Developing novel big-data based models for designing greener turbines
Grant number: LP160100228 | Funding period: 2017 - 2020
This project aims to improve the fuel efficiency of gas turbines, the backbone of power generation and aircraft propulsion, for efficient and affordable power generation and air travel. Australia is large, remote and has some of the world’s highest carbon dioxide emissions per capita. Improving fuel efficiency will reduce cost and emissions, but current design tools lack the accuracy to advance technology. This project will investigate fluid flow in gas turbines and use big-data analytics to develop more accurate design tools. Gas turbines with reduced fuel usage and carbon dioxide emissions are expected to reduce the cost and environmental impact of power generation and air travel in Austra..View full description
Related publications (18)
Machine-Learnt Turbulence Closures for Low Pressure Turbines with Unsteady Inflow Conditions
Harshal D Akolekar, Richard Sandberg, Nick Hutchins, Vittorio Michelassi, Gregory M Laskowski
The design of low-pressure turbines (LPT) must account for the losses generated by the unsteady interaction with the upstream blad..
Development and Use of Machine-Learnt Algebraic Reynolds Stress Models for Enhanced Prediction of Wake Mixing in Low-Pressure Turbines
HD Akolekar, J Weatheritt, N Hutchins, RD Sandberg, G Laskowski, V Michelassi
Nonlinear turbulence closures were developed that improve the prediction accuracy of wake mixing in low-pressure turbine (LPT) flo..
The Current State of High-Fidelity Simulations for Main Gas Path Turbomachinery Components and Their Industrial Impact
Richard D Sandberg, Vittorio Michelassi
Over the past two decades high-fidelity simulations have become feasible for most main gas path turbomachinery components. This pa..
Les and RANS analysis of the end-wall flow in a linear LPT cascade, part I: Flow and secondary vorticity fields under varying Inlet condition
R Pichler, Yaomin Zhao, RD Sandberg, V Michelassi, R Pacciani, M Marconcini, A Arnone
In low-pressure-turbines (LPT) around 60–70% of losses are generated away from end-walls, while the remaining 30–40% is controlled..
Identification and quantification of losses in a LPT cascade by POD applied to LES data
D Lengani, D Simoni, R Pichler, RD Sandberg, V Michelassi, F Bertini
A POD based procedure has been developed to identify and account for the different contributions to the entropy production rate ca..
Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot
RD Sandberg, R Tan, J Weatheritt, A Ooi, A Haghiri, V Michelassi, G Laskowski
A form of supervised machine learning was applied to highly resolved large-eddy simulation (LES) data to develop non linear turbul..
LES and RANS Analysis of the End-Wall Flow in a Linear LPT Cascade With Variable Inlet Conditions: Part II — Loss Generation
Michele Marconcini, Roberto Pacciani, Andrea Arnone, Vittorio Michelassi, Richard Pichler, Yaomin Zhao, Richard Sandberg
In low-pressure-turbines (LPT) at design point around 60–70% of losses are generated in the blade boundary layers far from end-wal..
A Comparative Study of Contrasting Machine Learning Frameworks Applied to RANS Modeling of Jets in Crossflow
Jack Weatheritt, Richard D Sandberg, Julia Ling, Gonzalo Saez, Julien Bodart
Classical RANS turbulence models have known deficiencies when applied to jets in crossflow. Identifying the linear Boussinesq stre..
HIGH-FIDELITY SIMULATIONS OF A LINEAR HPT VANE CASCADE SUBJECT TO VARYING INLET TURBULENCE
Richard Pichler, Richard D Sandberg, Gregory Laskowski, Vittorio Michelassi
The effect of inflow turbulence intensity and turbulence length scales have been studied for a linear high-pressure turbine vane c..
Machine Learning for Turbulence Model Development Using a High-Fidelity HPT Cascade Simulation
Jack Weatheritt, Richard Pichler, Richard D Sandberg, Gregory Laskowski, Vittorio Michelassi
The validity of the Boussinesq approximation in the wake behind a high-pressure turbine blade is explored. We probe the mathematic..