Convolutional Neural Network (CNN) based Planar Inductor Evaluation and Optimization
Authors:
- 20 March 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1506-1511
Abstract
Magnetic component as one of the most lossy and bulky components in power electronic converters has been researched on optimization through calculation, experimental and FEM simulation. However, the traditional methods are normally time-consuming or inaccurate. A novel method that combined FEM simulation and convolutional neural network (CNN) is discussed in this paper, which can predict the inductance and core loss efficiently and accurately. Experimental result shows the accuracy of CNN prediction. Based on the CNN inductor inductance and loss prediction, a novel optimization method is presented which can comprehensively and quickly provide the optimization result considering power loss and power density.Keywords
This publication has 22 references indexed in Scilit:
- Cauer Ladder Network Representation of Eddy-Current Fields for Model Order Reduction Using Finite-Element MethodIEEE Transactions on Magnetics, 2017
- Deep learningNature, 2015
- Planar inductor structure with variable flux distribution —A benefit or impediment?2015
- Fundamentals of Power Electronics2013
- Inductor optimization procedure for Power Supply in Package and Power Supply on Chip2011
- A new high frequency inductor loss measurement method2011
- Cross-Validation2009
- Coupled-inductor design optimization for fast-response low-voltage DC-DC converters2003
- Minimum copper and core losses power inductor design2002
- A study on stray capacitance modeling of inductors by using the finite element methodIEEE Transactions on Electromagnetic Compatibility, 2001