Abstract :

This work is to design a neural network based High voltage intelligent model reference adaptive controller. In this scheme, the intelligent supervisory loop is incorporated into the conventional model reference adaptive controller framework by utilizing an online growing multilayer back propagation neural network structure in parallel with it. The Conventional Model Reference Adaptive Controller (MRAC) schemes the controllers were designed to realize plant output converges with reference model which is linear. But this scheme is more efficient for controlling linear plant with unknown parameters. However, using MRAC for controlling the nonlinear system in a real time application is a challenging one. The control input parameter values are given by the sum of the output of conventional MRAC and the output of Neural Networks (NN). The NN is used because to compensate the non-linearity of the plant. The parallel neural controller is designed to precisely track the system output to the desired commend trajectory. The proposed work can improve the system behavior and also force the system to follow the reference model. The effectiveness of the proposed work is demonstrated by MATLAB simulation. The results of the proposed work have been demonstrated by simulations and compared with the existing methods for improved results. This MRAC scheme doesn’t need any initial parameters and works even in uncertain environmental conditions. It easily adopted for all real time environmental conditions without any pollution and fuel consumptions.