Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

doi:10.1109/TR.2022.3196272

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

2023-09-01

1

OA

AI

DOI：10.1109/TR.2022.3196272

Original

Original request for help

Save

Abstract

En 中文

In the context of aircraft system performance assessment, deep learning technologies allow us to quickly infer models from experimental measurements, with less detailed system knowledge than usually required by physics-based modeling. However, this inexpensive model development also comes with new challenges regarding model trustworthiness. This article presents a novel approach, physics-guided adversarial machine learning (ML), which improves the confidence over the physics consistency of the model. The approach performs, first, a physics-guided adversarial testing phase to search for test inputs revealing behavioral system inconsistencies, while still falling within the range of foreseeable operational conditions. Then, it proceeds with a physics-informed adversarial training to teach the model the system-related physics domain foreknowledge through iteratively reducing the unwanted output deviations on the previously uncovered counterexamples. Empirical evaluation on two aircraft system performance models shows the effectiveness of our adversarial ML approach in exposing physical inconsistencies of both the models and in improving their propensity to be consistent with physics domain knowledge.

Keywords:

Physics

Atmospheric modeling

Data models

Computational modeling

Sensitivity

Aircraft

Training

Adversarial machine learning

aircraft product development

deep learning (DL)

search-based software testing (SBST)

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

Abstract

Journal

Organization