Experimental and Numerical Based Defect Detection in a Model Combustion Chamber through Machine Learning

Originalpublikation

von der Haar, H.; Ignatidis, P.; Dinkelacker, F.: Experimental and Numerical Based Defect Detection in a Model Combustion Chamber through Machine Learning. In: International Journal of Gas Turbine, Propulsion and Power Systems 12 (2021), Nr. 4, S. 1-9. DOI: https://doi.org/10.38036/jgpp.12.4_1

Version im Repositorium

Zum Zitieren der Version im Repositorium verwenden Sie bitte diesen DOI: https://doi.org/10.15488/16726

Thumbnail
Name: 12_1-Experimental.pdf
Größe: 2.226Mb
Format: PDF
Öffnen
Zusammenfassung:
A disturbed combustion process in an aircraft engine has an impact on the internal flow and leads to specific irregularities in the species distribution in the exhaust jet. Measuring this distribution provides information about the combustion state and offers the possibility to reduce the engine down-time during inspection. The approach has the potential to improve the resource management as well as the availability and safety of the system. Aim of the research project is to evaluate the state of an aircraft engine by analyzing the emission field in the exhaust jet and using a support vector machine (SVM) algorithm for automatic defect detection and allocation.
Lizenzbestimmungen: CC BY 4.0 Unported - https://creativecommons.org/licenses/by/4.0/
Publikationstyp: Article
Publikationsstatus: publishedVersion
Erstveröffentlichung: 2021
Schlagwörter (englisch): Aircraft detection, Defects, Engines, Support vector machines, Automatic defect detections, Combustion pro-cess, Combustion state, Defect detection, Down time, Internal flows, Machine-learning, Resource management, Species distributions, Support vector machines algorithms, Aircraft engines
Fachliche Zuordnung (DDC): 620 | Ingenieurwissenschaften und Maschinenbau

Downloadstatistik

Zur Langanzeige

Die Publikation erscheint in Sammlung(en):

 

Suche im Repositorium


Durchblättern

Mein Nutzer/innenkonto

Nutzungsstatistiken