Show simple item record

dc.contributor.authorMcKee, Claire
dc.contributor.authorHarmanto, Dani
dc.contributor.authorWhitbrook, Amanda
dc.date.accessioned2018-02-19T09:15:38Z
dc.date.available2018-02-19T09:15:38Z
dc.date.issued2018-03
dc.identifier.citationMcKee, C., Harmanto, D., Whitbrook, A. (2018). A Conceptual Framework for Combining Artificial Neural Networks with Computational Aeroacoustics for Design Development. In: Proceedings of the International Conference on Industrial Engineering and Operations Management, Bandung, Indonesia, March 6 - 8, 2018, pp: 741-747en
dc.identifier.isbn9781532359446
dc.identifier.issn21698767
dc.identifier.urihttp://hdl.handle.net/10545/622161
dc.description.abstractThis paper presents a preliminary method for improving the design and development process in a way that combines engineering design approaches based on learning algorithms and computational aeroacoustics. It is proposed that machine learning can effectively predict the noise generated by a coaxial jet exhaust by utilizing a database of computational experiments that cover a variety of flow and geometric configurations. A conceptual framework has been outlined for the development of a practical design tool to predict the changes in jet acoustics imparted by varying the fan nozzle geometry and engine cycle of a coaxial jet. It is proposed that computational aeroacoustic analysis is used to generate a training and validation database for an artificial neural network. The trained network can then predict noise data for any operational configuration. This method allows for the exploration of noise emissions from a variety of fan nozzle areas, engine cycles and flight conditions. It is intended that this be used as a design tool in order to reduce the design cycle time of new engine configurations and provide engineers with insight into the relationship between jet noise and the input variables.
dc.description.sponsorshipN/Aen
dc.language.isoenen
dc.publisherIndustrial Engineering and Operations Management Society (IEOM)en
dc.relation.urlhttp://ieomsociety.org/ieom2018/papers/165.pdfen
dc.relation.urlhttp://ieomsociety.org/ieom2018/en
dc.relation.urlhttp://ieomsociety.org/ieom2018/proceedings/en
dc.subjectAeroacousticsen
dc.subjectArtificial neural networksen
dc.subjectMachine learningen
dc.titleA conceptual framework for combining artificial neural networks with computational aeroacoustics for design development.en
dc.typeMeetings and Proceedingsen
dc.contributor.departmentUniversity of Derbyen
dc.identifier.journalProceedings of the International Conference on Industrial Engineering and Operations Managementen
refterms.dateFOA2018-05-19T00:00:00Z
html.description.abstractThis paper presents a preliminary method for improving the design and development process in a way that combines engineering design approaches based on learning algorithms and computational aeroacoustics. It is proposed that machine learning can effectively predict the noise generated by a coaxial jet exhaust by utilizing a database of computational experiments that cover a variety of flow and geometric configurations. A conceptual framework has been outlined for the development of a practical design tool to predict the changes in jet acoustics imparted by varying the fan nozzle geometry and engine cycle of a coaxial jet. It is proposed that computational aeroacoustic analysis is used to generate a training and validation database for an artificial neural network. The trained network can then predict noise data for any operational configuration. This method allows for the exploration of noise emissions from a variety of fan nozzle areas, engine cycles and flight conditions. It is intended that this be used as a design tool in order to reduce the design cycle time of new engine configurations and provide engineers with insight into the relationship between jet noise and the input variables.


Files in this item

Thumbnail
Name:
Whitbrook_2018_A_conceptual_fr ...
Size:
874.4Kb
Format:
PDF
Description:
Final conference paper

This item appears in the following Collection(s)

Show simple item record