Effective PCB Decoupling Optimization by Combining an Iterative Genetic Algorithm and Machine Learning

Abstract

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.

Automated Placement of Decoupling Capacitors on a Printed Circuit Board by Genetic Algorithm

“…В [2]- [4] рассматриваются варианты анализа входного импеданса, однако расположение развязывающих конденсаторов осуществляется в фиксированные позиции. В [5]- [9] расположение развязывающих конденсаторов осуществляется в некоторых областях печатной платы, однако при этом не учитывается размещение остальных элементов устройства.…”

Tree-Based Machine Learning Models with Optuna in Predicting Impedance Values for Circuit Analysis

“…According to the finding of their study, using machine learning techniques logically can eliminate errors in the design process and thus, reduce design cycle time. Meanwhile, Cecchetti et al [ 12 ] proposed an iterative optimization for the placement of decoupling capacitors in PDNs based on genetic algorithms (GA) and artificial neural networks (ANN). The study revealed that the designed GA-ANN model effectively produced results consistent with those obtained from the simulator generating a longer computation time.…”

Fast impedance prediction for power distribution network using deep learning

“…In recent years, the success of deep learning for complex and non-linear problems like computer vision, 6 natural language processing, 7 and strategy games 8 has also impacted many other fields. There has been some research [9][10][11][12] in applying machine learning in PDN modeling and optimization. However, most of these works do not have a welltrained and generalized machine learning model for PDN impedance prediction at the PCB level.…”