Serviceeinschränkungen vom 12.-22.02.2026 - weitere Infos auf der UB-Homepage

Treffer: Data-driven nonlinear modeling for superheating degree in organic Rankine cycle systems

Title:
Data-driven nonlinear modeling for superheating degree in organic Rankine cycle systems
Source:
In proceedings of the 8th International Seminar on ORC Power Systems, 10 (2025-09-11); 8th International Seminar on ORC Power Systems, Lappeenranta, Finland [FI], 9 - 11 september
Publisher Information:
KORC, 2025.
Publication Year:
2025
Document Type:
Konferenz conference paper<br />http://purl.org/coar/resource_type/c_5794<br />conferenceObject<br />peer reviewed
Language:
English
Rights:
open access
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
Accession Number:
edsorb.336124
Database:
ORBi

Weitere Informationen

Organic Rankine Cycle (ORC) power systems have become a promising solution for improving energyefficiency, particularly in waste heat recovery (WHR) applications. These systems convert low-gradeheat into electricity, contributing to energy savings and emission reductions. A key control objective isthe regulation of the superheating degree, as it directly affects thermodynamic performance and systemreliability. This work explores a data-driven modeling strategy using neural networks (NNs) to capturethe nonlinear dynamics of the superheating process in a small-scale (11 kWel) ORC unit. To enhancegeneralization and interpretability, an automatic feature selection framework based on reinforcementlearning is developed. The approach evaluates the relevance of multiple candidate input variables, selectingthe most informative ones to optimize predictive accuracy. Experimental results show that theproposed model effectively reproduces system behavior while maintaining strong generalization to unseenoperating conditions. This modeling framework lays the foundation for advanced control developmentand contributes to data-driven methodologies for energy systems optimization
7. Affordable and clean energy