发表机构
School of Electrical and Data Engineering, the University of Technology Sydney; School of Electrical and Computer Engineering, the University of Sydney; National Railway Research and Design Institute of Signal and Communication（悉尼科技大学电气与数据工程学院; 悉尼大学电气与计算机工程学院; 中国铁路通信信号集团公司通信信号研究设计院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对功率磁器件瞬态磁化预测难题，提出物理信息混合神经算子PI-HNO，结合局部循环分支与类Preisach全局分支，在MagNetX数据库14种铁氧体材料上实现了高精度紧凑模型，验证了各组件的独特贡献。
AI 中文摘要
高频高功率密度变流器中的磁性元件日益由具有快速过渡、小磁滞回线运行、直流偏置和温度变化的非正弦磁通密度波形驱动。在此类工况下，稳态铁损公式和单值材料曲线无法完全捕捉瞬态磁化响应。本研究提出物理信息混合神经算子（Physics-Informed Hybrid Neural Operator, PI-HNO），这是一种针对特定材料的紧凑神经模型，带有面向铁损的瞬态磁化预测的B-H能量一致性正则化项。给定预测区间内的测量B(t)-H(t)历史、输入B(t)序列及工况信息，PI-HNO可预测H(t)序列及对应的重构B-H轨迹。该模型整合了用于边界状态表征和速率依赖响应演化的局部循环分支，以及提取波形级磁滞上下文的类Preisach全局分支。在MagNetX瞬态数据库上针对14种铁氧体材料的特定材料模型评估显示，PI-HNO在序列精度与B(t)-H(t)能量一致性间实现了紧凑权衡，每个模型仅用4777个可训练参数，B(t)-H(t)能量一致性误差的均值和第95百分位数分别为1.92%和7.60%。 ablation研究进一步表明，局部、全局和能量感知正则化组件对瞬态磁化预测具有不同贡献。
英文摘要
Magnetic components in high-frequency, high-power-density converters are increasingly driven by non-sinusoidal flux-density waveforms with fast transitions, minor-loop operation, dc bias, and temperature variation. Under these conditions, steady-state core-loss formulas and single-valued material curves cannot fully capture transient magnetization responses. This work proposes the Physics-Informed Hybrid Neural Operator (PI-HNO), a compact material-specific neural model with B-H energy-consistency regularization for core-loss-oriented transient magnetization prediction. Given the measured B(t)-H(t) history, the input B(t) series over the prediction interval and operating-condition information, PI-HNO predicts the H(t) series and the corresponding reconstructed B-H trajectory. The model integrates a local recurrent branch for boundary-state representation and rate-dependent response evolution with a Preisach-inspired global branch that extracts waveform-level hysteresis context. Evaluation on the MagNetX transient database using material-specific models for 14 ferrite materials demonstrates that PI-HNO achieves a compact trade-off between sequence accuracy and B(t)-H(t) energy consistency, with the mean and 95th percentile B(t)-H(t) energy consistency errors of 1.92% and 7.60%, respectively, using only 4777 trainable parameters per model. Ablation studies further demonstrate that the local, global, and energy-aware regularized components provide distinct contributions to transient magnetization prediction.
Comments13 pages, 7 figures. Preprint prepared for possible submission to IEEE Transactions on Power Electronics
