TY - GEN
T1 - The simulation model of API oil separator based on artificial neural network at Pt Saka Indonesia Pangkah limited
AU - Pratama, I. Putu Eka Widya
AU - Soehartanto, Totok
AU - Darmaatmaja, Abdussalam
AU - Mujiyanti, Safira Firdaus
N1 - Publisher Copyright:
© 2023 Author(s).
PY - 2023/5/22
Y1 - 2023/5/22
N2 - The research was designed an artificial neural network (ANN) to predict the output of API oil Separator at PT Saka Indonesia Pangkah Limited. This ANN has a feedforward structure and uses a Levenberg-Marquardt algorithm. It has three input nodes in the input layer of pH, temperature, and total suspended solids (TSS), one output node (TSS) in the output layer, and a hidden node that varies until twenty hidden layers. The simulation result shows that the best value of root mean square error (RMSE) lies in a neural network of 3-9-1 structure (Input layer-Hidden layer-Output layer) with a value of 32.65. Also, our ANN structure has a good result in estimating TSS output of the API Separator with a value of 14.16 - 169.12 mg/l compared to the output data of the API Separator in the range of 18 - 136 mg/l.
AB - The research was designed an artificial neural network (ANN) to predict the output of API oil Separator at PT Saka Indonesia Pangkah Limited. This ANN has a feedforward structure and uses a Levenberg-Marquardt algorithm. It has three input nodes in the input layer of pH, temperature, and total suspended solids (TSS), one output node (TSS) in the output layer, and a hidden node that varies until twenty hidden layers. The simulation result shows that the best value of root mean square error (RMSE) lies in a neural network of 3-9-1 structure (Input layer-Hidden layer-Output layer) with a value of 32.65. Also, our ANN structure has a good result in estimating TSS output of the API Separator with a value of 14.16 - 169.12 mg/l compared to the output data of the API Separator in the range of 18 - 136 mg/l.
KW - API Separator
KW - Artificial Neural Network (ANN)
KW - Total Suspended Solids (TSS)
UR - http://www.scopus.com/inward/record.url?scp=85161578193&partnerID=8YFLogxK
U2 - 10.1063/5.0122310
DO - 10.1063/5.0122310
M3 - Conference contribution
AN - SCOPUS:85161578193
T3 - AIP Conference Proceedings
BT - Engineering Physics International Conference 2021, EPIC 2021
A2 - Tenggara, Ayodya Pradhipta
A2 - Siddiq, Nur Abdillah
A2 - Pinasti, Sita Gandes
A2 - Insyani, Rizki
A2 - Kurnia, Jundika Candra
A2 - Saha, Geetali
A2 - Moradi-Dastjerdi, Rasool
PB - American Institute of Physics Inc.
T2 - 3rd Engineering Physics International Conference, EPIC 2021
Y2 - 24 August 2021 through 25 August 2021
ER -