A novel physical information neural network for real-time monitoring and sparse reconstruction of thermal environments with turbulent natural convection in nacelles

Zhenhuan Zhang, Yutian Hou and Yuan Yuan

Renewable Energy, 2025, vol. 240, issue C

Abstract: As wind turbine power increases, the heat loss from components within the nacelle can lead to localized overheating, adversely affecting both performance and lifespan. This issue can be addressed by real-time reconstruction of the thermal environment, focusing on pre-structural design and post-control maintenance. However, the instability and strong nonlinearity of the thermal conditions inside the nacelle pose significant challenges for existing reconstruction methods to accurately capture these physical properties. This study proposes a generalized Physics-Informed Neural Network (PINN) framework that optimizes computational efficiency, reconstruction accuracy, sensor utilization, and model generalizability. The results demonstrate the effectiveness of the proposed network in addressing these challenges.

Keywords: Thermal environments with turbulent natural convection; Physical information neural network; Adaptive sampling; Transfer learning acceleration (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148124022341
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:240:y:2025:i:c:s0960148124022341

DOI: 10.1016/j.renene.2024.122166

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().