Adaptive control system having direct output feedback and related apparatuses and methods

Claim 1

An adaptive control system (ACS) for controlling a plant based on at least one commanded output signal y c and an rth time-derivative of the commanded output signal y c (r) , and a plant output signal y that is a function of the states existing in the plant, r being the relative degree of the plant output signal y, the ACS comprising: a model inversion unit (MIU) coupled to receive a pseudo-control signal v and a plant output signal y, the MIU generating a control signal δ c by inverting an approximate model of the plant dynamics, the MIU supplying the control signal δ c to the plant for control thereof; a summing unit coupled to receive the rth time-derivative of the commanded output signal y c (r) , a pseudo-control component signal v dc , and an adaptive control signal v ad , the summing unit adding the rth time-derivative of the commanded output signal y c (r) and the pseudo-control component signal v dc , and subtracting the adaptive control signal v ad , to generate the pseudo-control signal v; an error signal generator (ESG) coupled to receive the commanded output signal y c and optional derivatives thereof and the plant output signal y, the ESG generating a tracking error signal {tilde over (y)} by differencing corresponding signal components of the commanded output signal y c and optional derivatives thereof, and a plant output signal y; a linear controller having a linear dynamic compensator (LDC) coupled to receive the tracking error signal {tilde over (y)}, the LDC generating the pseudo-control component signal v dc based on the tracking error signal {tilde over (y)}, the pseudo-control component signal v dc for stabilizing the feedback linearized dynamics of the model inverted in the MIU, the LDC generating a transformed signal {tilde over (y)} ad based on the tracking error signal {tilde over (y)} so that a transfer function from an adaptive control signal v ad to the transformed signal {tilde over (y)} ad is strictly positive real (SPR); an adaptive element having an error conditioning element coupled to receive the transformed signal {tilde over (y)} ad and at least one neural network basis function φ, the error conditioning element stable low-pass filtering the basis function φ to produce a filtered basis function φ f and multiplying the filtered basis function φ r by the transformed signal {tilde over (y)} ad to produce a training signal δ; and a neural network adaptive element (NNAE) coupled to receive the plant output signal y, the pseudo-control signal v, and the training signal δ, the NNAE having a neural network generating the adaptive control signal v ad based on the plant output signal y and the pseudo-control signal v supplied as inputs to the neural network, the neural network generating the adaptive control signal v ad by mapping the plant output signal y and a pseudo-control signal v to the adaptive control signal v ad based on at least one basis function φ and at least one connection weight W, the neural network couple to output the basis function φ to the error conditioning element, the adaptive element using the training signal δ to update the basis function φ and at least one connection weight W of the neural network so that the adaptive control signal v ad generated by the neural network is bounded.