IMASULY, GEOVANNY BRANCHINY (2024) PENERAPAN MACHINE LEARNING (DECISION TREE) DALAM PENENTUAN KANDIDAT REAKTIVASI IDLE WELL PADA PT. PERTAMINA EP REGIONAL 4 ZONA 11 LAPANGAN CEPU. Masters thesis, UPN Veteran Yogyakarta.
![[thumbnail of Cover.pdf]](http://eprints.upnyk.ac.id/style/images/fileicons/text.png) |
Text
Cover.pdf Download (138kB) |
|
Text
DAFTAR ISI.pdf Download (125kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (99kB) |
|
Text
Lembar Pengesahan.pdf Download (69kB) |
|
Text
Ringkasan (Abstrak).pdf Download (43kB) |
|
Text
TESIS (Geovanny Branchiny Imasuly-213221005) revisi (1).pdf Restricted to Repository staff only Download (8MB) |
Abstract
RINGKASAN
Indonesia memiliki tantangan berat dengan misi mewujudkan produksi
minyak sebesar 1 juta barel per hari pada tahun 2030, dengan mengandalkan
lapangan-lapangan tua atau mature (brownfield) yang mengupayakan eksploitasi
hidrokarbon tersisa. Salah satu targetnya adalah reaktivasi idle well pada PT.
Pertamina EP Regional 4 zona 11 lapangan Cepu, maka dilakukan pengembangan
riset dan inovasi yang berfokus pada produksi idle well.
Dalam penilitian ini dilakukan penentuan kandidat reaktivasi idle well.
Tahapan pertama yang di lakukan adalah menetapkan masalah untuk pemahaman
terhadap faktor-faktor yang mempengaruhi idle well, dan informasi tentang
perkembangan terkini dalam memprediksi penentuan kandidat reaktivasi idle well.
Pengumpulan data berupa dokumen primer dan sekunder tahun 2018-2023. Tahap
selanjutnya diterapkan Machine Learning (ML) (Decission Tree (DT)) untuk dapat
mengatasi masalah akurasi dan kompleksitas data, serta membuat pola klasfikasi
yang efisien dan akurat, maka dikembangkan Web Application yang dapat
membantu pengambil keputusan dalam menentukan sumur mana yang harus
direaktivasi yang dapat memberikan solusi terbaik untuk permasalahan peningkatan
perolehan minyak.
Hasil penelitian menunjukan tingkat keberhasilan yang tinggi pada Accuracy
Under Curve (AUC) dan Receiver Operating Curve (ROC) sebesar 0.99 yang
menunjukkan bahwa model klasifikasi memiliki probabilitas tinggi, dengan
menggunakan entropy didapatkan 2 sumur potential untuk di reaktivasi berdasarkan
Lifting method (ESP) yaitu sumur NGL-P-001 dan TPN-004 dengan Well Cum
Prod (Np, MBO) (107.89 dan 132.570 MBO) dan HC Remaining Potential (Oil,
MBO) (4.609 dan 52.42 MBO), dengan rekomendasi perbaikan yaitu Well Service.
Dari dua sumur yang memenuhi kriteria reaktivasi berdasarkan model decision tree,
maka dilakukan evaluasi Chan Diagnostic yang dimana pada sumur TPN-004
terjadi masalah Normal Displacement with High WOR dan Near Wellbore Water
Channeling. Well Production Performance dengan periode produksi 5 tahun (2018-
2022), dan Decline Curve Analysis (DCA) dimana semakin rendah MSE maka
semakin baik kecocokannya dan model Hyperbolic dan Stretched Exponential yang
menghasilkan nilai terendah sebesar 1106.6 dan 1142.35, sehingga menunjukkan
bahwa model tersebut mungkin paling sesuai di antara model-model yang
dipertimbangkan. Pada hasil dari forecast production rate vs cumulative oil
production digunakan untuk memprediksi produksi minyak di masa depan, dan
didapatkan cumulative oil sebesar 4451.22 BBL.
Keyword: Machine Learning, Reaktivasi, Idle Well, Decision Tree, Peningkatan
Perolehan Minyak
ABSTRACT
Indonesia has a tough challenge with realizing oil production of 1 million
barrels per day by 2030 by relying on old fields or mature (brownfield), which seeks
to exploit the remaining hydrocarbons. One of the targets is the reactivation of idle
wells at PT. Pertamina EP Regional 4 zone 11 Cepu field, research and innovation
development focused on production is carried out idle well.
In this research, reactivation candidates were determined to idle well. The
first stage is to define the problem to understand the influencing factors of idle well
and information about recent developments in predicting the determination of
reactivation candidates. Data collection in the form of primary and secondary
documents for 2018-2023. The next stage is implementing Machine Learning (ML)
(Decision Tree (DT)) to be able to overcome the problems of data accuracy and
complexity, as well as create efficient and accurate classification patterns, a Web
Application which can help decision-makers in determining which wells should be
reactivated which can provide the best solution to the problem of increasing oil
recovery.
The research results show a high success rate on Accuracy Under Curve
(AUC) and Receiver Operating Curve (ROC), amounting to 0.99 which shows that
the classification model has a high probability, using entropy two potential wells
were obtained for reactivation based on Lifting method (ESP) namely wells NGL-
P-001 and TPN-004 with Well Cum Prod (Np, MBO) (107.89 then 132.570 MBO)
then HC Remaining Potential (Oil, MBO) (4,609 and 52.42 MBO), with
recommendations for improvement, namely Well Service. Of the two wells that
meet the reactivation criteria based on the model decision tree, an evaluation is
carried out by Chan Diagnostic, where a problem occurred in the TPN-004 well
Normal Displacement with High WOR and Near Wellbore Water Channeling. Well,
Production Performance with a five-year production period (2018-2022) and
Decline Curve Analysis (DCA) where the lower the MSE, the better the fit and
model Hyperbolic and Stretched Exponential, which yielded the lowest values of
1106.6 and 1142.35, thus indicating that the model may be the best fit among the
models considered. The results of forecast production rate vs cumulative oil
production were used to predict future oil production and cumulative oil amounting
to 4451.22 BBL was obtained.
Keywords: Machine Learning, Reactivation, Idle Well, Decision Tree, Increased
Oil Recovery
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Machine Learning, Reactivation, Idle Well, Decision Tree, Increased Oil Recovery |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Engineering Sciences |
| Depositing User: | Eko Yuli |
| Date Deposited: | 28 May 2024 04:35 |
| Last Modified: | 28 May 2024 04:35 |
| URI: | http://eprints.upnyk.ac.id/id/eprint/39521 |
Actions (login required)
 |
View Item |