Neural Network Fractional Order Sliding Mode Control of DC-DC Buck Converter

In this paper, a double hidden layer recurrent neural network fractional order sliding mode control (DHLRNNFOSMC) based on a finite time disturbance observer (FTDO) is designed for a DC-DC buck converter. Fractional order term to the sliding controller improves the control accuracy of DC-DC buck converters. The FTDO was designed to compensate for the mismatch disturbance and the DHLRNN was used to approximate the nonlinear function of the converter system. Finally, hardware experiments of a DC-DC buck converter illustrate the proposed controller presents higher voltage tracking accuracy and faster dynamic response under different test conditions compared to other methods.