Author: United States. National Aeronautics and Space Administration
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
NEURAL NET-BASED REDESIGN OF TRANSONIC TURBINES FOR IMPROVED UNSTEADY AERODYNAMIC PERFORMANCE... NASA/TM-1998-208754... MAR. 1, 1999
Author: United States. National Aeronautics and Space Administration
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Neural Net-Based Redesign of Transonic Turbines for Improved Unsteady Aerodynamic Performance
Improving the Unsteady Aerodynamic Performance of Transonic Turbines Using Neural Networks
Author: National Aeronautics and Space Administration (NASA)
Publisher: Createspace Independent Publishing Platform
ISBN: 9781721511198
Category :
Languages : en
Pages : 26
Book Description
A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yielded a modified design that improves the aerodynamic performance through small changes to the reference design geometry. These results demonstrate the capabilities of the neural net-based design procedure, and also show the advantages of including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process. Rai, Man Mohan and Madavan, Nateri K. and Huber, Frank W. Ames Research Center NASA/TM-1999-208791, NAS 1.15:208791, A-99V0041
Publisher: Createspace Independent Publishing Platform
ISBN: 9781721511198
Category :
Languages : en
Pages : 26
Book Description
A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yielded a modified design that improves the aerodynamic performance through small changes to the reference design geometry. These results demonstrate the capabilities of the neural net-based design procedure, and also show the advantages of including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process. Rai, Man Mohan and Madavan, Nateri K. and Huber, Frank W. Ames Research Center NASA/TM-1999-208791, NAS 1.15:208791, A-99V0041
Improving the Unsteady Aerodynamic Performance of Transonic Turbines Using Neural Networks
Author: Nasa Technical Reports Server (Ntrs)
Publisher: BiblioGov
ISBN: 9781289275594
Category :
Languages : en
Pages : 30
Book Description
A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yielded a modified design that improves the aerodynamic performance through small changes to the reference design geometry. These results demonstrate the capabilities of the neural net-based design procedure, and also show the advantages of including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process.
Publisher: BiblioGov
ISBN: 9781289275594
Category :
Languages : en
Pages : 30
Book Description
A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yielded a modified design that improves the aerodynamic performance through small changes to the reference design geometry. These results demonstrate the capabilities of the neural net-based design procedure, and also show the advantages of including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process.
Improving the Unsteady Aerodynamic Performance of Transonic Turbines Using Neural Networks
ACCELERATED TRAINING FOR LARGE FEEDFORWARD NEURAL NETWORKS... NASA/TM-1998-112239... MAR. 1, 1999
Author: United States. National Aeronautics and Space Administration
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
TWO-DIMENSIONAL HIGH-LIFT AERODYNAMIC OPTIMIZATION USING NEURAL NETWORKS... NASA/TM-1998-112233... OCT. 27, 1998
Author: United States. National Aeronautics and Space Administration
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Unsteady Blade Row Interaction in a Transonic Turbine
Author: National Aeronautics and Space Adm Nasa
Publisher:
ISBN: 9781730897979
Category :
Languages : en
Pages : 66
Book Description
Experimental data from jet-engine tests have indicated that unsteady blade row interaction effects can have a significant impact on the performance of multiple-stage turbines. The magnitude of blade row interaction is a function of both blade-count ratio and axial spacing. In the current research program, numerical simulations have been used to quantify the effects of blade count ratio on the performance of an advanced turbine geometries. Dorney, Daniel J. Glenn Research Center...
Publisher:
ISBN: 9781730897979
Category :
Languages : en
Pages : 66
Book Description
Experimental data from jet-engine tests have indicated that unsteady blade row interaction effects can have a significant impact on the performance of multiple-stage turbines. The magnitude of blade row interaction is a function of both blade-count ratio and axial spacing. In the current research program, numerical simulations have been used to quantify the effects of blade count ratio on the performance of an advanced turbine geometries. Dorney, Daniel J. Glenn Research Center...
Cold-Air Performance of the Compressor-Drive Turbine of the Department of Energy Baseline Automobile Gas-Turbine Engine
Author: National Aeronautics and Space Adm Nasa
Publisher: Independently Published
ISBN: 9781720212096
Category : Science
Languages : en
Pages : 26
Book Description
The aerodynamic performance of the compressor-drive turbine of the DOE baseline gas-turbine engine was determined over a range of pressure ratios and speeds. In addition, static pressures were measured in the diffusing transition duct located immediately downstream of the turbine. Results are presented in terms of mass flow, torque, specific work, and efficiency for the turbine and in terms of pressure recovery and effectiveness for the transition duct. Roelke, R. J. and Mclallin, K. L. Glenn Research Center NASA-TM-78894, E-9480, DOE/NASA/1011-78/25 EC-77-A-31-1011
Publisher: Independently Published
ISBN: 9781720212096
Category : Science
Languages : en
Pages : 26
Book Description
The aerodynamic performance of the compressor-drive turbine of the DOE baseline gas-turbine engine was determined over a range of pressure ratios and speeds. In addition, static pressures were measured in the diffusing transition duct located immediately downstream of the turbine. Results are presented in terms of mass flow, torque, specific work, and efficiency for the turbine and in terms of pressure recovery and effectiveness for the transition duct. Roelke, R. J. and Mclallin, K. L. Glenn Research Center NASA-TM-78894, E-9480, DOE/NASA/1011-78/25 EC-77-A-31-1011
RECENT PRODUCTIVITY IMPROVEMENTS TO THE NATIONAL TRANSONIC FACILITY... NASA/TM-1998-207981... AUG. 6, 1998
Author: United States. National Aeronautics and Space Administration
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Publisher:
ISBN:
Category :
Languages : en
Pages :
Book Description