Data mining in the oil industry
Jazyk: | ruština |
---|---|
Rok vydání: | 2021 |
Předmět: | |
DOI: | 10.18720/spbpu/3/2021/vr/vr21-4664 |
Popis: | ÐÐ°Ð½Ð½Ð°Ñ ÑабоÑа поÑвÑÑена иÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ ÑазлиÑнÑÑ Ð¼ÐµÑодов маÑинного обÑÑÐµÐ½Ð¸Ñ Ð´Ð»Ñ ÑÑкоÑÐµÐ½Ð¸Ñ Ð¸Ð½ÑеÑпÑеÑаÑии даннÑÑ Ð³ÐµÐ¾ÑизиÑеÑÐºÐ¸Ñ Ð¸ÑÑледований Ñкважин (ÐÐС). ÐадаÑи, коÑоÑÑе ÑеÑалиÑÑ Ð² Ñ Ð¾Ð´Ðµ иÑÑледованиÑ: 1. ÐÑполниÑÑ Ð¾Ð±Ð·Ð¾Ñ Ð°ÐºÑÑалÑнÑÑ Ð´Ð»Ñ Ð¸ÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ Ð² вÑбÑанной облаÑÑи лиÑеÑаÑÑÑнÑÑ Ð¼Ð°ÑеÑиалов, вклÑÑÐ°Ñ ÑÑаÑÑи, ÑÑебнÑе маÑеÑÐ¸Ð°Ð»Ñ Ð¸ поÑобиÑ. 2. ÐÑполниÑÑ Ð¾Ð±Ð·Ð¾Ñ Ð·Ð°Ð´Ð°Ñ Ð² неÑÑÑной пÑомÑÑленноÑÑи, ÑеÑаемÑÑ Ð¼ÐµÑодами маÑинного обÑÑениÑ. 3. ÐÑовеÑÑи анализ оÑновнÑÑ Ð¼ÐµÑодов инÑеллекÑÑалÑного анализа даннÑÑ . 4. ÐоÑÑÑоиÑÑ Ð¼Ð¾Ð´ÐµÐ»Ð¸ мÑлÑÑиклаÑÑовой и бинаÑной клаÑÑиÑикаÑии Ð´Ð»Ñ Ð¸Ð½ÑеÑпÑеÑаÑии даннÑÑ ÐÐС, пÑименив ÑазлиÑнÑе алгоÑиÑÐ¼Ñ Ð°Ð½Ð°Ð»Ð¸Ð·Ð° даннÑÑ . 5. ÐÑполниÑÑ Ð°Ð½Ð°Ð»Ð¸Ð· ÑезÑлÑÑаÑов пÑÐ¸Ð¼ÐµÐ½ÐµÐ½Ð¸Ñ Ð¼ÐµÑодов клаÑÑиÑикаÑии. ÐÑл пÑоведен ÑÑавниÑелÑнÑй анализ меÑодов инÑеллекÑÑалÑного анализа Ð´Ð»Ñ ÐºÐ»Ð°ÑÑиÑикаÑии гоÑнÑÑ Ð¿Ð¾Ñод и коллекÑоÑов на оÑновании геоÑизиÑеÑÐºÐ¸Ñ Ð¸ÑÑледований, пÑоведеннÑÑ Ð² 20 ÑÐºÐ²Ð°Ð¶Ð¸Ð½Ð°Ñ Ð½Ð¾ÑвежÑкого ÑелÑÑа. РабоÑа пÑоведена Ñ Ð¿Ð¾Ð¼Ð¾ÑÑÑ Ð²ÑÑÑоеннÑÑ ÑÑнкÑий библиоÑеки «sklearn» ÑзÑка Python. Ðо пÑедваÑиÑелÑно обÑабоÑаннÑм даннÑм поÑÑÑоено 6 моделей маÑинного обÑÑениÑ, оÑнованнÑÑ Ð½Ð° алгоÑиÑÐ¼Ð°Ñ : наивнÑй байеÑовÑкий клаÑÑиÑикаÑоÑ, меÑÐ¾Ð´Ñ Ð¾Ð¿Ð¾ÑнÑÑ Ð²ÐµÐºÑоÑов, деÑева ÑеÑений, ÑлÑÑайного леÑа, логиÑÑиÑеÑкой ÑегÑеÑÑии и k-меÑода ближайÑего ÑоÑеда. Ð ÑезÑлÑÑаÑе ÑÑÐ°Ð²Ð½ÐµÐ½Ð¸Ñ Ð¿Ð¾ ÑоÑноÑÑи пÑедÑÐºÐ°Ð·Ð°Ð½Ð¸Ñ Ð¸ вÑемени обÑÑÐµÐ½Ð¸Ñ Ð¼Ð¾Ð´ÐµÐ»ÐµÐ¹, наилÑÑÑие ÑезÑлÑÑаÑÑ Ð¿Ð¾ÐºÐ°Ð·Ð°Ð»Ð¸ меÑÐ¾Ð´Ñ Ð»Ð¾Ð³Ð¸ÑÑиÑеÑкой ÑегÑеÑÑии, деÑева ÑеÑений и ÑлÑÑайного леÑа. 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. |
Databáze: | OpenAIRE |
Externí odkaz: |
načítá se...