Intelligent Structural Rating System Based on Backpropagation Network

摘要

The existing structural rating system in the maintenance steering group-3 is facing difficulties with developing new aircraft. There is always a lack of available data to help make proper inspection intervals. By taking advantage of the powerful learning ability and data fusion capability of the backpropagation network, this paper aims to develop a new decision support system for the determination of scheduled maintenance inspection intervals for aircraft structures susceptible to accidental damage. As long as various data are available, regardless of engineering experience, experimental values, and in-service reliability data feedback, the backpropagation network has been proven able to make acceptable predictions after training, making accidental damage rating a dynamic and flexible procedure.