TY - GEN
T1 - Analysis of heat recovery steam generator performance through simulation based on artificial neural network
AU - Aisyah, Putri Y.
AU - Soehartanto, Totok
AU - Noriyati, Ronny D.
AU - Chilmi, Furoidah
N1 - Publisher Copyright:
© 2023 Author(s).
PY - 2023/5/22
Y1 - 2023/5/22
N2 - The exhaust heat generated by the Gas Power Plant has a high value of around 500°C. The high exhaust heat temperature can be utilized by Heat Recovery Steam Generator (HRSG) to make superheated steam. HRSG has three main components: economizer, evaporator, and superheater. Artificial Neural Network-based Analysis Method can be used to determine the efficiency of HRSG without the inlet and outlet data of each component. Efficiency analysis is based on Mean Square Error (MSE) values obtained from Artificial Neural Network Method applied. The Neural Network is considered good if the MSE value is small, because the smaller MSE value is closer to the regression. From the research that has been done, the application of the Artificial Neural Network Analysis Method on HRSG obtained an MSE value around 10-3 - 10-4 with a regression value of about 0,9. Based on the MSE value obtained, it can be concluded that the modeling of the Artificial Terms Network on the HRSG can be a good estimator.
AB - The exhaust heat generated by the Gas Power Plant has a high value of around 500°C. The high exhaust heat temperature can be utilized by Heat Recovery Steam Generator (HRSG) to make superheated steam. HRSG has three main components: economizer, evaporator, and superheater. Artificial Neural Network-based Analysis Method can be used to determine the efficiency of HRSG without the inlet and outlet data of each component. Efficiency analysis is based on Mean Square Error (MSE) values obtained from Artificial Neural Network Method applied. The Neural Network is considered good if the MSE value is small, because the smaller MSE value is closer to the regression. From the research that has been done, the application of the Artificial Neural Network Analysis Method on HRSG obtained an MSE value around 10-3 - 10-4 with a regression value of about 0,9. Based on the MSE value obtained, it can be concluded that the modeling of the Artificial Terms Network on the HRSG can be a good estimator.
UR - http://www.scopus.com/inward/record.url?scp=85161587998&partnerID=8YFLogxK
U2 - 10.1063/5.0122817
DO - 10.1063/5.0122817
M3 - Conference contribution
AN - SCOPUS:85161587998
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 -