Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits
Abstract Millimeter-wave and terahertz integrated circuits and chips are expected to serve as the backbone for future wireless networks and high resolution sensing. However, design of these integrated circuits and chips can be quite complex, requiring years of human expertise, careful tailoring of h...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-54178-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559396075700224 |
|---|---|
| author | Emir Ali Karahan Zheng Liu Aggraj Gupta Zijian Shao Jonathan Zhou Uday Khankhoje Kaushik Sengupta |
| author_facet | Emir Ali Karahan Zheng Liu Aggraj Gupta Zijian Shao Jonathan Zhou Uday Khankhoje Kaushik Sengupta |
| author_sort | Emir Ali Karahan |
| collection | DOAJ |
| description | Abstract Millimeter-wave and terahertz integrated circuits and chips are expected to serve as the backbone for future wireless networks and high resolution sensing. However, design of these integrated circuits and chips can be quite complex, requiring years of human expertise, careful tailoring of hand crafted circuit topologies and co-design with parameterized and pre-selected templates of electromagnetic structures. These structures (radiative and non-radiative, single-port and multi-ports) are subsequently optimized through ad-hoc methods and parameter sweeps. Such bottom-up approaches with pre-selected regular topologies also fundamentally limit the design space. Here, we demonstrate a universal inverse design approach for arbitrary-shaped complex multi-port electromagnetic structures with designer radiative and scattering properties, co-designed with active circuits. To allow such universalization, we employ deep learning based models, and demonstrate synthesis with several examples of complex mm-Wave passive structures and end-to-end integrated mm-Wave broadband circuits. The presented inverse design methodology, that produces the designs in minutes, can be transformative in opening up a new, previously inaccessible design space. |
| format | Article |
| id | doaj-art-d3d2d558a80945c987fdbbd533ce1e36 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-d3d2d558a80945c987fdbbd533ce1e362025-01-05T12:35:02ZengNature PortfolioNature Communications2041-17232024-12-0115111310.1038/s41467-024-54178-1Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuitsEmir Ali Karahan0Zheng Liu1Aggraj Gupta2Zijian Shao3Jonathan Zhou4Uday Khankhoje5Kaushik Sengupta6Department of Electrical and Computer Engineering, Princeton UniversityDepartment of Electrical and Computer Engineering, Princeton UniversityDepartment of Electrical Engineering, Indian Institute of Technology MadrasDepartment of Electrical and Computer Engineering, Princeton UniversityDepartment of Electrical and Computer Engineering, Princeton UniversityDepartment of Electrical Engineering, Indian Institute of Technology MadrasDepartment of Electrical and Computer Engineering, Princeton UniversityAbstract Millimeter-wave and terahertz integrated circuits and chips are expected to serve as the backbone for future wireless networks and high resolution sensing. However, design of these integrated circuits and chips can be quite complex, requiring years of human expertise, careful tailoring of hand crafted circuit topologies and co-design with parameterized and pre-selected templates of electromagnetic structures. These structures (radiative and non-radiative, single-port and multi-ports) are subsequently optimized through ad-hoc methods and parameter sweeps. Such bottom-up approaches with pre-selected regular topologies also fundamentally limit the design space. Here, we demonstrate a universal inverse design approach for arbitrary-shaped complex multi-port electromagnetic structures with designer radiative and scattering properties, co-designed with active circuits. To allow such universalization, we employ deep learning based models, and demonstrate synthesis with several examples of complex mm-Wave passive structures and end-to-end integrated mm-Wave broadband circuits. The presented inverse design methodology, that produces the designs in minutes, can be transformative in opening up a new, previously inaccessible design space.https://doi.org/10.1038/s41467-024-54178-1 |
| spellingShingle | Emir Ali Karahan Zheng Liu Aggraj Gupta Zijian Shao Jonathan Zhou Uday Khankhoje Kaushik Sengupta Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits Nature Communications |
| title | Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits |
| title_full | Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits |
| title_fullStr | Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits |
| title_full_unstemmed | Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits |
| title_short | Deep-learning enabled generalized inverse design of multi-port radio-frequency and sub-terahertz passives and integrated circuits |
| title_sort | deep learning enabled generalized inverse design of multi port radio frequency and sub terahertz passives and integrated circuits |
| url | https://doi.org/10.1038/s41467-024-54178-1 |
| work_keys_str_mv | AT emiralikarahan deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT zhengliu deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT aggrajgupta deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT zijianshao deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT jonathanzhou deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT udaykhankhoje deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits AT kaushiksengupta deeplearningenabledgeneralizedinversedesignofmultiportradiofrequencyandsubterahertzpassivesandintegratedcircuits |