Nonlinear Control Allocation: A Learning Based Approach

Modern aircraft are designed with redundant control effectors to cater for fault tolerance and maneuverability requirements. This leads to an over-actuated aircraft which requires a control allocation scheme to distribute the control commands among effectors. Traditionally, optimization based control allocation schemes are used; however, for nonlinear allocation problems these methods require large computational resources. In this work, a novel ANN based nonlinear control allocation scheme is proposed. To start, a general nonlinear control allocation problem is posed in a different perspective to seek a function which maps desired moments to control effectors. Few important results on stability and performance of nonlinear allocation schemes in general and this ANN based allocation scheme, in particular, are presented. To demonstrate the efficacy of the proposed scheme, it is compared with standard quadratic programming based method for control allocation.