Machine Learning-Assisted Automated Parametric Modeling, Simulation, and Structural Optimization of On-Chip Inductors
- 1School of Physics and Electronics, Hunan Normal University, Changsha 410081, China
Abstract
Aiming at the challenges of complex structural parameter spaces, excessively time-consuming full-wave electromagnetic simulations, and the tendency of traditional optimization algorithms to fall into local optima in radio frequency integrated circuit (RFIC) on-chip passive inductor design, this paper proposes an automated modeling, surrogate model, and PSO-GA hybrid optimization framework based on full-wave simulation. First, automated parametric modeling and efficient interaction with full-wave solvers are achieved through dedicated scripting interfaces. Second, a high-precision surrogate model is constructed using a physical component decoupling mechanism and Gaussian Process Regression (GPR), with the coefficient of determination (R2) for each physical component exceeding 0.970. Finally, a hybrid optimization strategy integrating Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) is implemented to perform rapid inverse design under target inductance and quality factor constraints. The experimental results show that the error between the inductance and quality factor values predicted by the surrogate model and the target inductance and quality factor values is less than 1%.
Related
- AMIA: an automated workflow for analysing the structural and dynamic effects of protein variants
- Electrochemical Platform for Automated Design-of-Experiment Optimization of Ni-Catalyzed Cross-Electrophile Coupling Reactions.
- A Simulation-Driven Digital Workflow Integrating Bayesian Optimization for Early-Stage Process Design: A Methyl Acetate Production Case Study
- Accelerating Lead Optimization away from Anti-Targets: Navigating the Structural Complexity of Promiscuous ADMET Proteins
- Numerical Simulation Study on Structure Optimization of a New Swirl Stable Combustion Low Nitrogen Burner Based on Computational Fluid Dynamics
BibTeX
@article{li2026machine,
title = {{Machine Learning-Assisted Automated Parametric Modeling, Simulation, and Structural Optimization of On-Chip Inductors}},
author = {Tangyi Li and Xiaonian Liu and Zhiyang Wu and Xinjie Tang},
journal = {Nanomaterials},
year = {2026},
month = oct,
doi = {10.3390/nano16211381},
url = {https://www.mdpi.com/2079-4991/16/21/1381},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine Learning-Assisted Automated Parametric Modeling, Simulation, and Structural Optimization of On-Chip Inductors
AU - Tangyi Li
AU - Xiaonian Liu
AU - Zhiyang Wu
AU - Xinjie Tang
PY - 2026
DA - 2026/10/28
JO - Nanomaterials
DO - 10.3390/nano16211381
UR - https://www.mdpi.com/2079-4991/16/21/1381
AB - Aiming at the challenges of complex structural parameter spaces, excessively time-consuming full-wave electromagnetic simulations, and the tendency of traditional optimization algorithms to fall into local optima in radio frequency integrated circuit (RFIC) on-chip passive inductor design, this paper proposes an automated modeling, surrogate model, and PSO-GA hybrid optimization framework based on full-wave simulation. First, automated parametric modeling and efficient interaction with full-wave solvers are achieved through dedicated scripting interfaces. Second, a high-precision surrogate model is constructed using a physical component decoupling mechanism and Gaussian Process Regression (GPR), with the coefficient of determination (R2) for each physical component exceeding 0.970. Finally, a hybrid optimization strategy integrating Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) is implemented to perform rapid inverse design under target inductance and quality factor constraints. The experimental results show that the error between the inductance and quality factor values predicted by the surrogate model and the target inductance and quality factor values is less than 1%.
SN - 2079-4991
ER -