Expert supervision of fuzzy learning systems with applications to reconfigurable control for aircraft

Aircraft subsystem failures or battle damage can cause catastrophic failures that can lead to loss of the aircraft. While experienced pilots can often compensate for failures, in certain emergency situations there is the need for computer-assisted or fully computer-automated reconfiguration of the aircraft control laws to save the aircraft. In this paper we show that the performance of the fuzzy model reference learning controller (FMRLC) which solves the control reconfiguration problem for a class of actuator failures can be significantly enhanced by exploiting failure detection and identification (FDI) information. Moreover we show that by using failure information we are able to achieve a “performance adaptive” system that seeks an appropriate performance level depending on the type of failure that occurred