Abstract
Predictive control is a flexible control methodology that can optimize performance while satisfying current and voltage constraints. Its application in the power electronics domain is however hampered by the high computational demands associated with it. In this paper, piecewise-affine neural networks are explored to greatly simplify these controllers and allow for an inexpensive implementation in commercial hardware. More specifically, we tackle the problem of enhancing the start-up transient response of a step-down dc-dc converter while also satisfying inductor current constraints. We analyze the neural network architecture, and detail its training and validation procedures. The learned controller is then embedded on an inexpensive 80-MHz microcontroller, and experimental results are provided showing that the whole control algorithm can be executed in under 30 microseconds.
Highlights
Its application in the power electronics domain is hampered by the high computational demands associated with it
We tackle the problem of enhancing the start-up transient response of a step-down dc-dc converter while satisfying inductor current constraints
Well designed compensators are at the heart of highperformance power electronic devices
Summary
Well designed compensators are at the heart of highperformance power electronic devices In this context, linear control techniques are undoubtedly the most popular methodologies used by practitioners [1]–[3], usually exploiting problem-specific architectures and relying on proportionalintegral-derivative (PID) blocks [4]–[6]. Researchers in the control field have produced a large body of work on scaling down the complexity of EMPC with many ingenious ideas These include exploiting information regarding the initial condition of the system to ‘delete’ certain regions [19], approximating the optimal solution with specific sets of basis functions [20], finding efficient data structures to store and evaluate the piecewise control law [21], etc. We provide experimental results in closed-loop and show that the computations are executed in under 30 μs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Open Journal of the Industrial Electronics Society
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.
