Claim Missing Document
Check
Articles

Found 2 Documents
Search

ROP Prediction with Supervised Machine Learning; a Case Study : Supervised Machine Learning Ganesha R Darmawan; Dedi Irawan
Journal of Earth Energy Engineering Vol. 11 No. 1 (2022)
Publisher : Universitas Islam Riau (UIR) Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/jeee.2022.7772

Abstract

Optimum drilling penetration rate, known as the rate of penetration (ROP) has played a big role in drilling operations. Planning the well ROP always becomes a challenge for drilling engineers to calculate the drilling time needed for the section. Optimum ROP is achieved when the time to drill the section is as planned. Many empirical approaches were develop to model the ROP based on the drilling parameters, and might not always match the actual ROP. In some cases, the actual ROP was slower than planned, which may increase the drilling cost, which needs to be avoided. Hence, some approaches using artificial intelligence (AI), and supervised machine learning have been develop to overcome it. Supervised machine learning is used to developed a ROP model and ROP prediction for one of the development fields, based only on two wells drilling parameters data. The model was trained using Gradient Boosting, Random Forest, and Support Vector Machine. Drilling parameter test data then is used to validate the model. The model of Random Forest shows a good or promising result with R2 of 0.90, Gradient Boosting shows R2 of 0.86, and Support Vector Machine with R2 0.72. Based on the models generated, the Random Forest has shown a good trend which could be used for modeling ROP in the future development wells
The Recovery Factor Analysis on Heavy Oil Under Electromagnetic Heating Treatment Gerry Sasanti Nirmala; Diyah Rosiani; Dedi Irawan; Ismail Halim
Scientific Contributions Oil and Gas Vol 48 No 2 (2025)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v48i2.1737

Abstract

The use of electromagnetic heating mechanisms in heavy oil production operations is widely limited in Indonesia. In this context, there is a need for in-depth research regarding the effectiveness of the method. Therefore, this research aimed to discuss the efficacy of heating method through Recovery Factor (RF) analysis using imbibition with electromagnetic waves and the addition of nanopowder. The results showed that the speed of heating and RF imbibition using electromagnetic waves was higher than conventional imbibition. In addition, ferrous oxide nanopowder produced the highest heating speed and RF of 38.39% below the expected value. Further research could be conducted regarding changes in the wettability of rock due to electromagnetic heating and nanopowder required to answer the problem.