@inproceedings{8aceb1bed2794b6fad2990188ab526d8,
title = "Nonlinear Response Prediction of Voltage-Controlled Oscillators Based on Deep Learning",
abstract = "A composite deep learning model combining CNN, LSTM, and Transformer is proposed in this paper to predict the nonlinear response of voltage-controlled oscillators (VCOs). The model predicts injection locking phenomena based on the characteristic parameters of the interference waveform. Firstly, the architecture of the proposed model is introduced. Then it describes the data processing method, loss function and training process. Finally, this model is compared with other models to demonstrate the performance. Under the input of continuous wave interference, the highest prediction accuracy of the proposed model is 0.9636, and the average accuracy is 0.9164, outperforming classical models such as three-layer CNN and double-layer CNN-Transformer.",
keywords = "Deep learning, nonlinear response, spectrum prediction, voltage-controlled oscillators (VCOs)",
author = "Liu, \{Ya Jing\} and Ma, \{Pei Yuan\} and Jin, \{Yun Tao\} and Fei Dai",
note = "Publisher Copyright: {\textcopyright} 2025 Applied Computational Electromagnetics Society.; 2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 ; Conference date: 08-08-2025 Through 11-08-2025",
year = "2025",
doi = "10.23919/ACES-China66523.2025.11332947",
language = "英语",
series = "2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 - Proceedings",
address = "美国",
}