融合参考扰动校准与物理先验引导神经网络的非接触低频电流重构方法及系统
By integrating reference disturbance calibration with physical prior guided neural networks, and utilizing 3D electromagnetic simulation and neural network reconstruction paths, the non-contact reconstruction problem of low-frequency current signals in electric vehicle electromagnetic compatibility testing was solved. This approach achieves high-precision current reconstruction and evaluation, adapts to complex disturbance conditions, and provides an engineeringable testing solution.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA ELECTRONICS RELIABILITY AND ENVIRONMENTAL TESTING INSTITUTE ((THE FIFTH INSTITUTE OF ELECTRONICS MINISTRY OF INDUSTRY AND INFORMATION TECHNOLOGY) (CHINA SAIBAO LABORATORY)
- Filing Date
- 2025-09-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to perform high-precision reconstruction and anti-interference performance evaluation of low-frequency current signals in the 1Hz to 1MHz range under non-contact conditions during electromagnetic compatibility testing of electric vehicles. They also lack robustness and generalization ability, especially in complex injection scenarios. Furthermore, traditional methods cannot effectively encode response changes caused by variations in structural parameters.
A method integrating reference perturbation calibration and physical prior guided neural network is adopted. The principal component feature vector of probe response is generated by three-dimensional electromagnetic simulation. A standard sampling dataset is constructed by combining the output voltage of non-contact probe, and the neural network model is trained. The non-contact reconstruction and evaluation of low-frequency current is realized by derivative feedback correction.
It achieves high-precision reconstruction and evaluation of low-frequency immunity injection current under non-contact conditions, breaking through the bottlenecks of frequency, accuracy and adaptability, and providing a new systematic solution with engineering deployment capability for EMC testing of electric vehicles.
Smart Images
Figure CN121186484B_ABST
Abstract
Citation Information
Patent Citations
AC fault arc detection method and system
CN114609475A
Image processing method for estimating a brain shift in a patient
WO2010037850A2