Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Addressing a new class of multi-objective passive device optimization for radiofrequency circuit design

  • Passos, Fábio
  • Roca, Elisenda
  • Castro-López, Rafael
  • Fernández, Francisco V.
This article belongs to the Collection Advanced Design Techniques and EDA Methodologies for Analog, RF and MM-Wave Circuit Design., The design of radiofrequency circuits and systems lends itself to multi-objective optimization and the bottom-up composition of Pareto-optimal fronts. Conventional multi-objective optimization algorithms can effectively attain these fronts, which maximize or minimize a set of competing objective functions of interest. However, some of these real-life optimization problems reveal a non-conventional feature: there is one objective function that calls neither for minimization nor maximization. Instead, using the Pareto front demands this objective function to be swept across so that all its feasible values are available. Such a non-conventional feature, as shown here, emerges in the case of inductor optimization. The problem thus turns into a non-conventional one: determining how to find uniformly distributed feasible values of this function over the broadest possible range (typically unknown) while minimizing or maximizing the remaining competing objective functions. An NSGA-II-inspired algorithm is proposed that, based on the dynamic allocation of objective function slots and a modified dominance definition, can successfully return sets of solutions for inductor optimization problems with one sweeping objective. Furthermore, a mathematical benchmark function modeling this kind of problem is presented, which is also used to exhaustively test the proposed algorithm and obtain insight into its parameter settings., This work was supported by grant PID2019-103869RB-C31 funded by MCIN/AEI/10.13039/501100011033. Fabio Passos’ work was also supported by the European Union’s Horizon 2020 research and innovation program under the MSCA grant agreement No. 892431., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

PACOSYT: A Passive Component Synthesis Tool Based on Machine Learning and Tailored Modeling Strategies Towards Optimal RF and mm-Wave Circuit Designs

  • Passos, Fábio
  • Lourenco, Nuno
  • Roca, Elisenda
  • Martins, Ricardo
  • Castro-López, Rafael
  • Horta, Nuno
  • Fernández, Francisco V.
In this paper, the application of regression-based supervised machine learning (ML) methods to the modeling of integrated inductors and transformers is examined. Different ML techniques are used and compared to improve accuracy. However, it is demonstrated that none of the ML techniques considered provided good results unless a smart modeling strategy, tailored to the specific design problem, is used. Taking advantage of these modeling strategies, high accuracy can be obtained when compared to full-wave electromagnetic (EM) simulations (less than 2% error) and experimental measurements (less than 5% error). The most accurate model, obtained by the appropriate combination of an ML technique and modeling strategy, has been integrated into a tool called PACOSYT. The tool uses optimization algorithms to allow the designer to obtain an inductor/transformer with optimal performances in just seconds while keeping the accuracy of EM simulations. Furthermore, the tool provides the passive component S parameter description file for seamless use in circuit simulations. The tool can be used standalone or integrated with design frameworks, like Cadence Virtuoso or AIDASoft, a framework for circuit optimization. To illustrate the different usages of the tool, several passive devices are synthesized, and hundreds of millimeter-wave power amplifiers are synthesized using AIDASoft together with PACOSYT. The tool has been developed using open-source Python frameworks and does not use any closed-source licenses. PACOSYT, which also allows other designers to create their models for different technologies, is made publicly available., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program under MSCA Grant Agreement 892431, in part by the Instituto de Telecomunicações Internal Research Projects under Grants LAY(RF)2 (X-0002-LX-20) and HAICAS (X-0009-LX-20), in part by MCIN/AEI/10.13039/ 501100011033 under Grant PID2019-103869RB-C31, and in part by FCT/MCTES through National Funds and when applicable co-funded EU funds under Project UIDB/50008/2020., Peer reviewed