Comparison of Surrogate Modeling Techniques for Life Cycle Models of Advanced Air Mobility

Kurzfassung

Insights from life cycle simulations of Unmanned Air Vehicles (UAVs) can help in the introduction of the anticipated Advanced Air Mobility in a safe and economical manner. This includes (but is not limited to) effects between demand, utilization, fleet availability, and maintenance downtime. In a collaborative effort between NASA and DLR, we aim to evaluate different maintenance strategies for UAVs using uncertainty-driven and discrete event-based life cycle simulation. Computational efficiency is a prevalent issue with this type of research, particularly when expensive-to-evaluate submodels are added into already complex life cycle simulation frameworks. Surrogate modeling solutions reduce execution time but sacrifice output accuracy to do so. In this paper, we present the initial outcomes of the collaboration, which comprise the derivation and development of operational scenarios and a performance model. With the latter being the computational bottleneck, we have performed a comparative analysis of four commonly used surrogate modeling techniques, namely (a) Multilinear Interpolation (MLI), (b) Multilinear Regression, (c) Random Forest (RFo) supervised machine learning, and (d) Polynomial Chaos Expansions (PCE). Inputs for the models include the UAV's flown distance and direction, carried payload, wind magnitude and direction, turbulence level, and battery health. The model's output is the change in the battery's state of charge. The comparison focuses on accuracy, and decrease in computational expense. Calculated sensitivity measures revealed the flown distance, carried payload, and battery health to be the most influential parameters. All models show good overall accuracy values of 99\% and above but differ significantly in execution time. In addition, only the MLI model was able to capture the influences of head winds and tail winds correctly.