In this paper CNNs are used for solving an optimization problem with two different approaches: CNN is used as a surrogate model of the forward problem, inserted in an optimization loop governed by a genetic algorithm, in the first approach, while a CNN is trained for solving directly the inverse problem in the second approach. The case study is the shape design of a magnetic core used for material testing.
KomorowskiM.GratkowskiS. and ChadyT., Choice of the distance between the pole-pieces of the electromagnet yoke in a magnetic method of material testing, AIP Conference Proceedings760 (2005), 602.
2.
BlitzJ., Electrical and Magnetic Methods of Nondestructive Testing, Adam Hilger, New York, USA, 1991, ISBN 0-7503-0148-1.
3.
HuangS. and WangS., New Technologies in Electromagnetic Non-destructive Testing, First edn, Springer, 2016, ISBN: 978-981-10-0577-0.
4.
TrimmM., An overview of nondestructive evaluation methods, Practical Failure Analysis3 (2003), 17–31.
5.
StupakovO.TomášI. and KadlecováJ., Optimization of single-yoke magnetic testing by surface fields measurement, Journal of Physics D: Applied Physics39(2) (2006), 248–254.
6.
DuW.ZhaoY.RoyR.AddepalliS. and TinsleyL., A review of miniaturised non-destructive testing technologies for in-situ inspections, Procedia Manufacturing16 (2018), 16–23.
7.
GotohY.HiranoH.NakanoM.FujiwaraK. and TakahashiN., Electromagnetic nondestructive testing of rust region in steel, IEEE Transactions on Magnetics41(10) (2005), 3616–3618.
8.
KhanA.GhorbanianV. and LowtherD., Deep learning for magnetic field estimation, IEEE Transactions on Magnetics55(6) (2019), 1–4.
9.
KhanA.MohammadiM.H.GhorbanianV. and LowtherD.A., Efficiency map prediction of motor drives using deep learning, IEEE Transactions on Magnetics56(3) (2020).
10.
LiY.LeiG.BramerdorferG.PengS.SunX. and ZhuJ., Machine learning for design optimization of electromagnetic devices: Recent developments and future directions, Applied Sciences11(4) (2021), 1627.
11.
GoodfellowI.BengioY. and CourvilleA., Deep Learning, The MIT Press, 2016.
12.
BaldanM.Di BarbaP. and NackeB., Magnetic properties identification by using a bi-objective optimal multi-fidelity neural network, IEEE Transactions on Magnetics57(6) (2021).
13.
ZiolkowskiM.KwiatkowskiW.GratkowskiS. and ZiolkowskiM., Static analysis of a balanced armature receiver, COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering37(4) (2018), 1392–1404.
14.
TumanskiS. and BakonT., Measuring system for two-dimensional testing of electrical steel, Journal of Magnetism and Magnetic Materials223(3) (2001), 315–325.
HauptR.L. and HauptS.E., Practical Genetic Algorithms, John Wiley & Sons, Inc., 2003.
17.
Di BarbaP., Multiobjective Shape Design in Electricity and Magnetism, Lecture Notes in Electrical Engineering. Springer, 2010.
18.
IoffeS. and SzegedyC., Batch normalization: Accelerating deep network training by reducing internal covariant shift, in: 32nd International Conference on Machine Learning, ICML, Vol. 1, 2015, pp. 448–456.
19.
NeittaanmäkiP.RudnickiM. and SaviniA., Inverse Problems and Optimal Design in Electricity and Magnetism, Oxford University Press, 1996.
