现代信息科技2025，Vol.9Issue(17)：22-27,6.DOI:10.19850/j.cnki.2096-4706.2025.17.005
基于物理信息同步学习的高频传输线电压预测研究
Voltage Prediction Research on High-frequency Transmission Lines Based on Physically Informed Synchronous Learning
李通博 1黄浩 1程钰1
作者信息
- 1. 中国能源建设集团辽宁电力勘测设计院有限公司,辽宁 沈阳 110179
- 折叠
摘要
Abstract
High-frequency transmission lines play a vital role in power systems and are widely used in the propagation and interaction of electromagnetic waves.Therefore,accurate prediction of their voltage is of great significance for information acquisition.However,existing numerical methods have certain limitations in computational efficiency.To this end,the voltage prediction method of high-frequency transmission lines is studied,and a method based on Physically Informed Synchronous Learning(PISL)is proposed.Firstly,a Neural Network for predicting voltage is constructed,and it randomly samples to obtain the sparse training dataset and collocation point set without labels.Secondly,a data-physics information hybrid loss function is constructed to train the network,which considers data loss and physics-informed loss synthetically.Finally,the Pearson correlation coefficient and Root Mean Square Error are used as evaluation criteria to verify the effectiveness of the proposed method through experiments.Meanwhile,a comparative sensitivity analysis of the relevant network parameters is applied to verify the effectiveness and robustness of the method.关键词
数据-物理信息融合损失函数/物理信息同步学习/电压预测/神经网络Key words
data-physics information hybrid loss function/Physically Informed Synchronous Learning/voltage prediction/Neural Network分类
信息技术与安全科学引用本文复制引用
李通博,黄浩,程钰..基于物理信息同步学习的高频传输线电压预测研究[J].现代信息科技,2025,9(17):22-27,6.
