Optimal tracking control of MISO nonlinear systems based on multi-dimensional Taylor network only by output feedback

The control input item is added to constitute the nonlinear dynamic model, on the basis of the original multi-dimensional Taylor network in this paper. And this nonlinear dynamic model is used to optimally control MISO nonlinear system only by output feedback without the disturbance estimation of the system or needing the state observer. The back-propagation algorithm is used to train the parameters of the multi-dimensional network with the control input item. Through the simulation, it is demonstrated the multi-dimensional Taylor network used as the optimal MISO nonlinear system tracking controller is effective.