002783200 001__ 2783200
002783200 003__ SzGeCERN
002783200 005__ 20211005211158.0
002783200 0247_ $$2DOI$$a10.1142/s0129065721500337
002783200 0248_ $$aoai:cds.cern.ch:2783200$$pcerncds:FULLTEXT$$pcerncds:CERN:FULLTEXT$$pcerncds:CERN
002783200 035__ $$9https://inspirehep.net/api/oai2d$$aoai:inspirehep.net:1938023$$d2021-10-04T15:07:16Z$$h2021-10-05T04:00:07Z$$mmarcxml
002783200 035__ $$9Inspire$$a1938023
002783200 041__ $$aeng
002783200 100__ $$aAmodeo, Maria$$uCERN$$uTurin Polytechnic$$uU. Naples (main)
002783200 245__ $$9submitter$$aHysteresis Modeling in Iron-Dominated Magnets Based on a Multi-Layered NARX Neural Network Approach
002783200 260__ $$c2021
002783200 300__ $$a18 p
002783200 520__ $$9submitter$$aA full-fledged neural network modeling, based on a Multi-layered Nonlinear Autoregressive Exogenous Neural Network (NARX) architecture, is proposed for quasi-static and dynamic hysteresis loops, one of the most challenging topics for computational magnetism. This modeling approach overcomes drawbacks in attaining better than percent-level accuracy of classical and recent approaches for accelerator magnets, that combine hybridization of standard hysteretic models and neural network architectures. By means of an incremental procedure, different Deep Neural Network Architectures are selected, fine-tuned and tested in order to predict magnetic hysteresis in the context of electromagnets. Tests and results show that the proposed NARX architecture best fits the measured magnetic field behavior of a reference quadrupole at CERN. In particular, the proposed modeling framework leads to a percent error below 0.02% for the magnetic field prediction, thus outperforming state of the art approaches and paving a very promising way for future real time applications.
002783200 540__ $$aCC-BY-NC-ND-4.0$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/
002783200 542__ $$dThe Author(s)$$g2021
002783200 65017 $$2INSPIRE$$aOther
002783200 690C_ $$aARTICLE
002783200 690C_ $$aCERN
002783200 700__ $$aArpaia, Pasquale$$uCERN$$uU. Naples (main)
002783200 700__ $$aBuzio, Marco$$uCERN
002783200 700__ $$aDi Capua, Vincenzo$$uCERN$$uU. Naples (main)
002783200 700__ $$aDonnarumma, Francesco$$uCNR, Italy
002783200 773__ $$c2150033$$n09$$pInt. J. Neural Syst.$$v31$$y2021
002783200 8564_ $$82325721$$s3863710$$uhttp://cds.cern.ch/record/2783200/files/s0129065721500337.pdf$$yFulltext
002783200 960__ $$a13
002783200 980__ $$aARTICLE