Fault Detection and Fault Tolerance Mechanism for DC/DC Converters in Microgrids

A solution for modelling and controlling the operation of DC/DC converters, both in normal and in fault regime, is proposed. The proposed converter model is based on ARX structure with variable coefficients. Feedforward fully connected neural network are used in order to generate the appropriate model coefficients for variable duty cycle. A control structure that can be used both to detect the faults and to reject their effect is introduced. The proposed structure contains a compensator whose action assures the avoidance of the unstable regime when the converter parameters change from their nominal values, acting as an efficient fault tolerance mechanism The proposed approach is directed toward developing algorithms suitable for real-time implementation on 32 bit ARM processors. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.