Search

The objective of this document is to show the capabilities of parallel hardware-based on-line learning neural networks (NNs). This specific application is related to an on-line estimation problem for sensor validation purposes. Neural-network-based microprocessors are starting to be commercially available. However, most of them feature a learning performed with the classic back-propagation algorithm (BPA). To overcome this lack of flexibility a customized motherboard with transputers was implemented for this investigation. The extended BPA (EBPA), a modified and more effective BPA, was used for the on-line learning, These parallel hardware-based neural architectures were used to implement a sensor failure detection, identification, and accommodation scheme in the model of a flight control system assumed to be without physical redundancy in the sensory capabilities. The results of this study demonstrate the potential for these neural schemes for implementation in actual flight control systems of modern high performance aircraft, taking advantage of the characteristics of the extended back-propagation along with the parallel computation capabilities of NN customized hardware.

Research was conducted to examine the performance of fuzzy logic reconstructors (FLRs) and neural network (NN) for the creation of a virtual flight data recorder (VFDR). The goal of the VFDR is to permit the reconstruction of the control surface deflections when other flight parameters are present. Results relative to a VFDR based on a neural network simulator along with a FLR and a neural network reconstructor reveal that both schemes offer accurate reconstructions of the control surface deflections time histories.