Mathematical optimization and machine learning to support PCB topology identification
<p>In this paper, we study an identification problem for schematics with different concurring topologies. A framework is proposed, that is both supported by mathematical optimization and machine learning algorithms. Through the use of Python libraries, such as scikit-rf, which allows for the e...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
Copernicus Publications
2023-12-01
|
| Series: | Advances in Radio Science |
| Online Access: | https://ars.copernicus.org/articles/21/25/2023/ars-21-25-2023.pdf |
| _version_ | 1797435502811414528 |
|---|---|
| author | I. Cahani M. Stiemer |
| author_facet | I. Cahani M. Stiemer |
| author_sort | I. Cahani |
| collection | DOAJ |
| description | <p>In this paper, we study an identification problem for schematics with different concurring topologies. A framework is proposed, that is both supported by mathematical optimization and machine learning algorithms. Through the use of Python libraries, such as scikit-rf, which allows for the emulation of network analyzer measurements, and a physical microstrip line simulation on PCBs, data for training and testing the framework are provided. In addition to an individual treatment of the concurring topologies and subsequent comparison, a method is introduced to tackle the identification of the optimum topology directly via a standard optimization or machine learning setup: An encoder-decoder sequence is trained with schematics of different topologies, to generate a <i>flattened</i> representation of the rated graph representation of the considered schematics. Still containing the relevant topology information in encoded (i.e., flattened) form, the so obtained latent space representations of schematics can be used for standard optimization of machine learning processes. Using now the encoder to map schematics on latent variables or the decoder to reconstruct schematics from their latent space representation, various machine learning and optimization setups can be applied to treat the given identification task. The proposed framework is presented and validated for a small model problem comprising different circuit topologies.</p> |
| first_indexed | 2024-03-09T10:48:59Z |
| format | Article |
| id | doaj.art-1550d013f6e04f5c89b9f49c93cd51dc |
| institution | Directory Open Access Journal |
| issn | 1684-9965 1684-9973 |
| language | deu |
| last_indexed | 2024-03-09T10:48:59Z |
| publishDate | 2023-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Advances in Radio Science |
| spelling | doaj.art-1550d013f6e04f5c89b9f49c93cd51dc2023-12-01T08:47:11ZdeuCopernicus PublicationsAdvances in Radio Science1684-99651684-99732023-12-0121253510.5194/ars-21-25-2023Mathematical optimization and machine learning to support PCB topology identificationI. CahaniM. Stiemer<p>In this paper, we study an identification problem for schematics with different concurring topologies. A framework is proposed, that is both supported by mathematical optimization and machine learning algorithms. Through the use of Python libraries, such as scikit-rf, which allows for the emulation of network analyzer measurements, and a physical microstrip line simulation on PCBs, data for training and testing the framework are provided. In addition to an individual treatment of the concurring topologies and subsequent comparison, a method is introduced to tackle the identification of the optimum topology directly via a standard optimization or machine learning setup: An encoder-decoder sequence is trained with schematics of different topologies, to generate a <i>flattened</i> representation of the rated graph representation of the considered schematics. Still containing the relevant topology information in encoded (i.e., flattened) form, the so obtained latent space representations of schematics can be used for standard optimization of machine learning processes. Using now the encoder to map schematics on latent variables or the decoder to reconstruct schematics from their latent space representation, various machine learning and optimization setups can be applied to treat the given identification task. The proposed framework is presented and validated for a small model problem comprising different circuit topologies.</p>https://ars.copernicus.org/articles/21/25/2023/ars-21-25-2023.pdf |
| spellingShingle | I. Cahani M. Stiemer Mathematical optimization and machine learning to support PCB topology identification Advances in Radio Science |
| title | Mathematical optimization and machine learning to support PCB topology identification |
| title_full | Mathematical optimization and machine learning to support PCB topology identification |
| title_fullStr | Mathematical optimization and machine learning to support PCB topology identification |
| title_full_unstemmed | Mathematical optimization and machine learning to support PCB topology identification |
| title_short | Mathematical optimization and machine learning to support PCB topology identification |
| title_sort | mathematical optimization and machine learning to support pcb topology identification |
| url | https://ars.copernicus.org/articles/21/25/2023/ars-21-25-2023.pdf |
| work_keys_str_mv | AT icahani mathematicaloptimizationandmachinelearningtosupportpcbtopologyidentification AT mstiemer mathematicaloptimizationandmachinelearningtosupportpcbtopologyidentification |