Parametric S-Parameters for PCB based Power Delivery Network Design Using Machine Learning

Schierholz, Morten; Erdin, Ihsan; Balachandran, Jayaprakash; Yang, Cheng Fu; Schuster, Christian

doi:10.1109/spi54345.2022.9874946

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we demonstrated the potential of our neural network for designing the grid ground plane by comparing it with a traditional 3D field solver. This confirms the effectiveness of neural networks in electromagnetic modeling and parameter prediction, as previously shown in other studies [29][30][31][32][33][34][35][36]. Given its predictive capability, the model represents a powerful tool for system-level simulation and optimization, eliminating the need for tedious and repetitive simulation processes and saving significant time and computational resources.…”

Section: Discussionsupporting

confidence: 86%

“…ML models have high simulation speeds and do not need to fully understand the internal structure of modeling objects. Thus, S-parameter modeling technology based on ANNs has attracted increasing attention, and preliminary feasibility studies have been recently carried out [33][34][35][36]. While both SVMs and ANNs demonstrate efficacy in fitting, they have yet to be extensively applied in grid ground plane design parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Prediction Method for Scattering Parameters of Rigid-Flex PCBs Based on ANN

Mei,

Yuan,

Guo

et al. 2024

Sensors

View full text Add to dashboard Cite

InGaAs detection systems have been increasingly used in the aerospace field, and due to the high signal-to-noise ratio requirements of short-wave infrared quantitative payloads, there is an urgent need for methods for the rapid and precise evaluation and the optimal design of these systems. The rigid-flex printed circuit board (PCB) is a vital component of InGaAs detectors, as its grid ground plane design parameters impact parasitic capacitance and thus affect weak infrared analog signals. To address the time-intensive and costly nature of design optimization achieved with simulations and experimental measurements, we propose an innovative method based on a neural network to predict the scattering parameters of rigid-flex boards for InGaAs detection links. This is the first study in which the effects of rigid-flex boards on weak infrared detection signals have been considered. We first obtained sufficient samples with software simulation. A backpropagation (BP) neural network prediction model was trained on existing sample sets and then verified on a rigid-flex board used in a crucial aerospace short-wave infrared quantitative mission. The model efficiently and accurately predicted high-speed interconnect scattering parameters under various rigid-flex board grid plane parameter conditions. The prediction error was less than 1% compared with a 3D field solver, indicating an overcoming of the iterative optimization inefficiency and showing improved design quality for InGaAs detection circuits.

show abstract

Section: Discussionsupporting

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Fast Prediction Method for Scattering Parameters of Rigid-Flex PCBs Based on ANN

Mei,

Yuan,

Guo

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…A brief elucidation of the chosen delay estimation algorithm is hereby shown for the S 11 of three coupled (10), respectively. Note that, the total number of pole/residue pairs for DVF depends on the number of delays and is equal to M × C, as indicated in (9).…”

Section: Delay Estimation Via Gabor Transformmentioning

confidence: 99%

“…In recent years, several machine learning techniques, such as artificial neural networks (ANN) [7], [8], [9] or support vector machines (SVM) [10] have shown improved accuracy in interconnects macromodeling, especially for a large number of ports and design parameters. However, while ANNs are able to model high-dimensional and nonlinear functions, they require a high amount of training data and they tend to overfit.…”

mentioning

confidence: 99%

Modeling Electrically Long Interconnects Using Physics-Informed Delayed Gaussian Processes

Garbuglia,

Reuschel,

Schuster

et al. 2023

IEEE Trans. Electromagn. Compat.

Self Cite

View full text Add to dashboard Cite

This work presents a machine learning technique to model wide-band scattering parameters (S-parameters) of interconnects in the frequency domain using a new Gaussian processes (GP) model. Standard GPs with a general-purpose kernel typically assume high smoothness and therefore are not suitable to model S-parameters that are highly dynamic and oscillating due to propagation delays. The new delayed Gaussian process (τ GP) model employs a physics-informed kernel consisting of periodic components, whose fundamental frequencies are interpreted as tunable propagation delays. Then, the model hyperparameters are tuned using a combination of maximum marginal likelihood estimation (MMLE) and delay estimation using Gabor transform. The delay estimation allows one to automatically identify the optimal fundamental frequencies for the kernel, thus increasing the numerical stability of the hyperparameters tuning process. The resulting delayed Gaussian process model accurately predicts the S-parameter values at desired frequency points in the training interval. Two application examples demonstrate the increased accuracy of the new technique, compared to standard Gaussian processes, vector fitting (VF), and delayed vector fitting (DVF) rational models.

show abstract

Dimensional Reduction by Auto-Encoders in Machine Learning Based Power Integrity Analysis

Nezhi,

Stiemer,

Schierholz

et al. 2024

2024 IEEE 28th Workshop on Signal and Power Integrity (SPI)

View full text Add to dashboard Cite

Parametric S-Parameters for PCB based Power Delivery Network Design Using Machine Learning

Cited by 6 publications

References 10 publications

Fast Prediction Method for Scattering Parameters of Rigid-Flex PCBs Based on ANN

Fast Prediction Method for Scattering Parameters of Rigid-Flex PCBs Based on ANN

Modeling Electrically Long Interconnects Using Physics-Informed Delayed Gaussian Processes

Dimensional Reduction by Auto-Encoders in Machine Learning Based Power Integrity Analysis

Contact Info

Product

Resources

About