ABSTRACT

Fuzzy systems hold the capability to approximate non-linear systems with uncertainty over a wide range of operating conditions by means of a series of if–then fuzzy inference rules that represent the experience of human experts. Fuzzy logic-based controller design is a powerful tool to solve the aircraft landing problem under severe winds. In the feedback–error–learning scheme, the proposed sequential adaptive fuzzy inference system (SAFIS) and online sequential fuzzy extreme machine learning (OS-Fuzzy-ELM) algorithms are utilized as the fuzzy neural controller together with the basic trajectory following controller (BTFC) controller for the aircraft autolanding problem. The fault-tolerant controller design is illustrated for an unstable high-performance aircraft in the terminal-landing phase subjected to multiple control surface hard over failures and severe winds. The simulation results show that the proposed SAFIS-aided BTFC and OS-Fuzzy-ELM-aided BTFC control schemes have a clear improvement for the fault-tolerant envelope for both single and double faults compared to the conventional control methods used in the BTFC controller.