Neural network controllers for power factor correction of AC/DC switching converters

Abstract

AC/DC switching converters are highly nonlinear. Therefore they draw a nonsinusoidal current with a low power factor. Conventional linear controllers used for power factor correction of these converters do not offer a wide dynamic range. Neural network controllers (NNC) are nonlinear, which learn, adapt and provide wider dynamic range. This paper presents the use of NNCs in power factor correction of AC/DC switching converters. The NNC replaces the conventional current mode controller (CMC) of the high power factor AC/DC converter. Both the direct and indirect NN control schemes are used. Comparisons are made between the simulation results of the NNC and those of the CMC under normal and dynamic operations. The results demonstrate that NNCs can effectively control the high power factor AC/DC switching converter. The NNC performance is comparable, and in some cases better than the CMC. The NN controllers perform better with parameter variations compared to the fixed gain CMC. The fault tolerance capability of the NNC shows excellent results.