Claim Missing Document
Check
Articles

Found 23 Documents
Search

Application of PCA and Machine Learning for Predicting Oil Measurement Discrepancies in Custody Transfer Systems: Understanding from an Indonesian Mature Onshore Facility Fadly, Wan; Hidayat, Fiki; Abu, Noratikah; Afdhol, Muhammad Khairul; Putra, Dike; Mulyandri
Scientific Contributions Oil and Gas Vol 48 No 4 (2025)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v48i4.404

Abstract

Oil measured volume discrepancies in custody transfer systems is becoming a persistent challenge, which is often caused by complex thermal, hydraulic, and compositional interactions. Therefore, this study aimed to introduce a data-driven framework incorporating Principal Component Analysis (PCA) and machine learning (ML) to identify as well as predict discrepancies at a representative onshore gathering station (GS) in Indonesia (Field-X). Major operational parameters, including gross volume, unallocated net oil, pressure, temperature, and Basic Sediment & Water (BS&W), were analyzed to assess the impact on volumetric imbalance. During the analysis, PCA reduced 64 correlated variables to five principal components, explaining 95% of the total variance and showing gross volume, pressure, and temperature as dominant factors. Four ML models, namely XGBoost, Random Forest, Support Vector Regression, and ElasticNet, were trained as well as validated with three-fold time series cross-validation for temporal robustness. Incorporating PCA significantly improved predictive performance, with Support Vector Regression showing the largest R² increase (from –0.0082 to 0.82). Results signified that discrepancies were primarily governed by thermodynamic shrinkage, temperature changes, and BS&W-related metering errors. In addition, the proposed PCA–ML framework offered an interpretable, reliable method for early detection and mitigation of oil volume discrepancies in complex production environments.
Biopolimer dari Bahan Organik sebagai Biopolimer pada Metode EOR Fitra Ayu Lestari; Muhammad Khairul Afdhol; Hidayat Fiki; Erfando Tomi
Lembaran publikasi minyak dan gas bumi Vol 54 No 3 (2020)
Publisher : BBPMGB LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/LPMGB.54.3.568

Abstract

Rendahnya area sweep efficiency selama waterflooding merupakan salah satu masalah dalam meningkatkan produksi minyak. Sweep efficiency waterflood  kurang efektif dikarenakan permeabilitas air yang besar di batuan. Viskositas air bisa meningkat jika menambahkan polimer pada air sehingga bisa mengurangi permeabilitas air dibatuan. Injeksi polimer cukup menjanjikan untuk meningkatkan produksi minyak. Biopolimer merupakan salah satu jenis polimer yang berasal dari mahkluk hidup dengan komponen utama penyusunnya adalah karbohidrat. Bahan yang sering dijadikan biopolimer dan terdapat banyak di alam adalah polisakarida. Untuk mendapatkan polisakarida maka dilakukan ekstraksi pada bahan yang digunakan. Ekstraksi yang digunakan memiliki banyak jenis yang akan mempengaruhi biopolimer yang terbentuk. Pada review ini, berbagai aspek biopolimer dibahas mulai dari sumber biopolimer, jenis ekstraksi, dan serta uji reologi biopolimer.
Optimization of Chemicaly Activated Candlenut and Walnut Shell Biosorbents for Produced Water Purification Within an Iot-Based Monitoring System Muhammad Khairul Afdhol; Rika Lala Saputri; Mursyidah; Fiki Hidayat; Tomi Erfando; Ari Prasetyo; Adiella Zakky Juneid
Scientific Contributions Oil and Gas Vol 49 No 2 (2026)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v49i2.1972

Abstract

Produced water from petroleum operations contains high levels of hydrocarbons, suspended solids, and dissolved contaminants that must be treated before discharge or reuse. This study aims to optimize biosorbents derived from candlenut and walnut shells through chemical activation using potassium hydroxide (KOH) for the purification of produced water. In addition, an Internet of Things (IoT)-based monitoring system was integrated to enable real-time assessment of water quality parameters. The biosorbents were characterized using Fourier Transform Infrared Spectroscopy (FTIR) and Scanning Electron Microscopy (SEM) to identify surface functional groups and morphological modifications. Experimental evaluations of turbidity, bulk density, and total dissolved solids (TDS) were conducted under various operating conditions. The activated biosorbents exhibited enhanced hydroxyl and carboxyl functional groups, as confirmed by FTIR, with an optimal bulk density of 0.76 g/cm³. Under optimum conditions (pH 7, contact time 90 min, adsorbent dosage 15 g/L), turbidity and TDS removals reached 80% and 75%, respectively. The IoT system successfully enabled real-time data acquisition and process monitoring, ensuring operational reliability. The maximum adsorption capacity based on the Langmuir model reached 33.8 mg/g for KOH-activated walnut and 31.2 mg/g for candlenut biosorbent. Overall, the chemically activated candlenut and walnut biosorbents demonstrated excellent adsorption capacity and potential for sustainable produced water treatment. This approach offers an environmentally friendly and cost-effective solution by utilizing local biomass waste integrated with modern IoT-based control technologies. Adsorption behavior was further evaluated using Langmuir/Freundlich isotherm and kinetic models.