Comparison of Surrogate Modeling Methods for Finite Element Analysis of Landing Gear Loads
Bibliographic record
Abstract
Aircraft landing gear structures are exposed to complex loading in-service. Coupled with the geometry and joints used within landing gear structural assemblies, finite element models tend to be used to compute the loads acting on landing gear components during ground maneuvers. Concerning novel design approaches for complex structural assemblies, such as probabilistic assessment, optimization or ‘digital-twins’, the computational expense of using finite element models is prohibitive. Surrogate modeling methods have been proposed as a route to reducing the computational expense of assessing complex structural assemblies for static and fatigue design. This paper investigates the application of Response Surfaces, Radial Basis Functions, Gaussian Process Regression and Artificial Neural Networks as approaches to surrogate modeling for landing gear load models. Following the construction of the surrogate models within case studies representing a side stay and complex drag brace component, it was identified that Response Surface and Gaussian Process Regression surrogate models could be used to reduce the computational expense of a landing gear loads assessment from 20 seconds to less than a millisecond. As a result, surrogate modeling methods provide the required reduction in computational expense to support probabilistic design and optimization of complex structural assemblies.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".