Renee C. Swischuk

TL;DR: The case studies demonstrate the importance of embedding physical constraints within learned models, and highlight the important point that the amount of model training data available in an engineering setting is often much less than it is in other machine learning applications, making it essential to incorporate knowledge from physical models.

TL;DR: In this article, a physics-based data-driven method was proposed to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process.

TL;DR: In this article, a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations is presented and illustrated in the challenging context of a single-injec...

TL;DR: This work develops a novel data-driven approach to detect sensor failures and predict the corrected sensor data using machine learning methods in an offline/online paradigm and demonstrates the methodology on flight data from a four-engine commercial jet that contains failures in the pitot static system resulting in inaccurate airspeed measurements.

TL;DR: In this paper, a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations is presented and illustrated in the challenging context of a single-injec...