Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site
Well planning for every drilling project includes cost estimation. Maximizing the rate of penetration (ROP) reduces the time required for drilling, resulting in reducing the expenses required for the drilling budget. The empirical formulas developed to predict ROP have limited field applications. Si...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/12/4288 |
| _version_ | 1797487817493839872 |
|---|---|
| author | Mohamed Arbi Ben Aoun Tamás Madarász |
| author_facet | Mohamed Arbi Ben Aoun Tamás Madarász |
| author_sort | Mohamed Arbi Ben Aoun |
| collection | DOAJ |
| description | Well planning for every drilling project includes cost estimation. Maximizing the rate of penetration (ROP) reduces the time required for drilling, resulting in reducing the expenses required for the drilling budget. The empirical formulas developed to predict ROP have limited field applications. Since real-time drilling data acquisition and computing technologies have improved over the years, we implemented the data-driven approach for this purpose. We investigated the potential of machine learning and deep learning algorithms to predict the nonlinear behavior of the ROP. The well was drilled to confirm the geothermal reservoir characteristics for the FORGE site. After cleaning and preprocessing the data, we selected two models and optimized their hyperparameters. According to our findings, the random forest regressor and the artificial neural network predicted the behavior of our field ROP with a maximum absolute mean error of 3.98, corresponding to 19% of the ROP’s standard deviation. A tool was created to assist engineers in selecting the best drilling parameters that increase the ROP for future drilling tasks. The tool can be validated with an existing well from the same field to demonstrate its capability as an ROP predictive model. |
| first_indexed | 2024-03-09T23:53:11Z |
| format | Article |
| id | doaj.art-0ddff2936c814779871fc6dc12dd2aac |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T23:53:11Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-0ddff2936c814779871fc6dc12dd2aac2023-11-23T16:28:38ZengMDPI AGEnergies1996-10732022-06-011512428810.3390/en15124288Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE SiteMohamed Arbi Ben Aoun0Tamás Madarász1Department of Civil, Geological and Mining Engineering, Polytechnique Montréal, 2500 Chemin de Polytechnique, Montréal, QC H3T 1J4, CanadaInstitute of Environmental Management, University of Miskolc, 3515 Miskolc-Egyetemváros, HungaryWell planning for every drilling project includes cost estimation. Maximizing the rate of penetration (ROP) reduces the time required for drilling, resulting in reducing the expenses required for the drilling budget. The empirical formulas developed to predict ROP have limited field applications. Since real-time drilling data acquisition and computing technologies have improved over the years, we implemented the data-driven approach for this purpose. We investigated the potential of machine learning and deep learning algorithms to predict the nonlinear behavior of the ROP. The well was drilled to confirm the geothermal reservoir characteristics for the FORGE site. After cleaning and preprocessing the data, we selected two models and optimized their hyperparameters. According to our findings, the random forest regressor and the artificial neural network predicted the behavior of our field ROP with a maximum absolute mean error of 3.98, corresponding to 19% of the ROP’s standard deviation. A tool was created to assist engineers in selecting the best drilling parameters that increase the ROP for future drilling tasks. The tool can be validated with an existing well from the same field to demonstrate its capability as an ROP predictive model.https://www.mdpi.com/1996-1073/15/12/4288rate of penetration (ROP)predictive modelinggeothermal energymachine learningdeep learningrandom forests |
| spellingShingle | Mohamed Arbi Ben Aoun Tamás Madarász Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site Energies rate of penetration (ROP) predictive modeling geothermal energy machine learning deep learning random forests |
| title | Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site |
| title_full | Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site |
| title_fullStr | Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site |
| title_full_unstemmed | Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site |
| title_short | Applying Machine Learning to Predict the Rate of Penetration for Geothermal Drilling Located in the Utah FORGE Site |
| title_sort | applying machine learning to predict the rate of penetration for geothermal drilling located in the utah forge site |
| topic | rate of penetration (ROP) predictive modeling geothermal energy machine learning deep learning random forests |
| url | https://www.mdpi.com/1996-1073/15/12/4288 |
| work_keys_str_mv | AT mohamedarbibenaoun applyingmachinelearningtopredicttherateofpenetrationforgeothermaldrillinglocatedintheutahforgesite AT tamasmadarasz applyingmachinelearningtopredicttherateofpenetrationforgeothermaldrillinglocatedintheutahforgesite |