Development and implementation of adaptive critic based optimal neuro-controller on a cantilevered plate

“In this study, an adaptive critic-based optimal neuro-controller is developed and applied to a non-linear cantilevered plate system to improve its vibrational characteristics. The smart structural system incorporates a two-dimensional aluminum plate mounted with PZT actuators and PVDF sensors is interfaced to a PC with a DAS 1600 data acquisition card. The neural network plant model is acquired from experiments. Model based design approach is used to design optimal neuro-controllers which minimizes an infinite and a finite horizon quadratic cost function by solving the equations obtained by the Dynamic Programming methodology. Two multi-layer perceptron networks the action and the critic trained off-line for initial conditions in the specified range for the state vector. The critic (supervisor) network in our case outputs the co-state vector and critiques the output of the controller network. After convergence to a desired degree of accuracy the action (controller) network gives an optimal output in a feedback form and can be directly incorporated in the control loop.For the infinite horizon case, the control network is implemented directly. Receding horizon technique is used to implement the action networks for the finite horizon case to overcome the identification error in the plant model. The controllers are finally tested for a range of initial conditions and the experimental results are compared for a time response of the plant with and without control.”--Abstract, page iii.