Broadband scalable compact circuit model for on‐chip spiral inductors by neural network

Abstract

A scalable model combining the advantages of the compact model and space‐mapping neural network (SMNN) has been presented to characterize radio‐frequency behaviors of on‐chip spiral inductors. The physics‐based T equivalent circuit model has been used for constructing the proposed scalable SMNN model. All values of the T model elements are fast and accurately extracted based on the mathematical formulations derived by analyzing the resonant responses. A 4‐layer perceptron neural network has been applied for the space mapping of the T model and the measurement data. Compared with the conventional models of on‐chip spiral inductors, the proposed SMNN model not only preserves the accuracy of measurement data but also runs as fast as an approximate compact model. The presented SMNN model has been verified by a series of octagon spiral inductors fabricated by 130‐nm BiCMOS process of HHNEC. Excellent agreements are obtained between the measurement and simulation of the proposed SMNN model up to 40 GHz.

Design of an on-chip Hilbert fractal inductor using an improved feed forward neural network for Si RFICs

“…A feed forward neural network trained using a multilayer perception neural network was developed to design an octagonal inductor [19], a rounded spiral inductor [20], and a rectangular inductor [21]. Generalized knowledge-based neural network (GKBNN) [22] and space mapping neural network (SMNN) [23] were developed to design rounded spiral inductors. Similarly, knowledge-based frequency-dependent space-mapping neural network (KB-FDSMN) [24], combined neural network, transfer function [25], and physics-based sampling neural network [26] were proposed for the design of rectangular spiral inductors.…”

Surrogate modeling and variability analysis of on‐chip spiral inductors

“…1 Various approaches have been proposed to model, synthesize, and optimize these structures to attain the highest performance. [2][3][4][5] The trend of using integrated spiral inductors instead of traditional discrete ones brought about the need for their thorough analysis. Therefore, a fast analytical method with high accuracy is required for consultation by designers while constructing an integrated circuit or an inductor.…”