Machine Learning Classifies Data for Early Warning of Stuck Pipe Detection in Geothermal Drilling

Diyah Rosiani (1), Zulfan (2), Bambang Yudho Suranta (3), Akhmad Sofyan (4), Fandika Galih Pradana (5), Redha Bhawika Putra (6)
(1) Department of Oil and Gas Production Engineering, Politeknik Energi dan Mineral Akamigas, Cepu, Indonesia
(2) Department of Oil and Gas Production Engineering, Politeknik Energi dan Mineral Akamigas, Cepu, Indonesia
(3) Department of Oil and Gas Production Engineering, Politeknik Energi dan Mineral Akamigas, Cepu, Indonesia
(4) Department of Mineralogy, Geochemistry and Petrology, Faculty of Earth Science, University of Szeged, Szeged, Hungary
(5) PT Arka Data Pratama, Infiniti Office, Bellezza BSA 1st Floor, Jakarta Selatan, Indonesia
(6) PT Arka Data Pratama, Infiniti Office, Bellezza BSA 1st Floor, Jakarta Selatan, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
D. Rosiani, Zulfan, B. Y. Suranta, A. Sofyan, F. G. Pradana, and R. B. Putra, “Machine Learning Classifies Data for Early Warning of Stuck Pipe Detection in Geothermal Drilling”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 44–51, Feb. 2025.
Stuck pipe is a common issue encountered during geothermal well drilling which often disrupts operations and potentially leads to the suspension of drilling activities. This issue commonly occurs in lost circulation conditions within the reservoir zone, which reduce the capacity to lift cuttings and destabilize the drill hole due to inadequate drilling fluid performance. Therefore, this study aimed to propose an early warning system for detecting stuck pipe anomalies in geothermal drilling using machine learning as an Artificial Intelligence (AI) technique to expedite detection and response times. Time-based mud logging unit sensor data was used in the study collected from the drilling of five wells in the MGL field, all of which experienced stuck pipe incidents. The analysis further analyzed significant drilling parameters such as gas rate (considered for the first time), weight on bit (WOB), rotations per minute (RPM), standpipe pressure, mud flow rate, torque, hook load, rate of penetration (ROP), return, and condition readings. The dataset was evaluated using Support Vector Machine (SVM) and Artificial Neural Network (ANN) models to predict and classify conditions as normal, pre-stuck, or stuck. The results showed that SVM provided accuracy, precision, and recall of 0.99, 0.98, and 0.97, respectively outperforming ANN scoring 0.99, 0.98, and 0.89. This implied that SVM could provide better prediction results than ANN, offering a fast and effective method for early detection by improving response times and accuracy in preventing stuck pipe incidents.

A. Sofyan, J. Szanyi, and H.S. Aka, "Investigation of Zone and Type of Scaling Based on the Fluid Flow Pattern in the Geothermal Well “X” at the Salak Geothermal Field-Indonesia, " International Journal of Renewable Energy Research, vol. 14, 2024, doi:10.20508/ijrer.v14i1.14254.g8879.

A. Sofyan, S. Wiharti, J. Szanyi, B. Y. Suranta, and R. Njeru, “Determination of Scaling Zone and Scaling Type in Slotted Liner Based on the Fluid Flow Pattern in the Geothermal Well ‘X.’, ” International Journal of Renewable Energy Research, vol. 13, 2023, doi:10.20508/ijrer.v13i1.13603.g8681.

R. W. Putra and Ashadi, “Drilling through paleosol–an experience in Sorik Marapi,” the 8th Indonesia International Geothermal Convention & Exhibition (IIGCE), 2022.

D. J. EBTKE, Pedoman efisiensi biaya pengeboran sumur panas bumi. Direktorat Jenderal EBTKE: Jakarta, 2023.

M. J. Prihutomo and S. Arianto, ”Drilling performance improvements of Salak geothermal field, Indonesia 2006 – 2008,” Proceedings World Geothermal Congress, 2010.

D. Purba, D. W. Adityatama, F. N. Siregar, M. Solehudin, M. R. Al Asy’ari, A. A. Wicaksana, M. F. Umam, D. Alamsyah, and R. Asokawaty, “Integrated stuck-pipe-prevention campaign in a geothermal drilling project in Indonesia: a proactive approach,” Proceedings World Geothermal Congress, 2020.

V. S. M. Siqueira, M. A. S. L. Cuadros, C. J. Munaro, and G. M. D. Almeida, “Expert system for early sign stuck pipe detection: Feature engineering and fuzzy logic approach,” Engineering Applications of Artificial Intelligence, vol. 127, 2024, doi: 10.1016/j.engappai. 2023.107229.

A. Brankovic, M. Matteucci, M. Restelli, L. Ferrarini, L. Piroddi, A. Speltac, and F. Zausac, “ Data-driven indicators for the detection and prediction of stuck-pipe events in oil&gas drilling operations,” Upstream Oil and Gas Technology, vol. 7, 2021, doi:10.1016/j.upstre.2021.100043.

N. Zhu, W. Huang, and D. Gao, “ Numerical analysis of the stuck pipe mechanism related to the cutting bed under various drilling operations,” Journal of Petroleum Science and Engineering, vol. 208, 2022, doi:10.1016/j.petrol.2021.109783.

M. F. A. Dushaishi, A. K. Abbas, M. Alsaba, H. Abbas, and J. Dawood, “Data-driven stuck pipe prediction and remedies,” Upstream Oil and Gas Technology, vol. 6, 2021, doi: 10.1016/j.upstre.2020.100024.

K. Salminen, C. Cheatham, M. Smith, K. Valiulin, and R. Causes, “Stuck pipe prediction using automated real-time modelling and data,” the IADC/SPE Drilling Conference and Exhibition, Fort Worth, Texas, USA, March 2016, doi: 10.2118/178888-MS.

F. G. Pradana, “Reducing the possibility of stuck pipe in geothermal drilling operations using machine learning algorithm,” the 9th Indonesia International Geothermal Convention & Exhibition, 2023.

S. D’Amicis, M. Pagani, M. Matteucci, L. Piroddi, A. Spelta, and F. Zausa, “Stuck pipe prediction from rare events in oil drilling operations,” Upstream oil and gas technology, Vol. 11, September 2023, doi: 10.1016/j.upstre.2023.100096.

A. K. Abbas, R. Flori, H. Almubarak, J. Dawood, H. Abbas, and A. Alsaedi, “Intelligent Prediction of Stuck Pipe Remediation Using Machine Learning Algorithms,” SPE Annual Technical Conference and Exhibition, September 2019, doi: 10.2118/196229-MS.

Sarwono, Lukas, M. A. Kartawidjaja, and R. S. Wardana, “Stuck pipe detection for north Sumatera geothermal drilling operation,” Jurnal Migasian, Vol. VI, No. I, pp. 2580-5258, 2022, doi: 10.36601/jurnal-migasian.v6i1.192.

V. K. Payrazyan and T. S. Robinson, “Leveraging targeted machine learning for early warning and prevention of stuck pipe, tight holes, pack offs, hole cleaning issues and other potential drilling hazards, ”Offshore Technology Conference, Houston, Texas, USA, May 2023, doi: 10.4043/32169-MS

W. K. Wong, Y. Nuwara, F.H. Juwono, and F. Motalebi, “Sonic Waves Travel-time Prediction: When Machine Learning Meets Geophysics,” International Conference on Green Energy, Computing and Sustainable Technology (GECOST), doi:10.1109/gecost55694. 2022.10010361

W. K. Wong, F.H. Juwono, and J.T.H. Kong, “Synthesizing Missing Travel Time of P-Wave and S-Wave: A Two-Stage Evolutionary Modeling Approach,” IEEE Sensors Journal, Vol. 23, No. 14, 15 July 2023, doi: 10.1109/jsen.2023.3280708

A. K. Abbas, H. Almubarak, H. Abbas, and J. Dawood, “Application of machine learning approach for intelligent prediction of pipe, ”Abu Dhabi International Petroleum Exhibition & Conference, November 2019, doi: 10.2118/197396-MS.

Q. K. Do, T. Q. Hoang, T. Nguyen, and V. K. P. Ong, “Predicting and avoiding hazardous occurrences of stuck pipe for the petroleum wells at offshore Vietnam using machine,” IOP Conference Series: Earth and Environmental Science, November 2022, doi:10.1088/1755-1315 /1091/1/012003.

T. Kizayev, S. Irawan, J. A. Khana, and S. A. Khan, “Factors affecting drilling incidents: Prediction of suck pipe by XGBoost model,” The 7th International Conference on New Energy and Future Energy Systems 2022, doi: 10.1016/j.egyr.2023.03.083.

A. Aseel, M. A. Abdullah, R. Roy, P. V. Sidharth, O. K. Krishnan, and J. Joseph, “Analysis of pipe sticking due to wellbore uncleanliness using machine learning,” Heliyon, Vol. 9, Issue 12, December 2023, doi: 10.1016/j.heliyon.2023.e22366.

Z. Karimi, “Confusion Matrix,” Encycl. Mach. Learn. Data Min., pp. 260–260, October 2021, doi: 10.1007/978-1-4899-7687-1_50.

A. Munde and J. Kaur, “Predictive modelling of customer sustainable jewellery purchases using machine learning algorithms,” International Conference on Machine Learning and Data Engineering (ICMLDE 20) Procedia Computer Science, vol. 235, 2024, pp 683–700, doi:10.1016/j.procs.2024.04.066.

M. O. Miah, U. Habiba, and M. F. Kabir, “ODL-BCI: Optimal deep learning model for brain-computer interface to classify students confusion via hyperparameter tuning,” Brain Disorders, Vol. 13, March 2024, doi: 10.1016/j.dscb.2024.100121.

Husni, F. H. Rachman, I. O. Suzanti, and M. K. Sari, "Word ambiguity identification using pos tagging in automatic essay scoring," IEEE 8th Information Technology International Seminar (ITIS), 2022, pp. 140-144, doi:10.1109/ITIS57155. 2022.10009034.

B. A. Makayasa, M. U. Siregar, B. Sugiantoro, and A. Fatwanto, “Comparison of classification algorithm and language model in accounting financial transaction record: a natural language processing approach,” IJASEIT, Vol. 14, pp. 880-886, 2024, doi:10.18517/ijaseit.14.3.19179.

J. Chaoraingern, V. Tipsuwanporn, and A.Numsomran, “Artificial intelligence for the classification of plastic waste utilizing tinyml on low-cost embedded systems,” IJASEIT, Vol. 13, pp. 2328-2337, 2023, doi: 10.18517/ijaseit.13.6.18958.

E. A. Anggari, A. Herawan, P. R. Hakim, A. Wahyudiono, S. Salaswati, E. Rachim, and Z. Zylshal, “Assessing the accuracy of land use classification using multi-spectral camera from LAPAN-A3, Landsat-8 and Sentinel-2 satellite: A Case Study in Probolinggo-East Java,” IJASEIT, Vol. 13, pp.1622-1627, 2023, doi:10.18517/ijaseit.13.5.18570.

D. V. Carreras, J. Alcaraz, and M. Landete, “Comparing two SVM models through different metrics based on the confusion matrix,” Computers & Operations Research, Vol. 152, April 2023, doi:10.1016/ j.cor.2022.106131

V. Vapnik, “The Nature of Statistical Learning Theory,” New York: Springer-Verlag, 1995.

A. Mollajan, H. Memarian, and M. R. Jalali, “Prediction of reservoir water saturation using support vector regression in an Iranian carbonate reservoir,” 47th U.S. Rock Mechanics/Geomechanics Symposium, San Francisco, California, June 2013.

J. S. Pimentel, R. Ospina, and A. Ara, “A novel fusion support vector machine integrating weak and sphere models for classification challenges with massive data,” Decision Analytics Journal, Vol. 11, June 2024, doi: 10.1016/j.dajour.2024.100457.

I. Al-Baiyat and L. Heinze, “Implementing artificial neural networks and support vector machines in stuck pipe prediction,” SPE Kuwait International Petroleum Conference and Exhibition, 2012, doi:10.2118/163370-MS.

K. O. Akande, T. O. Owolabi, and S. O. Olatunji, ”Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization,” Journal of Natural Gas Science and Engineering, Vol. 22, pp 515-522, January 2015, doi: 10.1016/j.jngse.2015.01.007.

D. Rosiani, M. G. Walay, P. Rahalintar, A. D. Candra, A. Sofyan, and Y. A. Haratua, “Application of artificial intelligence in predicting oil production based on water injection rate, ”IJASEIT,” Vol.13, 2023, doi:10.18517/ijaseit.13.6.19399.

A. M. Al-Sabaeei, H. Alhussian, S. J. Abdulkadir, and A. Jagadeesh, “Prediction of oil and gas pipeline failures through machine learning approaches: A systematic review,” Energy Reports, Vol. 10, 2023, doi:10.1016/j.egyr.2023.08.009.

W. Pannakkong, K. Thiwa-Anont, K. Singthong, P. Parthanadee, and J. Buddhakulsomsiri, “Hyperparameter Tuning of Machine Learning Algorithms Using Response Surface Methodology: A Case Study of ANN, SVM, and DBN,” Mathematical Problems in Engineering, Vol. 2022, January 2022, doi: 10.1155/2022/8513719.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).