| DOI | Resolve DOI: https://doi.org/10.4050/F-0079-2023-18094 |
|---|
| Author | Search for: Cheung, Catherine1ORCID identifier: https://orcid.org/0000-0002-0696-8405; Search for: Seabrook, Emma1ORCID identifier: https://orcid.org/0009-0003-5754-0446 |
|---|
| Affiliation | - National Research Council of Canada. Aerospace
|
|---|
| Format | Text, Article |
|---|
| Conference | Vertical Flight Society 79th Annual Forum & Technology Display, May 16-18, 2023, West Palm Beach, FL, USA |
|---|
| Abstract | Regime recognition is an important tool for monitoring aircraft usage. Algorithms for this task are normally trained and tested on flight load survey data. In many instances, significant portions of the flight data are not used because of labeling uncertainties. Flight test data is expensive to generate, but machine learning-based solutions rely on copious amounts of training data, so the idea of discarding data is unappealing. This paper presents a process to consistently and systematically label flight data with common helicopter regimes that would reduce the amount of unlabeled flight test data. The approach makes use of regime descriptions and parameter time histories to assign labels, which are then verified using flight path and flight test card information. Although the implementation of the approach is challenging, the initial results from Bell 206 test flights demonstrate that this approach can significantly reduce the amount of unlabeled flight data, enabling much more usable data for training algorithms. |
|---|
| Publication date | 2023-05-16 |
|---|
| Publisher | The Vertical Flight Society |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | d6e7e1d0-9195-4657-a900-83642daa6974 |
|---|
| Record created | 2024-12-06 |
|---|
| Record modified | 2024-12-06 |
|---|
