(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Penganggaran pecahan minyak menggunakan sistem pintar berbilang /Tuan Sharifah @ Tuan Norhasliza Salleh

Penganggaran pecahan minyak menggunakan sistem pintar berbilang_Tuan Sharifah @ Tuan Norhasliza Salleh_E3_2006_NI
Penganggaran pecahan minyak merupakan salah satu proses yang sangat penting dalam industri petroleum untuk mengetahui pecahan sebenar minyak yang dihasilkan. Rangkaian Neural Buatan (RNB) boleh melakukan proses penganggaran aliran berdasarkan kepada data janaan sistem Tomografi Kemuatan Elektrik (TKE). Penganggaran ini dilakukan secara terus tanpa menjalani proses bina semula imej. Untuk projek ini, sistem RNB yang direkabentuk ialah Multilayer Perceptron (MLP) yang akan digunakan terhadap data-data janaan sistem TKE. Pengaturcaraan Matlab versi 7.0 digunakan untuk merekabentuk MLP. Data hasil janaan TKE dibahagikan kepada 3 set pecahan data iaitu set data latihan, set data pengesahan dan set data pengujian. Penganggar aliran strata dan umum akan dilatih menggunakan data ini. Pengesahan bertujuan untuk memberhentikan proses latihan sekiranya ralat pegesahan meningkat atau malar. Setelah proses latihan tamat, rangkaian neuron terbaik bagi setiap sistem diambil dan diuji dengan satu set data pengujian. Prestasi sistem menunjukkan ralat penganggar aliran strata lebih besar berbanding penganggar umum. Ini bermakna anggaran yang diberikan oleh penganggar umum adalah lebih baik. ______________________________________________________________________________________ Estimation of oil fraction is important to know the actual value of oil production. Artificial neural network (ANNs) are able to be used to estimate parameters of flow processes, based on electrical capacitance–sensed tomographic (ECT) data. The estimations of the parameters are done directly, without recourse to tomographic images. For this project, the architecture of ANN that has been used is the Multilayer Perceptron (MLP). The MLP has been trained with the simulated ECT data. The Matlab version 7 has been used to design the MLP architecture. The simulated ECT data have been divided into 3 sets for training, validation and testing process. Stratified and general estimator were trained with this data. The validation condition has been adopted to stop the training process. After completion of training process, the best network of each system will be tested with a set of testing data for its credibility to estimate oil fraction. The performance shows that the error from the stratified estimator is larger than the general estimator. Meaning that, the estimation made by general estimator is more accurate.
Contributor(s):
Tuan Sharifah @ Tuan Norhasliza Salleh - Author
Primary Item Type:
Final Year Project
Language:
Bahasa Melayu
Subject Keywords:
oil fraction; electrical capacitance–sensed tomographic (ECT); tomographic
First presented to the public:
5/1/2006
Original Publication Date:
1/10/2019
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 75
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2019-01-10 16:30:47.054
Submitter:
Nor Hayati Ismail

All Versions

Thumbnail Name Version Created Date
Penganggaran pecahan minyak menggunakan sistem pintar berbilang /Tuan Sharifah @ Tuan Norhasliza Salleh1 2019-01-10 16:30:47.054