A Real-time Analysis Tool based on Surrogate Models for Accurate Prediction of Combined Flight External Loads

The goal of the proposed effort is to develop and demonstrate an integrated software tool based on surrogate models for real-time analysis and prediction of combined static and dynamic external loads using non-proprietary physics-based models and existing flight-test data. In Phase I key technology elements were developed and proof-of-principle was successfully demonstrated. Load analysis software encapsulating unified formulation, varying-fidelity surrogate models, model fusion, input selection, and model verification were developed in an integrated environment. By way of extensive USAF relevant case studies, critical evidence was established to accurately analyze flight test data (5% uncertainty in load prediction) for various maneuvers at the real-time rate and to elucidate primary load-driving factors. In Phase II the software will be optimized in performance and functionality. The surrogate modeling will be expanded. Advanced fusion algorithms will be developed for improved reliability. Global sensitivity analysis technique will be developed for quantitative characterization of input significance. Model verification will be refined for objective evaluation of load prediction performance. The software will be integrated with USAF designated flight test tool (IADS) to automate the entire data analysis work flow in AFTC environment. The tool will be extensively validated/demonstrated via case studies of USAF interest.