Ultracapacitor modeling and control with discrete fractional order artificial neural network

Abstract

In this article a new approach of using the discrete time fractional order artificial neural network controller for control of charging and discharging process for system with ultracapacitor is proposed. First, the discrete fractional order neural network for incommensurate non-linear system modeling is presented. After successful modeling of the system with ultracapacitor the neural network inverse controller, based on the presented configuration of fractional order neural network, is given. All the computer simulations are tested and compared with the results achieved on the physical device. Advantages of the proposed solution are described and discussed.