基于人工智能高效近场扫描的瞬态强电磁干扰传导耦合路径可视化  

AI-Based Efficient Near-Field Scanning for Conductive Coupling Path Visualization Under High Transient Electromagnetic Interference

作　　者：杨振中 谢雨婷 许潘 邓帅荣 YANG Zhenzhong;XIE Yuting;XU Pan;DENG Shuairong(Microsystem and Terahertz Research Center,China Academy of Engineering Physics,Chengdu 610200,China;Institute of Electronic Engineering,China Academy of Engineering Physics,Mianyang 621000,China;College of Information Science and Electronic Engineering,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]中国工程物理研究院微系统与太赫兹研究中心,成都610200 [2]中国工程物理研究院电子工程研究所,绵阳621000 [3]浙江大学信息与电子工程学院,杭州310058

出　　处：《电子科技大学学报》2024年第4期495-502,共8页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(U203020025)。

摘　　要：在高压电子系统中,瞬态强电磁干扰会通过空间辐射、传导耦合等方式影响低压控制区的正常工作,在该工况下系统的电磁兼容问题较为突出。该文在时域电流测试与近场扫描结合的基础上,提出了一种改进的人工智能近场扫描算法,可实现强瞬态电磁干扰下传导耦合路径的高效可视化,据此采取了相应的整改措施并解决了系统中的电磁干扰问题。与传统近场扫描方法相比,该文提出的人工智能算法可大幅度提高测试效率。此外,还分析了不同参数的选择对该人工智能算法稳定性的影响,提出了一种自动停止扫描的判决标准,该判决标准使人工智能近场扫描算法不需要人为干预,从而具有更高的智能化与鲁棒性。In high-voltage electronic systems,high transient electromagnetic interference will affect the low-voltage controlling system via space electromagnetic radiation or coupling interference conduction.Under such circumstances,the electromagnetic compatibility problem of the system is more prominent.Based on the combination of time-domain current measurement and near-field scanning,this paper proposes an improved Artificial Intelligence(AI)near-field scanning algorithm,which can efficiently visualize the conductive coupling paths under strong transient electromagnetic interference.Further,mitigation methods are used to solve the electromagnetic interference problem in the system.Compared to the conventional near-field scanning method,the proposed AI method significantly improves the measurement efficiency.Moreover,this paper analyzes the influence of different parameter choices on the stability of the AI method,and proposes an automatic stopping criterion for the AI near-field scanning process.The stopping criterion makes the AI near-field scanning process more intelligent and robust without human intervention.

关 键 词：高压电子系统 瞬态强电磁干扰 近场扫描 耦合路径 人工智能近场扫描算法 

分 类 号：TN97[电子电信—信号与信息处理] TN99[电子电信—信息与通信工程]