Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements
Wind tunnel tests to measure unsteady cavity flow pressure measurements can be expensive, lengthy, and tedious. In this work, the feasibility of an active machine learning technique to design wind tunnel runs using proxy data is tested. The proposed active learning scheme used scattered data approxi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2014/218710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546568767537152 |
|---|---|
| author | Ankur Srivastava Andrew J. Meade |
| author_facet | Ankur Srivastava Andrew J. Meade |
| author_sort | Ankur Srivastava |
| collection | DOAJ |
| description | Wind tunnel tests to measure unsteady cavity flow pressure measurements can be expensive, lengthy, and tedious. In this work, the feasibility of an active machine learning technique to design wind tunnel runs using proxy data is tested. The proposed active learning scheme used scattered data approximation in conjunction with uncertainty sampling (US). We applied the proposed intelligent sampling strategy in characterizing cavity flow classes at subsonic and transonic speeds and demonstrated that the scheme has better classification accuracies, using fewer training points, than a passive Latin Hypercube Sampling (LHS) strategy. |
| format | Article |
| id | doaj-art-ee68b2b9ce564a4aa09c4c9ef50139d0 |
| institution | Kabale University |
| issn | 1687-5966 1687-5974 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj-art-ee68b2b9ce564a4aa09c4c9ef50139d02025-02-03T06:48:16ZengWileyInternational Journal of Aerospace Engineering1687-59661687-59742014-01-01201410.1155/2014/218710218710Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure MeasurementsAnkur Srivastava0Andrew J. Meade1Mechanical Engineering and Material Science Department, William Marsh Rice University, Houston, TX 77251-1892, USAMechanical Engineering and Material Science Department, William Marsh Rice University, Houston, TX 77251-1892, USAWind tunnel tests to measure unsteady cavity flow pressure measurements can be expensive, lengthy, and tedious. In this work, the feasibility of an active machine learning technique to design wind tunnel runs using proxy data is tested. The proposed active learning scheme used scattered data approximation in conjunction with uncertainty sampling (US). We applied the proposed intelligent sampling strategy in characterizing cavity flow classes at subsonic and transonic speeds and demonstrated that the scheme has better classification accuracies, using fewer training points, than a passive Latin Hypercube Sampling (LHS) strategy.http://dx.doi.org/10.1155/2014/218710 |
| spellingShingle | Ankur Srivastava Andrew J. Meade Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements International Journal of Aerospace Engineering |
| title | Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements |
| title_full | Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements |
| title_fullStr | Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements |
| title_full_unstemmed | Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements |
| title_short | Use of Active Learning to Design Wind Tunnel Runs for Unsteady Cavity Pressure Measurements |
| title_sort | use of active learning to design wind tunnel runs for unsteady cavity pressure measurements |
| url | http://dx.doi.org/10.1155/2014/218710 |
| work_keys_str_mv | AT ankursrivastava useofactivelearningtodesignwindtunnelrunsforunsteadycavitypressuremeasurements AT andrewjmeade useofactivelearningtodesignwindtunnelrunsforunsteadycavitypressuremeasurements |