Comparison of Circuit Models for ML-Assisted Microwave Circuit Design
Uloženo v:
| Název: | Comparison of Circuit Models for ML-Assisted Microwave Circuit Design |
|---|---|
| Autoři: | Sjödin, Martin E, 1983, Talcoth, Oskar, 1980, Chang, Haojie, 1994, Zhou, Han, 1994, Andersson, Kristoffer, 1976 |
| Zdroj: | IEEE Journal of Microwaves. 5(6):1358-1369 |
| Témata: | Circuit optimization, convolutional neural networks, genetic algorithm, electronic circuits, machine learning, surrogate models |
| Popis: | Machine-learning (ML) assisted microwave circuit design is an interesting complement to traditional topology-based design since it opens up previously unexplored design spaces that in some cases may offer better performance, or similar performance with a different form factor. A key part is the circuit model, i.e., the set of discrete building blocks used to create circuits. In the work published so far circuit models encompassed a single element type in the form of metal pixels. In this paper we propose a circuit model with additional elements that facilitates diagonal connections and provides higher robustness to variations in the manufacturing process. A comparison with the pixel model shows that the new model results in more accurate ML-models for S-parameter prediction with a 9.5% reduction in root mean-square error (RMSE) on the testset, which translates to more accurate results for circuit synthetization. In addition, we demonstrate that circuits built with the new model has a higher tolerance to manufacturing imperfections, with 33% smaller RMSE penalty with respect to the original S-parameters when adding a width perturbation of 50 μm to diagonal connections, and 50/40% smaller RMSE penalty when shrinking/expanding the size of elements forming diagonal connections with 2.5% . We also use both the pixel model and the newly proposed model to design low-pass filters with competitive performance. |
| Popis souboru: | electronic |
| Přístupová URL adresa: | https://research.chalmers.se/publication/548742 https://research.chalmers.se/publication/548742/file/548742_Fulltext.pdf |
| Databáze: | SwePub |
Nájsť tento článok vo Web of Science | Abstrakt: | Machine-learning (ML) assisted microwave circuit design is an interesting complement to traditional topology-based design since it opens up previously unexplored design spaces that in some cases may offer better performance, or similar performance with a different form factor. A key part is the circuit model, i.e., the set of discrete building blocks used to create circuits. In the work published so far circuit models encompassed a single element type in the form of metal pixels. In this paper we propose a circuit model with additional elements that facilitates diagonal connections and provides higher robustness to variations in the manufacturing process. A comparison with the pixel model shows that the new model results in more accurate ML-models for S-parameter prediction with a 9.5% reduction in root mean-square error (RMSE) on the testset, which translates to more accurate results for circuit synthetization. In addition, we demonstrate that circuits built with the new model has a higher tolerance to manufacturing imperfections, with 33% smaller RMSE penalty with respect to the original S-parameters when adding a width perturbation of 50 μm to diagonal connections, and 50/40% smaller RMSE penalty when shrinking/expanding the size of elements forming diagonal connections with 2.5% . We also use both the pixel model and the newly proposed model to design low-pass filters with competitive performance. |
|---|---|
| ISSN: | 26928388 |
| DOI: | 10.1109/JMW.2025.3610923 |