Search Results

The objective of this paper is to review the flight simulation facilities at NASA Ames Research Center, and to also consider the many uses of flight simulation that have emerged over the last decade. Flight simulators have evolved into a very useful and economic research tool. Component technologies have also evolved considerably to meet demands imposed by the aerospace community. In fact, the utilization of flight simulators for research and development has become so widely accepted that they are now being used as an integral element of much different and more complex domains. Whereas flight dynamics and control, guidance and navigation, human factors, vehicle design, mission assessment, and training have been, and perhaps always will be, the most popular research areas associated with simulation, many other areas have realized significant benefits from the use of simulation.

The aerodynamic stability and control derivative database for the F-15 ACTIVE aircraft's six degree-of-freedom simulation is currently being modeled using neural networks. The objective is to develop pre-trained neural networks using this database, and upon achieving acceptable levels of size and accuracy, to install the neural networks on the F-15 ACTIVE aircraft for in-flight experimentation in on-line learning and reconfigurable flight controls. The material presented in this paper examines a representative subset of the entire aerodynamic stability and control derivative database in order to: 1) develop accuracy criteria that neural networks must achieve in order to accurately model the database, and 2) develop guidelines for pre-training that will help achieve the accuracies while minimizing network size. The results show that neural networks must be within ±3.77%, ±15%, or ±50%, depending on individual derivative sensitivities and relative importance rankings.