Inverse Design of Multi-Layer Sub-Pixel-Resolution RF Passives Through Grayscale Diffusion with Flexible S-Parameter Conditioning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913104150921216 |
|---|---|
| author | Dreossi, Tommaso Bryant, Christopher M. Liu, Hao Mirman, Nathan Kessler, Noah Frei, Michael Krishnaswamy, Harish |
| author_facet | Dreossi, Tommaso Bryant, Christopher M. Liu, Hao Mirman, Nathan Kessler, Noah Frei, Michael Krishnaswamy, Harish |
| contents | Inverse design of RF passive components from S-parameters is a high-dimensional, ill-posed problem, and prior generative approaches are limited to single-layer binary-metallization structures. This paper presents an inverse design approach that generates passive components from partial S-parameter inputs on an $8\times8$ mm board discretized at $64\times64$ pixels with sub-pixel grayscale metallization across 1-20 GHz. The framework generates two-layer copper layouts with vias, with hard physical constraints on feed locations enforced through annealed Langevin projection, flexible multi-modal conditioning on partial S-parameter specifications, port locations, dielectric properties, reference topology, and variable port placement. Candidate designs are generated in seconds, with surrogate-predicted S-parameters matching targets to within $0.77 \pm 1.28$ dB weighted mean absolute error. We validate the approach with two fabricated designs on RO4003C: a manufacturable alternative to a hairpin filter whose coupling gaps violate fabrication rules, and a combline bandpass filter designed from scratch given only target S-parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08233 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Inverse Design of Multi-Layer Sub-Pixel-Resolution RF Passives Through Grayscale Diffusion with Flexible S-Parameter Conditioning Dreossi, Tommaso Bryant, Christopher M. Liu, Hao Mirman, Nathan Kessler, Noah Frei, Michael Krishnaswamy, Harish Signal Processing Machine Learning Inverse design of RF passive components from S-parameters is a high-dimensional, ill-posed problem, and prior generative approaches are limited to single-layer binary-metallization structures. This paper presents an inverse design approach that generates passive components from partial S-parameter inputs on an $8\times8$ mm board discretized at $64\times64$ pixels with sub-pixel grayscale metallization across 1-20 GHz. The framework generates two-layer copper layouts with vias, with hard physical constraints on feed locations enforced through annealed Langevin projection, flexible multi-modal conditioning on partial S-parameter specifications, port locations, dielectric properties, reference topology, and variable port placement. Candidate designs are generated in seconds, with surrogate-predicted S-parameters matching targets to within $0.77 \pm 1.28$ dB weighted mean absolute error. We validate the approach with two fabricated designs on RO4003C: a manufacturable alternative to a hairpin filter whose coupling gaps violate fabrication rules, and a combline bandpass filter designed from scratch given only target S-parameters. |
| title | Inverse Design of Multi-Layer Sub-Pixel-Resolution RF Passives Through Grayscale Diffusion with Flexible S-Parameter Conditioning |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2605.08233 |