Current turbulent heat flux models fail to predict accurate temperature distributions in film cooling flows. The present paper focuses on a machine learning (ML) approach to this problem, in which the gradient diffusion hypothesis (GDH) is used in conjunction with a data-driven prediction for the turbulent diffusivity field αt. An overview of the model is presented, followed by validation against two film cooling datasets. Despite insufficiencies, the model shows some improvement in the near-injection region. The present work also attempts to interpret the complex ML decision process, by analyzing the model features and determining their importance. These results show that the model is heavily reliant of distance to the wall d and eddy viscosity νt, while other features display localized prominence.
Skip Nav Destination
Article navigation
January 2019
Research-Article
Physical Interpretation of Machine Learning Models Applied to Film Cooling Flows
Pedro M. Milani,
Pedro M. Milani
Mechanical Engineering Department,
Stanford University,
Stanford, CA 94305
e-mail: pmmilani@stanford.edu
Stanford University,
Stanford, CA 94305
e-mail: pmmilani@stanford.edu
Search for other works by this author on:
Julia Ling,
Julia Ling
Principal Scientist,
Citrine Informatics,
Redwood City, CA 94063
Citrine Informatics,
Redwood City, CA 94063
Search for other works by this author on:
John K. Eaton
John K. Eaton
Mechanical Engineering Department,
Stanford University,
Stanford, CA 94305
Stanford University,
Stanford, CA 94305
Search for other works by this author on:
Pedro M. Milani
Mechanical Engineering Department,
Stanford University,
Stanford, CA 94305
e-mail: pmmilani@stanford.edu
Stanford University,
Stanford, CA 94305
e-mail: pmmilani@stanford.edu
Julia Ling
Principal Scientist,
Citrine Informatics,
Redwood City, CA 94063
Citrine Informatics,
Redwood City, CA 94063
John K. Eaton
Mechanical Engineering Department,
Stanford University,
Stanford, CA 94305
Stanford University,
Stanford, CA 94305
1Corresponding author.
Contributed by the International Gas Turbine Institute (IGTI) of ASME for publication in the JOURNAL OF TURBOMACHINERY. Manuscript received August 16, 2018; final manuscript received August 22, 2018; published online October 17, 2018. Editor: Kenneth Hall.
J. Turbomach. Jan 2019, 141(1): 011004 (10 pages)
Published Online: October 17, 2018
Article history
Received:
August 16, 2018
Revised:
August 22, 2018
Citation
Milani, P. M., Ling, J., and Eaton, J. K. (October 17, 2018). "Physical Interpretation of Machine Learning Models Applied to Film Cooling Flows." ASME. J. Turbomach. January 2019; 141(1): 011004. https://doi.org/10.1115/1.4041291
Download citation file:
Get Email Alerts
Effect of Blade Damage on Low Pressure Ratio Fan Windmill Aerodynamics
J. Turbomach (September 2025)
Related Articles
A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows
J. Turbomach (February,2018)
Optimal Turbulent Schmidt Number for RANS Modeling of Trailing Edge Slot Film Cooling
J. Eng. Gas Turbines Power (July,2015)
Machine Learning for the Development of Data-Driven Turbulence Closures in Coolant Systems
J. Turbomach (August,2022)
Analysis of Turbulent Scalar Flux Models for a Discrete Hole Film Cooling Flow
J. Turbomach (January,2016)
Related Proceedings Papers
Related Chapters
Two Advanced Methods
Applications of Mathematical Heat Transfer and Fluid Flow Models in Engineering and Medicine
Out-Of-Order Matrix Processor: Implementation and Performance Evaluation
International Conference on Advanced Computer Theory and Engineering (ICACTE 2009)
User-Centric Process Descriptions
International Conference on Software Technology and Engineering, 3rd (ICSTE 2011)