Method and device for extracting parameters of through-silicon-via inductance equivalent circuit based on neural network
The invention discloses a method and a device for extracting equivalent circuit parameters of a silicon through hole inductor based on a neural network. The equivalent circuit of the silicon through hole inductor in a three-dimensional integrated circuit is extracted so as to achieve the purpose of...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a method and a device for extracting equivalent circuit parameters of a silicon through hole inductor based on a neural network. The equivalent circuit of the silicon through hole inductor in a three-dimensional integrated circuit is extracted so as to achieve the purpose of efficiently obtaining electrical parameters of the silicon through hole inductor. The specific structure of a two-port equivalent circuit is designed according to the characteristics of the through-silicon-via inductor, a simple artificial neural network model is constructed to extract the through-silicon-via inductor equivalent circuit, the input of the network is design parameters of the through-silicon-via inductor and theoretically calculated inductance, and the output of the network is element values in the equivalent circuit. The model can be used for extracting an equivalent circuit and calculating the Y parameter of the silicon through hole inductor. According to the method and the device, the through-silic |
---|