A dynamic backpropagation algorithm with application to gain-scheduled aircraft flight control system design

The authors introduce a dynamic backpropagation algorithm for continuous-time dynamic neural fuzzy systems, as a generalization of the standard backpropagation algorithm for feedforward neural network systems. The proposed algorithm is applied to the design and training of a fuzzy-gain-scheduler for an aircraft flight control system. The trained control system is tested on a full-fledged six-degree-of-freedom nonlinear aircraft simulation package. Simulation results show that significant improvement is achieved through training of the fuzzy-gain-scheduler by using the proposed dynamic backpropagation algorithm.