Stochastic neural direct adaptive control

A stochastic neural direct adaptive control algorithm for partially known state-space nonlinear time-varying plants is presented. A neural network is used to generate the control signal, which optimizes a quadratic (one-step-ahead prediction) performance index. In comparison to conventional stochastic state-space adaptive control, this neural control algorithm offers higher computation speed due to the parallel processing structure of the neural network. The algorithm is limited to known system matrices B(k) and C(k). For applications where B(k) and C(k) are unknown to the controller, an indirect neural adaptive control scheme may be used.<<ETX>>