Modeling of MOSFETs Altered by Ionizing Radiation Using Artificial Neural Networks
dc.contributor.advisorOrcid | https://orcid.org/0000-0001-7110-7241 | |
dc.contributor.author | SANTOS, L. S. A. DOS | |
dc.contributor.author | ALLEGRO, P. R. P. | |
dc.contributor.author | Marcilei Aparecida Guazzelli | |
dc.contributor.author | GUIDI, A. L. | |
dc.contributor.author | G. JUNIOR, P. R. | |
dc.contributor.author | A. JUNIOR, V. S. | |
dc.contributor.author | TOUFEN, D. L. | |
dc.contributor.author | VILAS BOAS, A. C. | |
dc.date.accessioned | 2023-07-01T06:02:36Z | |
dc.date.available | 2023-07-01T06:02:36Z | |
dc.date.issued | 2023-08-05 | |
dc.description.abstract | © 2023, The Author(s) under exclusive licence to Sociedade Brasileira de Física.The ionizing radiation absorbed by semiconductor devices can change their properties by modifying their electrical parameters and, in the case of memories, it can modify the information contained in these components. Thus, the ability to predict how ionizing radiation affects electronic circuits becomes especially important in environments where there is the possibility of prolonged exposure to intense radiation, such as satellites, nuclear reactors, particle accelerators, and medical equipment, among others. In this sense, this paper proposes a methodology to reproduce the behavior of TID (total ionizing dose) damaged MOSFET transistors using the fully connected artificial neural networks, taking advantage of its universal estimator characteristics to oversample the dataset’s pattern and give it a better resolution. The dataset complexity requires a specific architecture choice, being necessary the use of two neural network models to separately reproduce the MOSFET electric current magnitude order and its curve shape. Results show a very good capability to reproduce and interpolate the MOSFET behavior, which makes the proposed method a promising way to simulate circuits based on MOSFETs that are exposed to ionizing radiation. | |
dc.description.issuenumber | 4 | |
dc.description.volume | 53 | |
dc.identifier.citation | SANTOS, L. S. A. DOS; ALLEGRO, P. R. P.; GUAZZELLI, M. A.; GUIDI, A. L.; G. JUNIOR, P. R.; A. JUNIOR, V. S.; TOUFEN, D. L.; VILAS BOAS, A. C. Modeling of MOSFETS altered by ionizing radiation using artificial neural networks, v. 53, n. 4, aug. 2023. | |
dc.identifier.doi | 10.1007/s13538-023-01307-8 | |
dc.identifier.issn | 1678-4448 | |
dc.identifier.uri | https://repositorio.fei.edu.br/handle/FEI/4852 | |
dc.relation.ispartof | Brazilian Journal of Physics | |
dc.rights | Acesso Restrito | |
dc.subject.otherlanguage | Artificial neural network | |
dc.subject.otherlanguage | MOSFET | |
dc.subject.otherlanguage | TID | |
dc.title | Modeling of MOSFETs Altered by Ionizing Radiation Using Artificial Neural Networks | |
dc.type | Artigo | |
fei.scopus.citations | 1 | |
fei.scopus.eid | 2-s2.0-85160833921 | |
fei.scopus.updated | 2024-12-01 | |
fei.scopus.url | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85160833921&origin=inward |