Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods
Supercritical CO2 (sCO2) stands out for concentrating solar power (CSP) due to its superior thermophysical and chemical properties, promising higher cycle efficiency compared to superheated or supercritical steam. Leveraging the waste heat from sCO2 cycles through the organic Rankine cycle (ORC) as...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-05-01
|
| Series: | International Journal of Thermofluids |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666202724000545 |
| _version_ | 1827228859575042048 |
|---|---|
| author | Asif Iqbal Turja Khandekar Nazmus Sadat Md. Mahmudul Hasan Yasin Khan Md. Monjurul Ehsan |
| author_facet | Asif Iqbal Turja Khandekar Nazmus Sadat Md. Mahmudul Hasan Yasin Khan Md. Monjurul Ehsan |
| author_sort | Asif Iqbal Turja |
| collection | DOAJ |
| description | Supercritical CO2 (sCO2) stands out for concentrating solar power (CSP) due to its superior thermophysical and chemical properties, promising higher cycle efficiency compared to superheated or supercritical steam. Leveraging the waste heat from sCO2 cycles through the organic Rankine cycle (ORC) as a low-grade energy source enhances overall thermal efficiency. This research explores advanced sCO2 power cycles and introduces a novel approach by integrating machine learning and genetic algorithms for optimizing cycle performance. Utilizing a thermodynamic model-derived dataset, various machine learning algorithms, including Random Forest, XGBoost, and Artificial Neural Network are employed for prediction, evaluation and optimization. This innovative integration enables a comprehensive understanding of the complex dynamics of sCO2 power cycles. Subsequently, the study employs multi-objective optimization for the systematic evaluation and optimization of the combined power cycles, incorporating multiple bottoming cycles to maximize efficiency. The findings not only showcase the superiority of the unified sCO2ORC cycle but also emphasize the impact of integrating advanced computational methods in achieving optimal performance. The sCO2 cycle is explored in recompression, partial cooling, and main compression intercooling configurations. Recompression cycles utilize a single cooling system, while partial cooling and main compression intercooling layouts integrate a pair of ORCs at two precoolers. The ORC cycle enhances the recompression cycle through heat recuperation, extracting enhanced power originating from the bottom cycle. Critical parameters are taken into consideration to carry out optimization and performance evaluations. such as cycle temperatures, recuperator effectiveness, bottoming cycle pressure ratio, and condensation temperature. Results indicate that the combined partial cooling sCO2ORC cycle yields the optimal net output power of 7994.541 kW and thermal efficiency of 53.365 %. The findings highlight the capacity to propel and promote the utilization of waste heat recovery in energy technologies through enhanced and optimized power cycle designs, contributing to their advancement and widespread adoption. |
| first_indexed | 2024-03-07T22:00:15Z |
| format | Article |
| id | doaj.art-9512dac7c6aa4fc0bdfb182761312102 |
| institution | Directory Open Access Journal |
| issn | 2666-2027 |
| language | English |
| last_indexed | 2025-03-21T18:20:33Z |
| publishDate | 2024-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Thermofluids |
| spelling | doaj.art-9512dac7c6aa4fc0bdfb1827613121022024-06-09T05:29:36ZengElsevierInternational Journal of Thermofluids2666-20272024-05-0122100612Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning MethodsAsif Iqbal Turja0Khandekar Nazmus Sadat1Md. Mahmudul Hasan2Yasin Khan3Md. Monjurul Ehsan4Department of Mechanical and Production Engineering (MPE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, BangladeshDepartment of Mechanical and Production Engineering (MPE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, BangladeshDepartment of Mechanical and Production Engineering (MPE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, BangladeshDepartment of Mechanical and Production Engineering (MPE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, BangladeshCorresponding author.; Department of Mechanical and Production Engineering (MPE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, BangladeshSupercritical CO2 (sCO2) stands out for concentrating solar power (CSP) due to its superior thermophysical and chemical properties, promising higher cycle efficiency compared to superheated or supercritical steam. Leveraging the waste heat from sCO2 cycles through the organic Rankine cycle (ORC) as a low-grade energy source enhances overall thermal efficiency. This research explores advanced sCO2 power cycles and introduces a novel approach by integrating machine learning and genetic algorithms for optimizing cycle performance. Utilizing a thermodynamic model-derived dataset, various machine learning algorithms, including Random Forest, XGBoost, and Artificial Neural Network are employed for prediction, evaluation and optimization. This innovative integration enables a comprehensive understanding of the complex dynamics of sCO2 power cycles. Subsequently, the study employs multi-objective optimization for the systematic evaluation and optimization of the combined power cycles, incorporating multiple bottoming cycles to maximize efficiency. The findings not only showcase the superiority of the unified sCO2ORC cycle but also emphasize the impact of integrating advanced computational methods in achieving optimal performance. The sCO2 cycle is explored in recompression, partial cooling, and main compression intercooling configurations. Recompression cycles utilize a single cooling system, while partial cooling and main compression intercooling layouts integrate a pair of ORCs at two precoolers. The ORC cycle enhances the recompression cycle through heat recuperation, extracting enhanced power originating from the bottom cycle. Critical parameters are taken into consideration to carry out optimization and performance evaluations. such as cycle temperatures, recuperator effectiveness, bottoming cycle pressure ratio, and condensation temperature. Results indicate that the combined partial cooling sCO2ORC cycle yields the optimal net output power of 7994.541 kW and thermal efficiency of 53.365 %. The findings highlight the capacity to propel and promote the utilization of waste heat recovery in energy technologies through enhanced and optimized power cycle designs, contributing to their advancement and widespread adoption.http://www.sciencedirect.com/science/article/pii/S2666202724000545Supercritical co2Organic rankineWaste heatCritical pointParametric AnalysisThermal Analysis |
| spellingShingle | Asif Iqbal Turja Khandekar Nazmus Sadat Md. Mahmudul Hasan Yasin Khan Md. Monjurul Ehsan Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods International Journal of Thermofluids Supercritical co2 Organic rankine Waste heat Critical point Parametric Analysis Thermal Analysis |
| title | Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods |
| title_full | Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods |
| title_fullStr | Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods |
| title_full_unstemmed | Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods |
| title_short | Waste Heat Recuperation in Advanced Supercritical CO2 Power Cycles with Organic Rankine Cycle Integration & Optimization Using Machine Learning Methods |
| title_sort | waste heat recuperation in advanced supercritical co2 power cycles with organic rankine cycle integration amp optimization using machine learning methods |
| topic | Supercritical co2 Organic rankine Waste heat Critical point Parametric Analysis Thermal Analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2666202724000545 |
| work_keys_str_mv | AT asifiqbalturja wasteheatrecuperationinadvancedsupercriticalco2powercycleswithorganicrankinecycleintegrationampoptimizationusingmachinelearningmethods AT khandekarnazmussadat wasteheatrecuperationinadvancedsupercriticalco2powercycleswithorganicrankinecycleintegrationampoptimizationusingmachinelearningmethods AT mdmahmudulhasan wasteheatrecuperationinadvancedsupercriticalco2powercycleswithorganicrankinecycleintegrationampoptimizationusingmachinelearningmethods AT yasinkhan wasteheatrecuperationinadvancedsupercriticalco2powercycleswithorganicrankinecycleintegrationampoptimizationusingmachinelearningmethods AT mdmonjurulehsan wasteheatrecuperationinadvancedsupercriticalco2powercycleswithorganicrankinecycleintegrationampoptimizationusingmachinelearningmethods |