Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning
An iterative optimization for decoupling capacitor placement on a power delivery network (PDN) is presented based on Genetic Algorithm (GA) and Artificial Neural Network (ANN). The ANN is first trained by an appropriate set of results obtained by a commercial simulator. Once the ANN is ready, it is...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/9/8/1243 |
_version_ | 1797560553573449728 |
---|---|
author | Riccardo Cecchetti Francesco de Paulis Carlo Olivieri Antonio Orlandi Markus Buecker |
author_facet | Riccardo Cecchetti Francesco de Paulis Carlo Olivieri Antonio Orlandi Markus Buecker |
author_sort | Riccardo Cecchetti |
collection | DOAJ |
description | An iterative optimization for decoupling capacitor placement on a power delivery network (PDN) is presented based on Genetic Algorithm (GA) and Artificial Neural Network (ANN). The ANN is first trained by an appropriate set of results obtained by a commercial simulator. Once the ANN is ready, it is used within an iterative GA process to place a minimum number of decoupling capacitors for minimizing the differences between the input impedance at one or more location, and the required target impedance. The combined GA–ANN process is shown to effectively provide results consistent with those obtained by a longer optimization based on commercial simulators. With the new approach the accuracy of the results remains at the same level, but the computational time is reduced by at least 30 times. Two test cases have been considered for validating the proposed approach, with the second one also being compared by experimental measurements. |
first_indexed | 2024-03-10T18:01:21Z |
format | Article |
id | doaj.art-a0f080086b56421d9e2eb424bb7e002b |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T18:01:21Z |
publishDate | 2020-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-a0f080086b56421d9e2eb424bb7e002b2023-11-20T08:50:55ZengMDPI AGElectronics2079-92922020-08-0198124310.3390/electronics9081243Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine LearningRiccardo Cecchetti0Francesco de Paulis1Carlo Olivieri2Antonio Orlandi3Markus Buecker4UAq EMC Laboratory, Dept. of Industrial and Information Engineering and Economics, University of L’Aquila, 64100 L’Aquila, ItalyUAq EMC Laboratory, Dept. of Industrial and Information Engineering and Economics, University of L’Aquila, 64100 L’Aquila, ItalyUAq EMC Laboratory, Dept. of Industrial and Information Engineering and Economics, University of L’Aquila, 64100 L’Aquila, ItalyUAq EMC Laboratory, Dept. of Industrial and Information Engineering and Economics, University of L’Aquila, 64100 L’Aquila, ItalyZuken GmbH, 33104 Paderborn, GermanyAn iterative optimization for decoupling capacitor placement on a power delivery network (PDN) is presented based on Genetic Algorithm (GA) and Artificial Neural Network (ANN). The ANN is first trained by an appropriate set of results obtained by a commercial simulator. Once the ANN is ready, it is used within an iterative GA process to place a minimum number of decoupling capacitors for minimizing the differences between the input impedance at one or more location, and the required target impedance. The combined GA–ANN process is shown to effectively provide results consistent with those obtained by a longer optimization based on commercial simulators. With the new approach the accuracy of the results remains at the same level, but the computational time is reduced by at least 30 times. Two test cases have been considered for validating the proposed approach, with the second one also being compared by experimental measurements.https://www.mdpi.com/2079-9292/9/8/1243machine learningartificial neural networkdecoupling capacitorspower delivery networkgenetic algorithmtwin removal |
spellingShingle | Riccardo Cecchetti Francesco de Paulis Carlo Olivieri Antonio Orlandi Markus Buecker Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning Electronics machine learning artificial neural network decoupling capacitors power delivery network genetic algorithm twin removal |
title | Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning |
title_full | Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning |
title_fullStr | Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning |
title_full_unstemmed | Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning |
title_short | Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning |
title_sort | effective pcb decoupling optimization by combining an iterative genetic algorithm and machine learning |
topic | machine learning artificial neural network decoupling capacitors power delivery network genetic algorithm twin removal |
url | https://www.mdpi.com/2079-9292/9/8/1243 |
work_keys_str_mv | AT riccardocecchetti effectivepcbdecouplingoptimizationbycombininganiterativegeneticalgorithmandmachinelearning AT francescodepaulis effectivepcbdecouplingoptimizationbycombininganiterativegeneticalgorithmandmachinelearning AT carloolivieri effectivepcbdecouplingoptimizationbycombininganiterativegeneticalgorithmandmachinelearning AT antonioorlandi effectivepcbdecouplingoptimizationbycombininganiterativegeneticalgorithmandmachinelearning AT markusbuecker effectivepcbdecouplingoptimizationbycombininganiterativegeneticalgorithmandmachinelearning |