POLNAMPOLNAM

JURNAL SIMETRIKJURNAL SIMETRIK

Reservoir parameter optimisation is a critical aspect of enhancing the hydrocarbon recovery factor and requires systematic, integrated approaches. This research develops an integrated framework combining numerical reservoir modelling with multivariate regression analysis to optimise key reservoir parameters. The research methodology employs three-dimensional numerical simulation, implementation of a multi-objective optimisation algorithm, and development of machine learning models for recovery factor prediction. Research data encompasses reservoir petrophysical parameters, including effective porosity ranging from 12.5% to 28.7%, horizontal permeability from 15 mD to 450 mD, and initial oil saturation from 52.3% to 84.6%. Optimisation analysis using three algorithms demonstrates that the Multi-Objective Grey Wolf Optimiser achieves superior performance, with an optimal recovery factor of 46.3% using only eight parameters. The third-order polynomial regression model yields a coefficient of determination of 0.89 in predicting nonlinear relationships between reservoir parameters and recovery factor. An artificial neural network implementation achieves 94.2% training and 89.3% test prediction accuracy, with a mean absolute error of 2.1%. Development scenario simulation indicates the five-spot injection pattern configuration produces the highest recovery factor, 48.2% with a present value of 187.3 million USD. The developed integrated framework demonstrates the ability to handle reservoir heterogeneity, with validation showing deviations of less than 7% relative to field data.

Penelitian ini berhasil mengembangkan framework terintegrasi yang menggabungkan pemodelan numerik reservoir dengan analisis regresi multivariat untuk mengoptimalkan parameter kunci dalam meningkatkan recovery factor hidrokarbon.Algoritma optimasi multiobjektif Grey Wolf Optimizer menunjukkan performa superior dengan recovery factor 46,3%.Simulasi skenario pengembangan mengindikasikan konfigurasi sumur dengan pola injeksi lima titik menghasilkan recovery factor optimal sebesar 48,2%.

Penelitian lanjutan perlu dilakukan untuk mengeksplorasi integrasi model pembelajaran mesin dengan data seismik 4D untuk meningkatkan akurasi karakterisasi heterogenitas reservoir secara real-time. Selain itu, studi lebih lanjut dapat difokuskan pada pengembangan algoritma optimasi yang lebih efisien dan adaptif, yang mampu menangani ketidakpastian parameter reservoir dan perubahan kondisi operasional secara dinamis. Terakhir, penelitian perlu dilakukan untuk menginvestigasi potensi penerapan teknologi enhanced oil recovery (EOR) seperti injeksi CO2 atau polimer, dengan mempertimbangkan aspek ekonomi dan lingkungan untuk memaksimalkan recovery factor secara berkelanjutan.

  1. PETRO. studi estimasi co2 storage reservoir gas penurunan petro jurnal ilmiah teknik perminyakan main... e-journal.trisakti.ac.id/index.php/petro/article/view/19284PETRO studi estimasi co2 storage reservoir gas penurunan petro jurnal ilmiah teknik perminyakan main e journal trisakti ac index php petro article view 19284
Read online
File size413.62 KB
Pages8
DMCAReport

Related /

ads-block-test