Research Article
Intelligent Measurement of Power Frequency Induced Electric Field Strength Based on Convolutional Neural Network Feature Recognition
@INPROCEEDINGS{10.1007/978-3-031-50571-3_20, author={Ying Li and Zheng Peng and Mancheng Yi and Jianxin Liu and Sifan Yu and Jing Liu}, title={Intelligent Measurement of Power Frequency Induced Electric Field Strength Based on Convolutional Neural Network Feature Recognition}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2024}, month={2}, keywords={Convolutional Neural Network Feature Recognition Power Frequency Induction Electric Field Strength Intelligent Measurement}, doi={10.1007/978-3-031-50571-3_20} }- Ying Li
Zheng Peng
Mancheng Yi
Jianxin Liu
Sifan Yu
Jing Liu
Year: 2024
Intelligent Measurement of Power Frequency Induced Electric Field Strength Based on Convolutional Neural Network Feature Recognition
ICMTEL
Springer
DOI: 10.1007/978-3-031-50571-3_20
Abstract
Aiming at the problem of large measurement error in existing electric field intensity measurement methods, an intelligent measurement method of power frequency induced electric field intensity based on convolution neural network feature recognition is proposed. According to the working principle of power devices in power environment, the mathematical model of power frequency induced electric field is established. The power frequency induction electric field intensity signal is collected by the intelligent chemical frequency induction electric field intensity measuring device. The convolution neural network is used to extract and recognize the characteristics of the power frequency induced electric field intensity signal. Through feature matching, intelligent measurement results of power frequency induced electric field intensity are obtained. The test results show that the average electric field intensity measurement error of the proposed method is reduced by 1.24 N/C, which solves the problem of large measurement error.
