Efficient sequential fuzzy-neural algorithms for aircraft fault-tolerant control

This thesis focuses on the development of two efficient sequential fuzzy neural algorithms. The first algorithm is named as Sequential Adaptive Fuzzy Inference System where the number of fuzzy rules is determined automatically according to the learning procedure and the parameters in the existing fuzzy rules are modified. The second algorithm is called as On-line, Sequential, Fuzzy Extreme Learning Machine where the parameters for the fuzzy rules are updated at an extremely high speed. Besides based on the two new fuzzy neural algorithms, two adaptive, fault-tolerant, fuzzy control strategies are developed in this thesis for a high performance fighter automatic landing problem under the failures of stuck control surfaces and severe winds.DOCTOR OF PHILOSOPHY (EEE