Machine Learning to Predict EMI Radiation and Optimize the Structure of Pinmap Packages
- 13 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 67 (4) , 1259-1270
Abstract
With the rapid increase in integrated circuit chip frequencies, the complexity of electromagnetic interference issues and the time-consuming nature of traditional pin mapping (pinmap) design methods have become increasingly evident. This article leverages advanced machine learning techniques to accurately and efficiently predict the maximum 3-m radiated electric field of pinmap packages. Among the various models tested, the convolutional neural network (CNN) demonstrated the best performance. When combined with the Adam optimizer, the CNN achieved an average relative error of less than 1.5% across the 6 to 20 GHz frequency range. The trained CNN model’s prediction speed is several orders of magnitude faster than full-wave simulation methods. Furthermore, this article proposes a structural optimization method to minimize radiation in pinmap packages. By integrating ground ball position optimization with the trained CNN model, the method achieves optimal radiation suppression. Validation across three different cases demonstrated a reduction in radiation by 4.85 to 10.37 dB (mV/m), confirming the effectiveness and applicability of the proposed approach.Keywords
Funding Information
- National Natural Science Foundation of China (62071424, 62027805)
- Zhejiang Provincial Natural Science Foundation of China (LHZSD25F010001)
This publication has 31 references indexed in Scilit:
- Environmentally Tough and Stretchable MXene Organohydrogel with Exceptionally Enhanced Electromagnetic Interference Shielding PerformancesNano-Micro Letters, 2022
- A data augmentation approach to XGboost-based mineral potential mapping: An example of carbonate-hosted Zn Pb mineral systems of Western IranJournal of Geochemical Exploration, 2021
- Lightweight high-performance carbon-polymer nanocomposites for electromagnetic interference shieldingComposites Part A: Applied Science and Manufacturing, 2021
- Diverse Metal–Organic Framework Architectures for Electromagnetic Absorbers and ShieldingAdvanced Functional Materials, 2021
- 4H-silicon-carbide-on-insulator for integrated quantum and nonlinear photonicsNature Photonics, 2019
- Teraelectronvolt emission from the γ-ray burst GRB 190114CNature, 2019
- Metrology for the next generation of semiconductor devicesNature Electronics, 2018
- Electronic modulation of infrared radiation in graphene plasmonic resonatorsNature Communications, 2015
- Limits on fundamental limits to computationNature, 2014
- Lightweight and Flexible Graphene Foam Composites for High‐Performance Electromagnetic Interference ShieldingAdvanced Materials, 2013