Afandy, Muhammad Arif
(2021)
*Optimisasi Techno Economic Kondisi Operasi Multi-stage Independent Gas Turbine Compressor Dengan Mempertimbangkan Ketidakpastian Proses Menggunakan Algoritma Stokastik.*
Masters thesis, Institut Teknologi Sepuluh Nopember.

Text
Laporan Thesis_02311850017003_Final.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (5MB) | Request a copy |

## Abstract

Centrifugal gas compressors are widely used by the upstream oil and gas industry to deliver hydrocarbon product or gas injections for oil lifting. Saka Indonesia Pangkah Limited (SIPL) is one of the companies that possess Gas Turbine Compressors (GTC) used for Gas Lift and Gas Booster which are configured serially independent through the pipeline’s arrangement. The serial configuration intends to reduce Gas Lift Compressor (GLC) compression ratio in order to increase the injection gas flow rate. The research objective is to determine the optimal operating point of gas compressor, analyze the operating conditions and the economic impact of the compression system by considering process uncertainty. GTC Serial Multistage Independent modeling using Artificial Neural Network (ANN) with Partial Least Square and Pearson methods for pre-processing input/output variable data.

This ANN-based compression system modelling uses Multi Layer Perceptron (MLP) with Finite Impulse Response (FIR) input structure and Lavenberg-Marquardt training algorithm. This model is built on operating data compiled from the actual parameters of the gas turbine and centrifugal compressor unit GLC and 1st Stage Medium Pressure Compressor (MPC-1). The data used for ANN based modeling is 3950, data set is then allocated for training 76% and validation 24%. Analysis and optimization of centrifugal gas compressors serial independent operating conditions using Genetic Algorithm Optimization (GAO) with the objective function of maximum total gas delivery and compressor shaft rotational speed as optimized variables where both compressors operation at stable region as constraint. The best optimization simulation results are obtained in the “Maximum Production and Gas Lift” scenario with the objective function value of total gas delivery 85.10 kg/min and MPC-1 speed setpoints at 11683 RPM and GLC 15160 RPM. Optimization of serial independent compressors operating condition also increasing revenue of natural gas sales in that scenario, where the total income value is 143,434.05 USD/day with a profit against the pre-optimized value of 28,294.89 USD/day.

## Actions (login required)

View Item |