Fast prediction and sensitivity analysis of gas turbine cooling performance using supervised learning approaches

Qi Wang, Li Yang and Kang Huang

Energy, 2022, vol. 246, issue C

Abstract: Fast prediction tools for turbine cooling performance have been demanded by industry for decades to support the iterative design process and the comprehensive response analysis and sensitivity analysis. This study aimed at establishing a comprehensively evaluated deep learning-based data modeling tool for the design of gas turbine blades. The geometry focused on was an air-cooled blade with ribbed channels and film cooling holes, which deformed globally within a wide range of geometrical parameters. A Conditional Generative Adversarial Network was constructed to model the distribution of the internal heat transfer coefficient and the external adiabatic film cooling effectiveness under any in-range geometry and boundary conditions. A series of single-point tests, response analysis, and sensitivity analysis were conducted using the trained model and compared with the Computational Fluid Dynamics results to comprehensively evaluate the model performance. The results showed that the model provided accurate predictions for cooling performance distributions, and also possessed the ability to obtain reasonable response and sensitivity. This study was a successful case of using deep learning approaches to model complex heat transfer problems. For practical applications, the proposed model could serve as an aid to designers to reduce the design burden.

Keywords: Gas turbines; Fast prediction; Sensitivity analysis; Supervised learning (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222002766
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:energy:v:246:y:2022:i:c:s0360544222002766

DOI: 10.1016/j.energy.2022.123373

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

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