Abstract
Abstract 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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.