Fault-tolerant autolanding controller design using neural network

In the paper, a neural control scheme is presented for an UAV automatic landing problem under the failure of stuck control surfaces and severe winds. The scheme incorporates a neural controller which augments an existing conventional controller called Baseline Trajectory Following Controller (BTFC). The neural controller is designed using Single Hidden Layer Feedforward Networks (SLFNs) with additive or Radial Basis Function (RBF) hidden nodes in a unified framework. The SLFNs are trained based on the recently proposed neural algorithm named Online Sequential Extreme Learning Machine (OS-ELM). In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. Performance of the proposed neural control scheme is evaluated on a typical aircraft autolanding with a single stuck failure of left elevator. The simulation results demonstrate good fault tolerant performance of the proposed neural fault tolerant controller.