Recovery of Intrinsic Heterojunction Bipolar Transistors Profiles by Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Recovery of Intrinsic Heterojunction Bipolar Transistors Profiles by Neural Networks

Nicolas Guitard
  • Fonction : Auteur
  • PersonId : 1112352
Didier Celi
  • Fonction : Auteur
  • PersonId : 1219238

Résumé

Due to the shrinking size of devices, the calibration process for TCAD simulators is becoming increasingly complex with time mandatory to run simulations steadily increasing. In this work, we propose a Statistical Learning approach to predicting Figures of Merit (FoMs) of a Silicon Germanium Heterojunction bipolar transistor (HBT) 1D doping and germanium profile. The surrogate model thus built allows to simulate electrical outputs with high precision much faster than traditional simulations. This model is then used to solve the inverse design problem and recover profiles that match target FoMs.
Fichier non déposé

Dates et versions

hal-03954870 , version 1 (24-01-2023)

Identifiants

Citer

Grégoire Caron, Anatoli B. Juditsky, Nicolas Guitard, Didier Celi. Recovery of Intrinsic Heterojunction Bipolar Transistors Profiles by Neural Networks. BCICTS 2022, IEEE BiCMOS and Compound Semiconductor Integrated Circuits and Technology Symposium, IEEE, Oct 2022, Phoenix, Arizona USA, United States. pp.228-231, ⟨10.1109/BCICTS53451.2022.10051699⟩. ⟨hal-03954870⟩
23 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More