Data-Driven Antenna Miniaturization: A Knowledge-Based System Integrating Quantum PSO and Predictive Machine Learning Models
Khan Masood Parvez, Sk Md Abidar Rahaman, Ali Shiri Sichani
TL;DR
This work presents a data-driven framework that couples Quantum-Behaved Dynamic Particle Swarm Optimization (QDPSO) with predictive machine learning to automate slot-antenna miniaturization. By optimizing loop dimensions and predicting resonant frequencies from HFSS simulations, the approach reduces a reference $f_r$ of $2.27\ \text{GHz}$ to $1.4208\ \text{GHz}$ (about $12.7\%$ reduction) with the optimization completing in $11.53\text{ s}$, while ML models predict resonance in $0.75\ \text{s}$. The complete design cycle—optimization, prediction, and validation—executes in about $12.42\ \text{minutes}$ on a standard desktop, offering a $\approx 240\times$ speedup over PSADEA benchmarks and enabling rapid fabrication-ready antenna parameters for IoT and 6G. The results demonstrate that ensemble ML (notably stacked) achieves high training accuracy ($R^2 \approx 0.9825$) and that SVM provides strong generalization ($R^2 \approx 0.72$) on unseen data, establishing a scalable AI-CAD paradigm for automated RF design and validation.
Abstract
The rapid evolution of wireless technologies necessitates automated design frameworks to address antenna miniaturization and performance optimization within constrained development cycles. This study demonstrates a machine learning enhanced workflow integrating Quantum-Behaved Dynamic Particle Swarm Optimization (QDPSO) with ANSYS HFSS simulations to accelerate antenna design. The QDPSO algorithm autonomously optimized loop dimensions in 11.53 seconds, achieving a resonance frequency of 1.4208 GHz a 12.7 percent reduction compared to conventional 1.60 GHz designs. Machine learning models (SVM, Random Forest, XGBoost, and Stacked ensembles) predicted resonance frequencies in 0.75 seconds using 936 simulation datasets, with stacked models showing superior training accuracy (R2=0.9825) and SVM demonstrating optimal validation performance (R2=0.7197). The complete design cycle, encompassing optimization, prediction, and ANSYS validation, required 12.42 minutes on standard desktop hardware (Intel i5-8500, 16GB RAM), contrasting sharply with the 50-hour benchmark of PSADEA-based approaches. This 240 times of acceleration eliminates traditional trial-and-error methods that often extend beyond seven expert-led days. The system enables precise specifications of performance targets with automated generation of fabrication-ready parameters, particularly benefiting compact consumer devices requiring rapid frequency tuning. By bridging AI-driven optimization with CAD validation, this framework reduces engineering workloads while ensuring production-ready designs, establishing a scalable paradigm for next-generation RF systems in 6G and IoT applications.