UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya
Kampus ITS Sukolilo - Surabaya 60111
Phone
:
031-5921733 , 5923623
Fax
:
031-5937774
E-mail
:
libits@its.ac.id
Website
:
http://library.its.ac.id
Support (Customer Service) :
timit_perpus@its.ac.id
Welcome..guys!
Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT
Moh. Fandika Aqsa
Davi Wahyuni
Tondo Indra Nyata
Anis Wulandari
Ansi Aflacha
ITS » Paper and Presentation » S2 - Teknik Fisika Posted by tondoindra@gmail.com at 07/03/2016 15:50:37 • 734 Views
PERANCANGAN ESTIMATOR KANDUNGAN CRUDE OIL GAS OIL WATER PADA WELLHEAD PLATFORM BERBASIS JARINGAN SYARAF TIRUAN JST
ESTIMATOR DESIGN CRUDE OIL CONTENT GAS OIL WATER AT WELLHEAD PLATFORM BASED ON ARTIFICIAL NEURAL NETWOR
Author : BUDI, AGUS SULISTYO ( 2412201703 )
ABSTRAK
Pengukuran crude oil gas oil water saat ini menggunakan vessel separator
dan indikator di lokal yang mana digunakan untuk mengetahui flow rate dari masingmasing
fase nya. Kelemahan dari sistem ini adalah biaya instalasi dan pemeliharaan
yang tinggi serta operator lambat dalam mengetahui kandungan crude oil dari sumur
karena harus mendatangi platform untuk bisa mengetahui kandungan crude oil
tersebut.
Dalam penelitian ini digunakan perancangan model Jaringan Syaraf Tiruan
JST untuk mengestimasi kandungan crude oil. Variabel masukan yang digunakan
pada JST ini adalah flowrate total Q total tekanan masukan 1 P1 separator
tekanan masukan 2 P2 separator dan temperatur T sedangkan variabel pada
keluaran adalah flowrate gas Qg flowrate oil Qo dan flowrate water Qw.
Metode perancangan ini menggunakan struktur Multi Layer Perceptron MLP
dengan alogaritma pembelajaran Lavenberg Marquardt serta menggunakan 3 layer
yaitu untuk layer pertama adalah layer masukan terdiri dari 4 node layer kedua
adalah layer tersembunyi terdiri dari 4 layer tersembunyi dan ketiga yaitu layer
keluaran terdiri dari 3 node.
Hasil simulasi dari perancangan pemodelan JST ini menghasilkan nilai MSE
Mean Square Error sebesar 3.29E-10 dan nilai VAF Variance Accounted For
yaitu 98.8.
ABSTRACT
Measurement of crude oil gas oil water is currently using the separator
vessel and local indicators which are used to determine the flow rate of each of its
phases. The downside of this system is the cost of installation and high
maintenance as well as slow the operators know the content of crude oil because
they have to come to the platform without the occupant to be able to know the
content of the crude oil.
In this study the design model of Artificial Neural Network ANN to
estimate the content crude oil. Input variables used in this ANN is the flowrate
total Q total input pressure 1 P1 separator input pressure 2 P2 separator and
temperature T while the output variables are flowrate gas Qg flowrate oil
Qo and flowrate water QW. This design method using Multi Layer Perceptron
structure MLP with Lavenberg Marquardt learning algorithm and using 3
layers namely for the first layer is the input layer consists of 4 nodes the second
layer is a hidden layer consisting of four hidden layer and the third layer is the
output consists of 3 nodes.
The simulation result of the design of the ANN modeling is to produce a
value of MSE Mean Square Error is 3.29E-10 and the value of VAF Variance
Accounted For is 98.8 .
Keywords:
separator, Jaringan Syaraf Tiruan (JST), multi layer perceptron,
Lavenberg Marquadt
Subject
: Jaringan Komputer
Contributor
Dr. Ir. Aulia Siti Aisjah, M.T.
Totok Ruki Biyanto, S.T. ,M.T.,Ph.D
Date Create
: 07/03/2016
Type
: Text
Format
: PDF
Language
: Indonesian
Identifier
: ITS-paper-24121150008628
Collection ID
: 24121150008628
Call Number
: RTF 006.32 Bud p
Source Paper And Presentation Of Physics Engineering RTF 006.32 Bud p, 2016
Coverage ITS Community
Rights Copyright @2016 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library