CaltechAUTHORS
  A Caltech Library Service

Deep learning and data assimilation approaches to sensor reduction in estimation of disturbed separated flows

Le Provost, Mathieu and Hou, Wei and Eldredge, Jeff (2020) Deep learning and data assimilation approaches to sensor reduction in estimation of disturbed separated flows. In: AIAA Scitech 2020 Forum. American Institute of Aeronautics and Astronautics , Reston, VA, Art. No. 2020-0799. ISBN 978-1-62410-595-1. https://resolver.caltech.edu/CaltechAUTHORS:20200113-081647731

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200113-081647731

Abstract

Unsteady loads created by environmental perturbations - namely gusts - can strongly affect small and light-weighted aerial vehicles. To control vehicle's behavior in this perturbed environment, a robust, cheap and accurate estimator of the surrounding flow field and aerodynamic load is essential. Low-order inviscid vortex models constitute an attractive solution to this problem. For aerodynamic applications, the role of viscosity is primarily to inject vorticity into the flow. Intrinsically, this mechanism can't be captured by an inviscid model and need to be modeled. In modern inviscid models, the vorticity shedding criterion is set by the critical leading edge suction parameter (LESP) (Ramesh et al., Theor. Comput. Fluid Dyn., 2013). Without satisfying closure model, the critical LESP has been estimated from data assimilation (Darakananda et al., Phys. Rev. Fluids, 2018) and deep learning (Hou et al., AIAA J., 2019). Refining these works, we explore the influence of the spatial distribution of sensors through these two questions: what is the optimal placement of the pressure sensors? How many sensors are required to accurately estimate the LESP? For the deep learning model, a weight vector is determined which measures the influence of each pressure sensor on the final estimate. This weight vector is regularized by the L1 norm to promote sparsity. The number of sensors used is skrunk from 126 to 3 without significant loss of accuracy. Our deep learning framework is interpreted as the learning of a Koopman invariant subspace for the LESP and angle of attack. In the ensemble Kalman filter framework, an iterative algorithm based on the representers identifies the most impactful sensors. We reduce the number of sensors from 50 to 30.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.2514/6.2020-0799DOIArticle
Additional Information:© 2020 American Institute of Aeronautics and Astronautics. Published Online: 5 Jan 2020.
Other Numbering System:
Other Numbering System NameOther Numbering System ID
AIAA Paper2020-0799
Record Number:CaltechAUTHORS:20200113-081647731
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200113-081647731
Official Citation:Deep learning and data assimilation approaches to sensor reduction in estimation of disturbed separated flows. Mathieu Le Provost, Wei Hou, and Jeff Eldredge. AIAA Scitech 2020 Forum. January 2020; doi: 10.2514/6.2020-0799
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:100657
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:13 Jan 2020 18:18
Last Modified:13 Jan 2020 18:18

Repository Staff Only: item control page