Neural Network Architectures and Magnetic Hysteresis - Overview and Comparisons

• DOI: 10.20944/preprints202409.2246.v1
• Publication Date: 2024-09-30T02:53:29Z
• Authors: Silvia Licciardi; Guido Ala; Elisa Francomano; Fabio Viola; Michele Lo Giudice; Alessandro Salvini; Fausto Sargeni; Vincenzo Bonaiuto; Andrea Di Schino; Antonio Faba
• Keywords: Settore ING-IND/31; global optimization; numerical methods; hybrid neural networks architectures; QA1-939; deep learning; LSTM architectures; Settore IIET-01/A - Elettrotecnica; magnetic hysteresis; gradient methods; Mathematics; Preisach model

The development of innovative materials, based on the modern technologies and processes, is the key factor to improve the energetic sustainability and reduce the environmental impact of the electrical equipment. In particular, modeling of magnetic hysteresis is crucial for the design and construction of electrical and electronic devices. In recent years, additive manufacturing techniques are playing a decisive role in the project and production of magnetic elements and circuits for applications in various engineering fields. To this aim, the use of Deep learning paradigm, integrated with the most common models of the magnetic hysteresis process, has become increasingly present in recent years. Particularly in the paper, different Neural networks used in scientific literature, integrated with various hysteretic mathematical models, including the well-known Preisach model, are compared. It is shown that this hybrid approach not only improves the modelling of hysteresis by significantly reducing computational time and efforts, but also offers new perspectives for analysis and prediction of the behavior of magnetic materials, with significant implications for the production of advanced devices.