Conure: Surrogate-based Artwork Generator for RFCMOS Integrated Inductors

Designing integrated inductors can be a resource-intensive task, requiring computationally demanding electromagnetic simulations and relying on libraries constrained by the capabilities offered by foundries. In this paper, we present a surrogate-based artwork generator for integrated inductor design: Conure. The surrogate model is based on a single artificial neural network that predicts the inductor’s performance over a frequency range of 1MHz to 50GHz from geometric parameters. It is capable of processing diverse coil configurations for the entire frequency range in a single model. Additionally, the optimization algorithm NSGA-II has been applied to derive design parameters that meet desired specifications. Conure is a promising approach for complete CMOS RF passive component design. The presented model is trained using data from electromagnetic simulations of coplanar symmetric octagonal inductors in 65nm CMOS. However, Conure can be scaled to other processes, inductor geometries, and frequencies.