Genetic algorithms for reconfiguration

This paper describes the use of genetic algorithms for the reconfiguration of the control system of a contemporary fly-by-wire aircraft. Control system reconfiguration is required in case of failures or damages in the aircraft actuator system (elevator, aileron, rudder, thrust,...). The control system has to be adapted in order to have intact actuators take over the task of the impaired ones. Besides knowledge based reconfiguration for that part of the fault that can be quantitatively sensed, automatic control system parameter adaptation by means of robust generic algorithms can take care of those fault impacts that have not been numerically determined. Genetic algorithms utilize the same three procedures (survival of the fittest, recombination, and mutation) mother nature uses to adapt and optimize her individuals. Such algorithms have been proven very effective during flight tests to adapt the feedforward controller of a model following control system of a modern variable stability aircraft after a 50% elevator effectiveness reduction. The benefits of genetic algorithms for the adaptation of model following control systems will be addressed as well as advanced operators and techniques in genetic search.