MagLearn 2：PWM激励下瞬态B-H行为的保真度、饱和感知与历史高效序列到序列建模
MagLearn 2: High-Fidelity, Saturation-Aware, and History-Efficient Sequence-to-sequence Modeling of Transient B-H Behaviour Under PWM Excitation
- University of Bristol（布里斯托大学）
- Würth Elektronik（伍尔特电子）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出MagLearn 2，一种基于LSTM的序列到序列框架，用于PWM激励下瞬态B-H波形预测，通过饱和感知辅助模块和遮挡敏感性分析，在MagNet Challenge II中取得2.2%的最低平均RMSE。
AI中文摘要：
在脉宽调制（PWM）激励下，精确的瞬态B-H建模具有挑战性，因为磁场响应既取决于瞬时磁通密度，又取决于先前的磁化轨迹。尽管序列到序列模型能够实现波形预测，但现有研究尚未共同解决需要多少磁历史、如何处理饱和区域以及如何使训练好的模型适应未见过的材料等问题。为解决这些空白，本文提出MagLearn 2，一种基于条件感知、短窗口LSTM的序列到序列框架，用于从历史B(t)和H(t)轨迹重建未来的H(t)响应。一个饱和感知辅助模块在完整波形预测中选择性地替换饱和主导的预测。在一个具有代表性的饱和3C90案例中，辅助模块将序列级相对均方根误差（RMSE）从67.84%降至9.19%。为了理解历史样本对预测的贡献程度，进行了基于遮挡的敏感性分析，以量化磁历史的贡献，并揭示与预测最相关的信息集中在预测边界附近。在MagNet Challenge II的独立评估中，所提出框架的最佳性能模型在序列预测任务上取得了迄今为止报告的最低平均RMSE，为2.2%。
英文摘要：
Accurate transient B-H modeling under pulsewidth-modulated (PWM) excitation is challenging since the magnetic-field response depends on both the instantaneous flux density and the preceding magnetisation trajectory. Although sequence-to-sequence models enable waveform prediction, existing studies have not jointly addressed how much magnetic history is required, how saturation region should be handled, and how trained models can be adapted to unseen materials. To address these gaps, this paper presents MagLearn 2, a condition-aware, short-window LSTM-based sequence-to-sequence framework for reconstructing the future H(t) response from the historical B(t) and H(t) trajectories. A saturation-aware auxiliary module selectively replaces saturation-dominated predictions within the complete waveform forecast. In a representative saturated 3C90 case, the auxiliary module reduces the sequence-level relative RMSE from 67.84% to 9.19%. To understand how much the history samples contributes to the predictions, an occlusion-based sensitivity analysis is conducted to quantifies the contribution of magnetic history and reveals that that the information most relevant to prediction is concentrated near the forecast boundary. In the independent evaluation for MagNet Challenge II, the proposed framework's best-performing model achieved the lowest reported average RMSE to date on the sequence-prediction task at 2.2%.
