波形协变量偏移下磁芯损耗预测的跨材料支持迁移
Cross-Material Support Transfer for Core-Loss Prediction Under Waveform Covariate Shift
浏览论文内容
中文总结 AI 辅助
本文针对波形协变量偏移下磁芯损耗预测的数据稀疏问题，提出跨材料支持迁移（MIST）方法，联合训练多材料模型，显著降低材料D的误差，证明稀缺材料应联合表征。
中文摘要 AI 辅助
功率磁性材料是在正弦和三角波形下表征的，这些波形是激励硬件方便产生的，而实际部署的变换器使磁芯暴露于梯形、PWM形状的磁通轨迹，因此损耗模型必须准确预测其训练数据最稀疏的区域。MagNet挑战赛的最终测试嵌入了一个刻意极端的表征-部署不匹配实例：对于材料D，梯形波占测试集的16.4%，但仅占训练集的1.4%。基于顺序迁移学习的最佳提交的95百分位相对误差（以下简称p95）停滞在15.9%，是五种材料中最差的。本文表明，障碍是协变量偏移下的信息缺失而非类别不平衡，并且缺失的支持可以从兄弟材料借用而非外推。受控实验首先反驳了不平衡的解读：四种标准补救措施失败，将梯形波比例提高到测试集水平进一步降低了精度。所提出的材料身份支持迁移（MIST）在全部五种挑战材料上联合训练一个2784参数的预测器。材料身份通过特征级线性调制（FiLM）进入，稀缺材料的真实标签损失被重新加权，材料D不进行微调，因此其无梯形波训练集的偏差永远不会被重新引入。MIST将五种种子材料D的p95从20.39±2.03%降低到12.38±0.92%，梯形类p95从37.4±8.8%降低到15.16±1.69%，以六分之一的参数且无微调阶段超越了最佳提交；在匹配容量下移除材料身份会使误差增加一个数量级。这些结果表明，稀缺材料应与其兄弟材料联合表征。
英文摘要
Power magnetic materials are characterized on the sinusoidal and triangular waveforms that excitation hardware conveniently produces, whereas deployed converters expose cores to trapezoidal, PWM-shaped flux trajectories, so loss models must predict exactly where their training data are thinnest. The final test of the MagNet Challenge embeds a deliberately extreme instance of this characterization-deployment mismatch: for material D, trapezoids form 16.4% of the test set but only 1.4% of the training set. The 95th-percentile relative error, hereafter p95, of the best submission, built on sequential transfer learning, stalled at 15.9%, the worst among the five materials. This paper shows that the obstacle is missing information under covariate shift rather than class imbalance, and that the missing support can be borrowed from sibling materials instead of being extrapolated. Controlled experiments first refute the imbalance reading: four standard remedies fail, and raising the trapezoidal share to the test-set level degrades accuracy further. The proposed material-identity support transfer, MIST, then trains one 2784-parameter predictor jointly on all five challenge materials. Material identity enters through feature-wise linear modulation, or FiLM, the scarce material's true-label loss is reweighted, and material D receives no fine-tuning, so that the bias of its trapezoid-free training set is never re-installed. MIST lowers the five-seed material-D p95 from 20.39+/-2.03% to 12.38+/-0.92% and the trapezoidal-class p95 from 37.4+/-8.8% to 15.16+/-1.69%, surpassing the best submission with one-sixth of its parameters and no fine-tuning stage; removing material identity at matched capacity inflates the error by an order of magnitude. These results argue that scarce materials should be characterized jointly with their siblings.
