Title :
Online detection and modeling of safety boundaries for aerospace applications using active learning and Bayesian statistics
Author_Institution :
UARC, NASA AMES Research Center, Moffett Field, CA, United States
fDate :
7/1/2015 12:00:00 AM
Abstract :
The behavior of complex aerospace systems is governed by numerous parameters. For safety analysis it is important to understand how the system behaves with respect to these parameter values. In particular, understanding the boundaries between safe and unsafe regions is of major importance. In this paper, we describe a hierarchical Bayesian statistical modeling approach for the online detection and characterization of such boundaries. Our method for classification with active learning uses a particle filter-based model and a boundary-aware metric for best performance. From a library of candidate shapes incorporated with domain expert knowledge, the location and parameters of the boundaries are estimated using advanced Bayesian modeling techniques. The results of our boundary analysis are then provided in a form understandable by the domain expert. We illustrate our approach using a simulation model of a NASA neuro-adaptive flight control system, as well as a system for the detection of separation violations in the terminal airspace.
Keywords :
"Atmospheric modeling","Analytical models","Shape","Uncertainty","Computers"
Conference_Titel :
Neural Networks (IJCNN), 2015 International Joint Conference on
Electronic_ISBN :
2161-4407
DOI :
10.1109/IJCNN.2015.7280595