An optimization approach for improving steam production of heat recovery steam generator
Abstract The heat recovery steam generator (HRSG) is a critical component of a combined cycle power plant, linking the gas turbine to the steam cycle. Optimizing the parameters affecting HRSG’s steam outputs is critical for the design of combined cycle plants to maximize steam cycle efficiency. Howe...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87715-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract The heat recovery steam generator (HRSG) is a critical component of a combined cycle power plant, linking the gas turbine to the steam cycle. Optimizing the parameters affecting HRSG’s steam outputs is critical for the design of combined cycle plants to maximize steam cycle efficiency. However, detailed optimization of the HRSG is a difficult task due to numerous parameters. Consequently, this paper aims to explore the impact of the parameters affecting the HRSG’s ability to generate steam. In addition, response surface methodology and artificial neural network are used to build a mathematical relation between the steam production and the input parameters with the aim to determine the optimal values of the parameters to maximize steam production. The proposed models are effectively constructed and tested using real datasets. The findings revealed that the most parameters affecting steam production include high-pressure (HP) feed gas flow, HP feed gas pressure, and the interaction between low-pressure (LP) feed gas pressure, and HP feed gas flow. In addition, the results showed that the interaction between the input parameters and the quadratic terms have a significant impact. The results also indicated that the proposed models for both approaches predict the future of steam production with an accuracy of 99%. The results also showed that the proposed model selects and provides the optimal HRSG parameter values to maximize steam production within the relevant defined constraints. |
|---|---|
| ISSN: | 2045-2322 |