Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling
Assessing the phase composition of the fluid in a well based analysis of the frequencies of the radial resonance modes excited by acoustic noise in the inflow zone is a promising method for interpreting the results of passive noise metering. Machine learning makes it possible to take into account ma...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Sergo Ordzhonikidze Russian State University for Geological Prospecting
2020-03-01
|
| Series: | Известия высших учебных заведений: Геология и разведка |
| Subjects: | |
| Online Access: | https://www.geology-mgri.ru/jour/article/view/550 |
| _version_ | 1797878506958356480 |
|---|---|
| author | N. V. Mutovkin |
| author_facet | N. V. Mutovkin |
| author_sort | N. V. Mutovkin |
| collection | DOAJ |
| description | Assessing the phase composition of the fluid in a well based analysis of the frequencies of the radial resonance modes excited by acoustic noise in the inflow zone is a promising method for interpreting the results of passive noise metering. Machine learning makes it possible to take into account many factors affecting the spectrum of the measured signal, extracting from them exactly those factors associated with a change in phase composition. In order to build the best model, machine learning approaches such as linear regression with different variants of regularisation, Bayesian regression, neural net, methods of supporting vectors, decision tree, random forest and gradient boosting are considered. Data sets for training and testing the algorithm were obtained on the basis of scenarios calculated using a two-dimensional mathematical model with the different values of the bed parameters and ratio of volume fractions of the well filling fluids. The effect on the assessment accuracy of the phase composition of various factors, including the presence of acoustic device housing, the foreign noise in the signal and the shape of the signal spectrum, was checked. It is shown that in the absence of data distortion, it is possible to build models that provide an absolute error in the assessment of the phase composition about 1% after the zone of fluid inflow and about 5% in the zone before the inflow. |
| first_indexed | 2024-04-10T02:34:20Z |
| format | Article |
| id | doaj.art-15c97bbcf4ad47ae860f5ebb1eea2603 |
| institution | Directory Open Access Journal |
| issn | 0016-7762 2618-8708 |
| language | Russian |
| last_indexed | 2024-04-10T02:34:20Z |
| publishDate | 2020-03-01 |
| publisher | Sergo Ordzhonikidze Russian State University for Geological Prospecting |
| record_format | Article |
| series | Известия высших учебных заведений: Геология и разведка |
| spelling | doaj.art-15c97bbcf4ad47ae860f5ebb1eea26032023-03-13T07:51:38ZrusSergo Ordzhonikidze Russian State University for Geological ProspectingИзвестия высших учебных заведений: Геология и разведка0016-77622618-87082020-03-0106737910.32454/0016-7762-2019-6-73-79417Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modellingN. V. Mutovkin0Московский физико-технический институтAssessing the phase composition of the fluid in a well based analysis of the frequencies of the radial resonance modes excited by acoustic noise in the inflow zone is a promising method for interpreting the results of passive noise metering. Machine learning makes it possible to take into account many factors affecting the spectrum of the measured signal, extracting from them exactly those factors associated with a change in phase composition. In order to build the best model, machine learning approaches such as linear regression with different variants of regularisation, Bayesian regression, neural net, methods of supporting vectors, decision tree, random forest and gradient boosting are considered. Data sets for training and testing the algorithm were obtained on the basis of scenarios calculated using a two-dimensional mathematical model with the different values of the bed parameters and ratio of volume fractions of the well filling fluids. The effect on the assessment accuracy of the phase composition of various factors, including the presence of acoustic device housing, the foreign noise in the signal and the shape of the signal spectrum, was checked. It is shown that in the absence of data distortion, it is possible to build models that provide an absolute error in the assessment of the phase composition about 1% after the zone of fluid inflow and about 5% in the zone before the inflow.https://www.geology-mgri.ru/jour/article/view/550акустический шуминтерпретациямашинное обучениелинейная регрессияметод опорных векторовслучайный лесградиентный бустингнейронная сеть |
| spellingShingle | N. V. Mutovkin Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling Известия высших учебных заведений: Геология и разведка акустический шум интерпретация машинное обучение линейная регрессия метод опорных векторов случайный лес градиентный бустинг нейронная сеть |
| title | Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| title_full | Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| title_fullStr | Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| title_full_unstemmed | Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| title_short | Analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| title_sort | analysis of machine learning approaches for the interpretation of acoustic fields obtained by well noise data modelling |
| topic | акустический шум интерпретация машинное обучение линейная регрессия метод опорных векторов случайный лес градиентный бустинг нейронная сеть |
| url | https://www.geology-mgri.ru/jour/article/view/550 |
| work_keys_str_mv | AT nvmutovkin analysisofmachinelearningapproachesfortheinterpretationofacousticfieldsobtainedbywellnoisedatamodelling |