Adding Flight Mechanics to Flight Loads Surrogate Model using Multi-Output Gaussian Processes

Abstract : In this paper analytical methods to formally incorporate knowledge of physics-based equations between multiple outputs in a Gaussian Process (GP) model are presented. In Gaussian Processes a multi-output kernel is a covariance function over correlated outputs. Using a general framework for constructing auto- and cross-covariance functions that are consistent with the physical laws, physics-based relationships among several outputs can be imposed. Results of the proposed methodology for simulated data and measurement from flight tests are presented. The main contribution of this paper is the application and validation of our methodology on a dataset of flight tests, while imposing knowledge of flight mechanics into the model.
Document type :
Conference papers
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01828749
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Tuesday, July 3, 2018 - 1:36:26 PM
Last modification on : Tuesday, October 22, 2019 - 5:20:43 PM
Long-term archiving on : Monday, October 1, 2018 - 10:24:59 AM

File

Chiplunkar_18001.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01828749, version 1
  • OATAO : 18001

Citation

Ankit Chiplunkar, Michele Colombo, Emmanuel Rachelson, Joseph Morlier. Adding Flight Mechanics to Flight Loads Surrogate Model using Multi-Output Gaussian Processes. 17th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, AIAA AVIATION Forum, Jun 2016, Washington, United States. pp.1-11. ⟨hal-01828749⟩

Share

Metrics

Record views

44

Files downloads

40