An I-term direct adaptive neural control of a nonlinear oscilatory plant

The authors of the paper proposed to use a new Modular Recurrent Trainable Neural Network (MRTNN) for system identification and direct adaptive neural control of a nonlinear oscillatory mechanical plant. The control system contained a MRTNN identifier and a RTNN controller. The first MRTNN module identified the exponential part of the unknown plant and the second one - the oscillatory part of the plant. The RTNN controller used the estimated state vector to suppress the plant oscillations and the static plant output control error is reduced by an I-term added to the control.