Utami, Erna (2017) Prediksi Zona Reservoir Berbasis Atribut Data Log Sumur Dengan Metode Levenberg - Marquardt. Masters thesis, Institut Teknologi Sepuluh Nopember Surabaya.
Preview |
Text
2215206702-Master_Theses.pdf - Published Version Download (2MB) | Preview |
Abstract
Dalam meningkatkan produksi minyak bumi salah satu cara dengan memperbanyak eksplorasi pada lapangan baru. Metode yang cukup efektif digunakan dalam eksplorasi minyak dan gas bumi adalah metode well logging. Metode well logging merupakan suatu metode perolehan data yang diperlukan untuk mengevaluasi secara kualitatif dan kuantitatif adanya keberadaan hidrokarbon. Di penelitian ini, menggunakan hubungan kualitatif antara data logging sumur dengan zona reservoir di basin Salawati, Irian Jaya area. Empat log sumur sebagai atribut data input diantaranya Log Gamma Ray (GR), Log Resistivity (ILD), Log Densitas (RHOB), Log Neutron (NPHI). Sedangkan formasi zona reservoir dijadikan sebagai data target yang telah diinterpretasi sebelumnya terhadap kurva log. Pada dasarnya data logging sangat kompleks dan tidak linier, sehingga pada proses pelatihan dan pengujian digunakan metode Levenberg - Marquardt. Karena metode levenberg – marquardt merupakan salah satu metode optimasi untuk penyelesaian masalah kuadrat terkecil.
Hasil penelitian ini menunjukkan bahwa hasil training prediksi zona reservoir dengan metode levenberg – marquardt mempunyai nilai Mean Absolute Percentage Error (MAPE) sebesar 0.3803% dengan 500 iterasi. Uji Validasi hasil berdasarkan kurva ROC dengan cross validation folds 10 diperoleh akurasi sebesar 84.9984%. Dengan Area Under ROC sebesar 0.992. Dari nilai area under ROC tersebut, maka dapat dikatakan bahwa prediksi zona reservoir dengan metode levenberg – marquardt mempunyai unjuk kerja “Excellent”. Oleh sebab itu, daerah yang memiliki respon atribut yang sama dengan lapangan yang telah berproduksi, diperkirakan sebagai zona prospek baru reservoir.
Kata kunci: Prediksi zona reservoir, data log sumur, Neural Network di Minyak dan Gas, Algoritma Levenberg - Marquardt
=========================================================
=========================================================
Well logging is a well-known and effective method for oil and natural gas exploration in new fields in order to enhance oil and gas production. Well Logging is defined as an acquisition method to qualitatively and quantitatively evaluate the existence of hydrocarbon layer in the well. In this research, we studied the relations between well logging data and reservoir zone in Salawati basin, Irian Jaya area. Four well logs with four attributes such as Log Gamma Ray (GR), Log Resistivity (ILD), Log Density (RHOB), and Log Neutron (NPHI) were explored. The reservoir zone data has been previously determined by using log curve whether it is a reservoir zone or not. This data then is being used as a target for learning. Since the logging data is a complex and non-linear, Levenberg-Marquardt (LM) was then implemented as an artificial intelligent algorithm in performing this study. The objective of this work is to build decision support system that will automatically find reservoir zone based on well logging data.
The results of this work showed that Mean Absolute Percentage Error (MAPE) of training for reservoir zone prediction by exploiting Levenberg – Marquardt is 0.3803 % with 500 iteration. Validity test results based on ROC curve with cross validation folds 10 is 84.9984% and area of under ROC is 0.992. This result showed that this method has a high potential to be used in real exploration activities so that the predicting reservoir zone then can be done precisely.
Key words: Reservoir zone prediction, well logging data, Neural Network in oil and gas, Levenberg–Marquardt algorithm.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Kata kunci: Prediksi zona reservoir, data log sumur, Neural Network di Minyak dan Gas, Algoritma Levenberg - Marquardt ======================================================== Key words: Reservoir zone prediction, well logging data, Neural Network in oil and gas, Levenberg–Marquardt algorithm. |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms |
| Divisions: | Faculty of Industrial Technology > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | Erna Utami Utami |
| Date Deposited: | 10 Jul 2017 07:21 |
| Last Modified: | 05 Mar 2019 02:09 |
| URI: | http://repository.its.ac.id/id/eprint/41867 |
Actions (login required)
 |
View Item |