Vector Hysteresis Processes for Innovative Fe-Si Magnetic Powder Cores: Experiments and Neural Network Modeling

Abstract

A thorough investigation of the 2-D hysteresis processes under arbitrary excitations was carried out for a specimen of innovative Fe-Si magnetic powder material. The vector experimental measurements were first performed via a single disk tester (SDT) apparatus under a controlled magnetic induction field, taking into account circular, elliptic, and scalar processes. The experimental data relative to the circular loops were utilized to identify a vector model of hysteresis based on feedforward neural networks (NNs), having as an input the magnetic induction vector B and as an output the magnetic field vector H. Then the model was validated by the simulation of the other experimental hysteresis processes. The comparison between calculated and measured loops evidenced the capability of the model in both the reconstruction of the magnetic field trajectory and the prediction of the power loss under various excitation waveforms. Finally, the computational efficiency of the model makes it suitable for future application in finite element analysis (FEA).

Neural Network Modeling of Arbitrary Hysteresis Processes: Application to GO Ferromagnetic Steel

“…Feedforward neural networks (FFNNs) became quite popular in modeling nonlinear systems, also accounting for vector problems [8], because they allow a very fast calculation of the output with a reduced occupation of memory. The feedforward architecture is preferred over the others mostly for the abundance of well-established learning algorithms.…”

Special Issue: Advances in Computational Electromagnetics

“…Recent advances in computational electromagnetics (CEMs) have made the full characterization of complex magnetic materials possible, such as superconducting materials, composite or nanomaterials, rare-earth free permanent magnets, etc. Such advances are found in the collection of papers from this Special Issue, where vector properties and the non-linearity of ferromagnetic materials are investigated in [1][2][3][4], while new composite materials for automotive and aircraft are envisaged in [5,6], respectively. Finally, novel deposition techniques for nanomaterials using nonuniform magnetic fields are addressed in [7].…”

“…The obtained results with FEM were in agreement with the ones available in the current literature, demonstrating the validity of their approach. Staying in the field of ferromagnetic materials, but with the aim of characterizing their hysteresis loops, D'Aloia and co-workers [2] and Quondam Antonio and co-workers [3] presented two novel and efficient approaches to deal with. The former was conceptually inspired by the classical Preisach model, but with a more efficient phenomenological representation of the so-called Barkhausen jumps based on velocity jumps between two colliding disks.…”