Tiltrotor aircrafts have both fixed-wing control surfaces and helicopter rotors for attitude control. The redundancy of control surfaces provides the possibility for the control system to reconfigure the control law when actuator faults occur during flight. Possible actuator faults have been classified into two categories: predictable and unpredictable faults, and a different strategy has been adopted to deal with each kind of fault. Firstly, the predictable faults are handled by a multiple-model switching adaptive scheme. These kinds of faults are modeled, and their corresponding controllers are derived offline. Secondly, since the degree of drop in aerodynamic effectiveness cannot be predicted a priori, unpredictable faults are handled by a simple adaptive control scheme, to force the plant with faults to track the prescribed reference model. The presented methodology has been verified by nonlinear full-envelope flight simulation for both categories of actuator faults. The predictable fault is represented by the elevator floating. Elevator damage causing an aerodynamic effectiveness drop by 80% is chosen as the example of unpredictable fault. Both faults are simulated at the late stage of the tiltrotor conversion mode. Results show that the presented strategy of reconfiguration is able to detect the fault rapidly and stabilize the aircraft when a fault occurs, while the aircraft motion diverges without the reconfiguration scheme. The aircraft also presents a relatively good performance under controller reconfiguration with a well-tracked conversion path.
Neural networks have been widely used as compensational models for aircraft control designs and as surrogate models for other optimizations. In the case of tiltrotor aircraft, the total number of aircraft states and controls is much greater than that of both traditional fixed-wings and helicopters. This requires, in general, a huge amount of training data for the network to reach a satisfactory approximation precision and makes the network size rise considerably. To solve the practical problem of reducing the size of the approximating network, efforts have to be made in the efficient utilization of the limited amount of training data. This work presents the methodology of optimizing the sample pattern of the training data set by adopting the metaheuristic algorithm of the particle swarm optimizer improved by the fourth-order Runge–Kutta algorithm. A 6-degree-of-freedom nonlinear flight dynamics model of the tiltrotor aircraft is derived, along with its approximation radial basis function neural network. An example case of approximating a highly nonlinear function is studied to illustrate the principle and main parameters of the optimizer, and the approximation performance of the time-domain response of the unstable nonlinear system is revealed by the study of a Van der Pol oscillator. Then, the presented method is applied to the modeled tiltrotor aircraft for its early and late conversion modes. The optimization scheme shows great improvement in both cases, as the function approximation error is reduced significantly.