Prediksi Rate of Penetration pada Pengeboran Minyak Bumi dengan Elman Recurrent Neural Network

ELSA AIZIYAH; ALLEN HARYANTO; AGUS MAMAN ABADI

doi:10.26760/mindjournal.v10i2.145-161

Prediksi Rate of Penetration pada Pengeboran Minyak Bumi dengan Elman Recurrent Neural Network

ELSA AIZIYAH, ALLEN HARYANTO, AGUS MAMAN ABADI

Sari

ABSTRAK

Penelitian ini bertujuan memprediksi laju penetrasi (ROP) guna mempercepat waktu pengeboran dan menekan biaya operasional. Metode yang digunakan adalah Elman Recurrent Neural Network (ERNN) dengan algoritma backpropagation, yang dipilih karena kemampuannya dalam mengenali pola data sekuensial pada data pengeboran. Data yang digunakan 2613 data ASCII Mudlogging minyak bumi dari PT Geotama Jogja dengan 5 variabel input, yaitu Kedalaman Vertikal Sejati atau TVD (m), Beban Mata Bor atau WOB (klbs), Kepadatan Sirkulasi Ekuivalen atau ECD (SG), Mud Weight in atau MWI (SG), dan Total Kecepatan Rotasi Pahat atau TRPM. Sedangkan variabel outputnya yaitu laju penetrasi atau ROP (m/hr). Data dihaluskan menggunakan Savitzky-Golay filter dan dibagi data training dan data testing yang sebesar 90% dan 10%. Model ERNN terbaik yang diperoleh yaitu 5 variabel input, 17 neuron tersembunyi, dan 1 variabel output. Nilai MAPE data training sebesar 16.18%, dengan akurasi 83.82%. Sedangkan nilai MAPE data testing sebesar 15.48%, sehingga akurasinya 84.52%.

Kata kunci: Elman Recurrent Neural Network, laju penetrasi, prediksi, minyak bumi, MAPE

ABSTRACT

This study aims to predict the rate of penetration (ROP) to speed up drilling time and reduce operational costs. The method used is the Elman Recurrent Neural Network (ERNN) with the backpropagation algorithm, which was chosen because of its ability to recognize sequential data patterns in drilling data. The data used are 2613 ASCII Mudlogging data from PT Geotama Jogja with 5 input variables, namely True Vertical Depth or TVD (m), Drill Bit Load or WOB (klbs), Equivalent Circulation Density or ECD (SG), Mud Weight in or MWI (SG), and Total Tool Rotation Speed or TRPM. While the output variable is the rate of penetration or ROP (m/hr). The data is smoothed using the Savitzky-Golay filter and divided into training data and testing data of 90% and 10%. The best ERNN model obtained is 5 input variables, 17 hidden neurons, and 1 output variable. The MAPE value of the training data is 16.18%, so the accuracy is 83.82%. Meanwhile, the MAPE value for the testing data was 15.48%, resulting in an accuracy of 84.52%.

Keywords: Elman Recurrent Neural Network, penetration rate, prediction, petroleum, MAPE

Teks Lengkap:

PDF

Referensi

Abadi, A. M., Mansyaroh, A. K., Lukmana, A. H., & Harini, L. (2024). Construction of fuzzy systems based on fuzzy c-means clustering and singular value decomposition for predicting rate of penetration in geothermal drilling, 15 (4), 2190–2198. https://doi.org/10.11591/ijpeds.v15.i4.pp2190-2198

Adebiyi, F. M. (2022). Environmental Chemistry and Ecotoxicology Air quality and management in petroleum refining industry : A review. Environmental Chemistry and Ecotoxicology, 4 (January), 89–96. https://doi.org/10.1016/j.enceco.2022.02.001

Alkinani, H. H., Al-hameedi, A. T. T., & Dunn-norman, S. (2021). Data-driven recurrent neural network model to predict the rate of penetration Upstream Oil and Gas Technology. Upstream Oil and Gas Technology, 7(May 2020), 100047. https://doi.org/10.1016/j.upstre.2021.100047

Anemangely, M., Ramezanzadeh, A., & Tokhmechi, B. (2018). Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network. Journal of Geophysics and Engineering, 15(4), 1146–1159. https://doi.org/10.1088/1742-2140/aaac5d

Asante, D., Omar, T., Ganat, A., Gholami, R., & Ridha, S. (2021). Journal of Petroleum Science and Engineering Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties : Comparative analysis of ANN and SVM models. Journal of Petroleum Science and Engineering, 200(November 2020), 108182. https://doi.org/10.1016/j.petrol.2020.108182

Bani, A., Ahmed, M., Mortadha, K. A., & Mamoon, A. (2021). Improving drilling performance through optimizing controllable drilling parameters. Journal of Petroleum Exploration and Production, 11(3), 1223–1232. https://doi.org/10.1007/s13202-021-01116-2

Bourgoyne, A.T., and F.S. Young. "A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection." SPE J. 14 (1974): 371–384. doi: https://doi.org/10.2118/4238-PA

Brenjkar, E., & Delijani, E. B. (2022). Computational prediction of the drilling rate of penetration (ROP): A comparison of various machine learning approaches and traditional models. Journal of Petroleum Science and Engineering, 210, 110033. https://doi.org/10.1016/j.petrol.2021.110033.

Bromba, A. (1981). Application hints for Savitzky-Golay digital smoothing filters. Analytical Chemistry, 53(11), 1583–1586. https://doi.org/10.1021/ac00234a011

Chen, W., & Zhou, K. (2017). Data quality of electricity consumption data in a smart grid environment. Renewable and Sustainable Energy Reviews, 75(October 2016), 98–105. https://doi.org/10.1016/j.rser.2016.10.054

Elkatatny, S. (2021). Real-time prediction of rate of penetration while drilling complex lithologies using artificial intelligence techniques. Ain Shams Engineering Journal, 12(1), 917–926. https://doi.org/10.1016/j.asej.2020.05.014

Farida, Y., Sulistiani, D. A., & Ulinnuha, N. (2023). Klasifikasi data ketidakpastian menggunakan metode fuzzy decision tree. Teorema: Teori dan Riset Matematika, 6(2), 173–183. https://doi.org/10.25157/teorema.v6i2.5521

Fu, Q., Nicholson, G. L., & Easton, J. M. (2024). Journal of Industrial Information Integration Understanding data quality in a data-driven industry context : Insights from the fundamentals. Journal of Industrial Information Integration, 42(November), 100729. https://doi.org/10.1016/j.jii.2024.100729

Hegde, C., Daigle, H., Millwater, H., & Gray, K. (2017). Journal of Petroleum Science and Engineering Analysis of rate of penetration (ROP) prediction in drilling using physics-based and data-driven models. Journal of Petroleum Science and Engineering, 159, 295–306. https://doi.org/10.1016/j.petrol.2017.09.020

lhassanien, A. A., Nooh, A. Z., & Abu-Hashish, M. F. (2024). Pore pressure prediction using artificial intelligence techniques: A case study of Rudeis Formation at Al-Amal Oil Field, Gulf of Suez, Egypt. Middle East Journal of Petroleum Sciences, 13(1), 1–11. https://doi.org/10.62593/2090-2468.1045

Islam, M. R., & Hossain, M. E. (2021). Chapter 2 - State-of-the-art of drilling. In M. R. Islam & M. E. B. T.-D. E. Hossain (Eds.), Sustainable Oil and Gas Development Series (pp. 17–178). Gulf Professional Publishing. https://doi.org/https://doi.org/10.1016/B978-0-12-820193-0.00002-2

Karkouch, A., Mousannif, H., Al, H., & Noel, T. (2016). Journal of Network and Computer Applications Data quality in internet of things : A state-of-the-art survey. Journal of Network and Computer Applications, 73, 57–81. https://doi.org/10.1016/j.jnca.2016.08.002

Lin, C. Y., & Tjeerdema, R. S. (2008). Crude Oil, Oil, Gasoline and Petrol. In S. E. Jørgensen & B. D. B. T.-E. of E. Fath (Eds.) (pp. 797–805). Oxford: Academic Press. https://doi.org/https://doi.org/10.1016/B978-008045405-4.00382-7

Radjabaycolle, J. (2020). Prediksi penggunaan bandwidth menggunakan Elman recurrent. Barekeng: Jurnal Ilmu Matematika dan Terapan, 10(2), 127–135. https://doi.org/10.30598/barekengvol10iss2pp127-135

Rahmayanti, L., Rahmah, D. M., & Larashati. (2021). Minyak dan gas bumi di Indonesia. Jurnal Sains Edukatika Indonesia (JSEI), 3(2), 9–16.

Riazi, M., Mehrjoo, H., Nakhaei, R., & Jalalifar, H. (2022). Modelling rate of penetration in drilling operations using RBF , MLP , LSSVM , and DT models. Scientific Reports, 1–24. https://doi.org/10.1038/s41598-022-14710-z

Sadeghi, M., & Behnia, F. (2018). Optimum window length of Savitzky-Golay filters with arbitrary order. arXiv. https://doi.org/10.48550/arXiv.1808.10489

Savitzky, A., & Golay, M. J. E. (1964). Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry, 36(8), 1627–1639. https://doi.org/10.1021/ac60214a047

Sobhi, I., Dobbi, A., & Hachana, O. (2021). deterministic and metaheuristic optimization methods Prediction and analysis of penetration rate in drilling operation using deterministic and metaheuristic optimization methods. Journal of Petroleum Exploration and Production Technology, (December). https://doi.org/10.1007/s13202-021-01394-w

Suahati, A. F., Nurrahman, A. A., & Rukmana, O. (2022). Penggunaan Jaringan Syaraf Tiruan – Backpropagation dalam Memprediksi Jumlah Mahasiswa Baru Predicting Number of New Student Using Artificial Neural Network - Backpropagation, 6(1), 21–29. https://doi.org/10.35194/jmtsi.v6i1.1589

Sun, J., Yang, F., Qi, B., Li, Z., & Li, J. (2024). A New Calculation Model for Equivalent Circulating Density Considering Interface Effect between Various Fluids during Cementing Process. SPE Journal, 29(05), 2242–2256. https://doi.org/10.2118/219481-PA

Wang, Y., Storey, V. C., & Firth, P. (1995). A framework for analysis of data quality research. IEEE Transactions on Knowledge and Data Engineering, 7(4), 554–568. https://doi.org/10.1109/69.404034

Wang, Z., Fingas, M., Yang, C., & Christensen, J. H. (1964). 16 - Crude Oil and Refined Product Fingerprinting: Principles. In R. D. Morrison & B. L. B. T.-E. F. Murphy (Eds.) (pp. 339–407). Burlington: Academic Press. https://doi.org/https://doi.org/10.1016/B978-012507751-4/50038-0

Xiong, M., Zheng, S., Cheng, R., Bai, K., Wang, L., Zhang, H., & Wang, G. (2024). A rate of penetration (ROP) prediction method based on improved dung beetle optimization algorithm and BiLSTM-SA. arXiv. https://doi.org/10.21203/rs.3.rs-4255057/v1 Zhou, C., Zou, C., Zhang, Y., &

Wang, Z. (2014). Nonparametric Control Chart Based on Change-point Model. Computational Statistics & Data Analysis, 51(2), 1237–1245. https://doi.org/10.1007/s00362-007-0054-7

Zhou, C., Zou, C., Zhang, Y., & Wang, Z. (2014). Nonparametric Control Chart Based on Change-point Model. Computational Statistics & Data Analysis, 51(2), 1237–1245. https://doi.org/10.1007/s00362-007-0054-7

DOI: https://doi.org/10.26760/mindjournal.v10i2.145-161