Physics Informed Machine Learning for Advanced Diagnostics & Prognostics of Ground Combat Vehicles

Abstract

<div class="section abstract"><div class="htmlview paragraph">We introduce novel approaches utilizing Physics Informed Machine Learning (PIML) for advanced diagnostics & prognostics of ground combat vehicles (CV). Specifically, we present the development of a PIML model designed to predict the health of engine oil in diesel engines. The condition of engine oil is closely linked to engine wear, thus serving as a crucial indicator of engine health. Our model integrates a physics-based simulation of engine wear in diesel engines, leveraging a time history of engine oil viscosity and engine speed as key input parameters. Furthermore, we conduct uncertainty quantification to assess the impact of varying parameters on engine oil health prediction. Additionally, our model demonstrates the capability to enhance low-fidelity physics models through the integration of a limited set of experimental data. By combining data-driven techniques with physics-based insights, our approach offers enhanced diagnostics and prognostics capabilities for ground combat vehicles, thereby facilitating proactive maintenance and optimization for operational readiness.</div></div>