Dynamic Ferromagnetic Hysteresis Modelling Using a Preisach-Recurrent Neural Network Model

In this work, a Preisach-recurrent neural network model is proposed to predict the dynamic hysteresis in ARMCO pure iron, an important soft magnetic material in particle accelerator magnets. A recurrent neural network coupled with Preisach play operators is proposed, along with a novel validation method for the identification of the model’s parameters. The proposed model is found to predict the magnetic flux density of ARMCO pure iron with a Normalised Root Mean Square Error (NRMSE) better than 0.7%, when trained with just six different hysteresis loops. The model is evaluated using ramp-rates not used in the training procedure, which shows the ability of the model to predict data which has not been measured. The results demonstrate that the Preisach model based on a recurrent neural network can accurately describe ferromagnetic dynamic hysteresis when trained with a limited amount of data, showing the model’s potential in the field of materials science.

[1]  G. Biorci,et al.  Analytical theory of the behaviour of ferromagnetic materials , 1958 .

[2]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[3]  Isaak D. Mayergoyz,et al.  Dynamic Preisach models of hysteresis , 1988 .

[4]  Pavel Krejčí.  On Maxwell equations with the Preisach hysteresis operator: The one- dimensional time-periodic case , 1989 .

[5]  M. Brokate,et al.  Some mathematical properties of the Preisach model for hysteresis , 1989 .

[6]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[7]  Laure-Line Rouve,et al.  Application of Preisach model to grain oriented steels: comparison of different characterizations for the Preisach function p(/spl alpha/, /spl beta/) , 1995 .

[8]  D. A. Lowther,et al.  The use of neural networks in magnetic hysteresis identification , 1997 .

[9]  D.A. Lowther,et al.  A Neural Network Model Of Magnetic Hysteresis For Computational Magnetics , 1997, 1997 IEEE International Magnetics Conference (INTERMAG'97).

[10]  Amr A. Adly,et al.  Using neural networks in the identification of Preisach-type hysteresis models , 1998 .

[11]  C. Visone,et al.  Magnetic hysteresis modeling via feed-forward neural networks , 1998 .

[12]  J. D. Lavers,et al.  Eddy-current power loss in toroidal cores with rectangular cross section , 1998 .

[13]  Dongwoo Song,et al.  Modeling of piezo actuator’s nonlinear and frequency dependent dynamics , 1999 .

[14]  János Füzi,et al.  Computationally efficient rate dependent hysteresis model , 1999 .

[15]  J. P. Castagna,et al.  Avoiding overfitting caused by noise using a uniform training mode , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[16]  Ridha Ben Mrad,et al.  Dynamic modeling of hysteresis in piezoceramics , 2001, 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Proceedings (Cat. No.01TH8556).

[17]  Ciro Visone,et al.  Identification and compensation of Preisach hysteresis models for magnetostrictive actuators , 2001 .

[18]  Andrew Nafalski,et al.  Dynamic magnetic hysteresis modelling using Elman recurrent neural network , 2002 .

[19]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[20]  I. D. Mayergoyz.  CHAPTER 1 – The Classical Preisach Model of Hysteresis , 2003 .

[21]  L. Dupré,et al.  Dynamic hysteresis modelling using feed-forward neural networks , 2003 .

[22]  John S. Baras,et al.  Modeling and control of hysteresis in magnetostrictive actuators , 2004, Autom..

[23]  Chun-Yi Su,et al.  On the Control of Plants with Hysteresis: Overview and a Prandtl-Ishlinskii Hysteresis Based Control Approach , 2005 .

[24]  Martin Kozek,et al.  Identification and Inversion of Magnetic Hysteresis for Sinusoidal Magnetization , 2005, Int. J. Online Eng..

[25]  Hans-Georg Zimmermann,et al.  Recurrent Neural Networks are Universal approximators , 2007, Int. J. Neural Syst..

[26]  Y. Yao,et al.  On Early Stopping in Gradient Descent Learning , 2007 .

[27]  Alireza Sadeghian,et al.  Neural network modeling of magnetic hysteresis , 2008, 2008 IEEE International Conference on Emerging Technologies and Factory Automation.

[28]  R. Iyer,et al.  Control of hysteretic systems through inverse compensation , 2009, IEEE Control Systems.

[29]  Mohsen Firouzi,et al.  Hysteresis nonlinearity identification by using RBF neural network approach , 2010, 2010 18th Iranian Conference on Electrical Engineering.

[30]  Alexander Sutor,et al.  A Preisach-based hysteresis model for magnetic and ferroelectric hysteresis , 2010 .

[31]  Pasquale Arpaia,et al.  High-performance permeability measurements: A case study at CERN , 2010, 2010 IEEE Instrumentation & Measurement Technology Conference Proceedings.

[32]  S. Sgobba.  Physics and measurements of magnetic materials , 2011 .

[33]  Lutz Prechelt,et al.  Early Stopping - But When? , 2012, Neural Networks: Tricks of the Trade.

[34]  Torsten Bertram,et al.  Identification of Soft Magnetic B-H Characteristics Using Discrete Dynamic Preisach Model and Single Measured Hysteresis Loop , 2012, IEEE Transactions on Magnetics.

[35]  D. Suess,et al.  An Eddy-Current Model Describing the Frequency Dependence of the Coercivity of Polycrystalline Galfenol , 2012, IEEE Transactions on Magnetics.

[36]  M. Kuczmann,et al.  Dynamic Preisach model identification applying FEM and measured BH curve , 2014 .

[37]  Jon Åge Stakvik.  Identification, Inversion and Implementaion of the Preisach Hysteresis Model in Nanopositioning , 2014 .

[38]  Qi Zhang,et al.  Hysteresis Model of Magnetically Controlled Shape Memory Alloy Based on a PID Neural Network , 2015, IEEE Transactions on Magnetics.

[39]  Mit Critical Data.  Secondary Analysis of Electronic Health Records , 2016 .

[40]  Matthieu Komorowski,et al.  Sensitivity Analysis and Model Validation , 2016 .

[41]  R. Xu,et al.  Elman neural network-based identification of Krasnosel'skii-Pokrovskii model for magnetic shape memory alloys actuator , 2017, 2017 IEEE International Magnetics Conference (INTERMAG).

[42]  A. Liccardo,et al.  Magnetic Properties of Pure Iron for the Upgrade of the LHC Superconducting Dipole and Quadrupole Magnets , 2019, IEEE Transactions on Magnetics.

[43]  Yasser Fouad,et al.  Identification of Preisach hysteresis model parameters using genetic algorithms , 2017, Journal of King Saud University - Science.

[44]  Pasquale Arpaia,et al.  A Superconducting Permeameter for Characterizing Soft Magnetic Materials at High Fields , 2020, IEEE Transactions on Instrumentation and Measurement.

[45]  Pasquale Arpaia,et al.  Characterization of Magnetic Steels for the FCC-ee Magnet Prototypes , 2020, 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).