Development of Artificial Neural Network for Field Prediction of Unknown EM Source
| Autor: | Jun Wen, Yong-Liang Zhang, Yu-Fei Shu, Xing-Chang Wei |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Nonlinear system
Artificial neural network Field (physics) Computer science 0202 electrical engineering electronic engineering information engineering Magnitude (mathematics) Device under test 020206 networking & telecommunications 02 engineering and technology Function (mathematics) Algorithm Electromagnetic interference Electronic circuit |
| Zdroj: | 2020 IEEE International Conference on Computational Electromagnetics (ICCEM). |
| DOI: | 10.1109/iccem47450.2020.9219502 |
| Popis: | Unintended electromagnetic (EM) radiation source may cause device failure in high-speed circuits. In this paper, an artificial neural network (ANN) combined with the Green’s function is applied to construct a mapping relationship between the magnitude of the radiation field from an unknown EM source and the observation point. The ANN is trained by using the scanned near-field magnitude from the unknown EM source. The strong nonlinearity ability of the ANN makes the field prediction of the device under test (DUT) possess high accuracy, even if there is strong electromagnetic reflections around the DUT. Both numerical and measurement experiments are carried out to verify the effectiveness of this method. The proposed method provides a new solution for electromagnetic interference modelling in complex electromagnetic environments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|