| Zugriffsnummer | 54804 |
| Dokumenttyp | Zeitschriftenartikel |
| Peer Review | mit Peer Review |
| Sprache | Englisch |
| Titel | Parametric investigation and optimization of phase change material-based thermal energy storage integrated desiccant coated energy exchanger through physics informed neural networks oriented deep learning approach |
| Autor(in); Institution |
Priyadarshi, Gaurav; NIT Rourkela, Rourkela, INDIA
Murali, Cheepurupalli; NIT Rourkela, Rourkela, INDIA
Naik, Bukke Kiran; NIT Rourkela, Rourkela, INDIA
|
| Quelle/Jahr | Journal of Energy Storage: 80 (2024), 1 - 17 |
| Artikelnummer | 110231 |
| ISSN | 2352-152X |
| DOI | |
| Verlag | Amsterdam: Elsevier |
| Freie Schlagworte | Desiccant coated energy exchanger ; Physics-informed neural network ; Thermal energy storage ; Phase change materials ; Effectiveness ; Adsorption |
| Zusammenfassung | To improve the energy exchange abilities, and to enhance indoor air quality, a desiccant-coated energy exchanger (DCEE) is a capable substitute compared to conventional energy exchangers such as fixed beds and desiccant wheels. Thus, accurately predicting the DCEE's physical characteristics is crucial for enhancing the system's performance. Therefore, in the current study, a novel data-driven modeling methodology utilizing physics informed neural networks (PINNs) is developed to predict the exit parameters of DCEE, like the outlet temperature of cooling water, the outlet temperature of the air, and the outlet-specific humidity of the air. The performance characteristics of DCEE are evaluated using PINN by considering different input parameters. The performance parameters selected for the DCEE performance assessment are dehumidification capacity, thermal coefficient of performance, and heat recovery efficiency. The coated desiccant material chosen for the present study is silica gel. Good agreement is obtained between the PINN and experimental results for both the steady-state and transient cases, proving the PINN method's capability in solving multiple physics-based partial differential equations (PDEs) on a single domain with a maximum discrepancy of ±7.8 %. The developed model is used to obtain the optimal inlet conditions for a given operating condition. Adsorption kinetics of the coated desiccant silica gel revealed that the maximum water uptake capability for the given operating range is 0.345 g.g-1. A case study has been carried out by integrating an industrial waste heat-driven DCEE with a thermal energy storage module (TES) to analyze the energy storage ability during regeneration. A parametric study has been conducted to examine the transfer characteristics of the TES module. Further, the effectiveness of the TES module for five different phase change materials (PCMs) has been assessed. Finally, the seasonal energy efficacy ratio (SEER) of five different PCMs was investigated for 365 days to evaluate year-round performance. The effectiveness of thermal energy storage is maximum for Palmitic acid and minimum for Climsel C48, with corresponding values of 0.73 and 0.37. SEER is the largest for Palmitic acid and lowest for Climsel C48. The values of SEER for Palmitic acid during the summer and winter seasons are 5.489 and 3.31, whereas the values of SEER for Climsel C48 during the summer and winter seasons are 5 and 2.89, respectively. |
| Themenbereich der Metrologie | Metrologie in der Chemie und Stoffeigenschaften |
| Förderinformationen (1) |
Förderername: Indo-German Science & Technology Centre (IGSTC)
Förderer ID: 0000 0005 0269 1690 Förderer ID Typ: ISNI Förderprogramm: IGSTC-PECFAR-2022 Förderungsnummer: IGSTC/PECFAR/Call 2022/BKN-SA/40/2022-23/Decision letter/481 (https://www.igstc.org/) |
Zitierung
Priyadarshi, G., Murali, C., Agarwal, S., & Naik, B. K. (2024). Parametric investigation and optimization of phase change material-based thermal energy storage integrated desiccant coated energy exchanger through physics informed neural networks oriented deep learning approach. Journal of Energy Storage, 80, 1–17. https://doi.org/10.1016/j.est.2023.110231