Becker, Richard-Gregor and Bolemant, Martin and Krause, Daniel and Peitsch, Dieter (2015) An Automated Process to Create Start Values for Gas Turbine Performance Simulations Using Neural Networks and Evolutionary Algorithms. International Gas Turbine Congress 2015 Tokyo, 2015-11-15 - 2015-11-20, Tokyo, Japan.
![]() |
PDF
2MB |
Abstract
This paper presents a fully automated methodology to create start values for gas turbine performance computer programs. The methodology employs the application of evolutionary algorithms for a more robust convergence of the iterative process of a performance program as well as neural networks for a self-learning start value generation procedure. The achieved results showed that a connection of both methods for the creation of performance model start values is a feasible option. Different types of neural networks as well as several training methods have been evaluated in order to find the best equivalent model. Having found a practical approach for the structure of the neural networks, several performance models of different levels of complexity have been tested. The combination of both of the above presented steps achieved very good convergence rates in combination with a minimum effort for the creation of start values.
Item URL in elib: | https://elib.dlr.de/100666/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Document Type: | Conference or Workshop Item (Speech) | ||||||||||||||||||||
Title: | An Automated Process to Create Start Values for Gas Turbine Performance Simulations Using Neural Networks and Evolutionary Algorithms | ||||||||||||||||||||
Authors: |
| ||||||||||||||||||||
Date: | November 2015 | ||||||||||||||||||||
Refereed publication: | Yes | ||||||||||||||||||||
Open Access: | Yes | ||||||||||||||||||||
Gold Open Access: | No | ||||||||||||||||||||
In SCOPUS: | No | ||||||||||||||||||||
In ISI Web of Science: | No | ||||||||||||||||||||
Status: | Published | ||||||||||||||||||||
Keywords: | gas turbine performance, robust convergence, evolutionary algorithms, neural networks | ||||||||||||||||||||
Event Title: | International Gas Turbine Congress 2015 Tokyo | ||||||||||||||||||||
Event Location: | Tokyo, Japan | ||||||||||||||||||||
Event Type: | international Conference | ||||||||||||||||||||
Event Start Date: | 15 November 2015 | ||||||||||||||||||||
Event End Date: | 20 November 2015 | ||||||||||||||||||||
Organizer: | Gas Turbine Society of Japan | ||||||||||||||||||||
HGF - Research field: | Aeronautics, Space and Transport | ||||||||||||||||||||
HGF - Program: | Aeronautics | ||||||||||||||||||||
HGF - Program Themes: | propulsion systems | ||||||||||||||||||||
DLR - Research area: | Aeronautics | ||||||||||||||||||||
DLR - Program: | L ER - Engine Research | ||||||||||||||||||||
DLR - Research theme (Project): | L - Virtual Engine and Validation methods (old) | ||||||||||||||||||||
Location: | Köln-Porz | ||||||||||||||||||||
Institutes and Institutions: | Institute of Propulsion Technology > Engine | ||||||||||||||||||||
Deposited By: | Becker, Richard-Gregor | ||||||||||||||||||||
Deposited On: | 14 Dec 2015 09:46 | ||||||||||||||||||||
Last Modified: | 24 Apr 2024 20:06 |
Repository Staff Only: item control page