью встроенных функций библиотеки «sklearn» языка Python. По предварительно обработанным данным построено 6 моделей машинного обучения, основанных на алгоритмах: наивный байесовский классификатор, методы опорных векторов, дерева решений, случайного леса, логистической регрессии и k-метода ближайшего соседа. В результате сравнения по точности предсказания и времени обучения моделей, наилучшие результаты показали методы логистической регрессии, дерева решений и случайного леса.

The subject of the graduate qualification work is «Data mining in the oil industry». The given work is devoted to the study of various machine learning methods to accelerate the interpretation of well logging data. The research set the following goals: 1. Review relevant literature materials for research in the chosen field, including articles, abstracts, educational materials and manuals. 2. Review of tasks in the oil industry, performed by machine learning methods. 3. Analyze the main methods of data mining. 4. Build multiclass and binary classification models for interpreting data using various data analysis algorithms. 5. Analyze the results of applying classification methods. A comparative analysis of mining methods was carried out for the classification of rocks and reservoirs based on well logging data of 20 the Norwegian shelf wells. The work was carried out using the built-in functions of the sklearn library of the Python language. Based on the processed data, 6 machine learning models were built: a naive Bayesian classifier, support vector machines, decision trees, a random forest, logistic regression, and the k-nearest neighbor method. As a result of comparison of the accuracy of prediction and training time of the models, the method of logistic regression, decision tree and random forest were determined by the optimal methods.

Keywords

Нефтяная промышленность, Программирования языки, Искусственный интеллект, Базы данныÑ, Алгоритмы, Нефтяные и газовые скважины

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!