Support Vector Regression Application for the Flight Dynamics New Modelling of the UAS-S4
Bibliographic record
Abstract
View Video Presentation: https://doi.org/10.2514/6.2022-2576.vid Having access to an Unmanned Aerial System (UAS) Flight Dynamics Model (FDM) enhances our ability to evaluate its controller performance in the early development phases, which boosts safety while reducing costs. With this aim, the flight tests are normally carried for a pre-established number of flight conditions. Then, mathematical methods are used to obtain the FDM for the entire flight envelope. For our UAS-S4 Ehecatl, we utilized 216 local FDMs corresponding to 216 trim flight conditions. The initial flight envelope data containing 216 local FDMs was then augmented using interpolation and extrapolation methodologies; the three closest neighbors of the supposed original operating point in the flight envelope were firstly obtained. Then, the centroid of the embedding local FDMs was computed. Lastly, the new FDM was generated through interpolation and extrapolation between the centroid and the original operating point. Following this procedure, the number of trimmed local FDMs was augmented up to 3,642. Relying on the augmented dataset, the Support Vector Machine methodology was used as the benchmarking regression algorithm due to its excellent ability when training samples can not be separated linearly. The trained Support Vector Regression model predicted the FDM for the entire flight envelope. For validation studies, the quality of predicted UAS-S4 FDM is evaluated based on the Root Locus diagram. The predicted eigenvalues closeness to the original eigenvalues, confirmed the high accuracy of our developed UAS-S4 FDM. The SVR prediction accuracy was evaluated in different flight conditions, for different number of neighbours, while a variety of kernel functions were also considered. Besides, the regression performance was analyzed based on the state variables step response in the closed-loop control architecture. By utilizing the developed UAS-S4 FDM instead of the initial one, the controller could provide 0.76 faster rise-time, 1.05 faster settling time, and 0.105% less over-shoot for the pitch angle. The UAS-S4 state variables step response properties validated that the developed flight envelope could provide more accurate FDM compared to the initial one for the Linear Quadratic Regulator.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".