HARDCORE：在铁氧体磁芯中利用残差扩张卷积神经网络估计任意波形的H场与功率损耗
HARDCORE: H-field and power loss estimation for arbitrary waveforms with residual, dilated convolutional neural networks in ferrite cores
AI总结：
面向MagNet Challenge 2023，本文提出HARDCORE残差扩张卷积模型，通过重建bh曲线并结合专家特征工程，实现小参数规模下任意波形铁氧体磁芯功率损耗的可解释高精度估计。
摘要：
MagNet Challenge 2023呼吁参赛者开发数据驱动模型，用于针对特定材料且与波形无关地估计环形铁氧体磁芯中的稳态功率损耗。下文所述HARDCORE（H-field and power loss estimation for Arbitrary waveforms with Residual, Dilated convolutional neural networks in ferrite COREs，即在铁氧体磁芯中利用残差扩张卷积神经网络进行任意波形H场与功率损耗估计）方法表明，带有物理信息扩展的残差卷积神经网络在事先基于观测数据训练后，能够高效完成该任务。一个关键解决方案要素是一个中间模型层：它首先重建bh曲线，随后根据曲线面积估计功率损耗，从而使所提出的拓扑结构具有物理可解释性。此外，研究重点放在基于专家经验的特征工程和信息丰富的输入上，以实现精简的模型架构。每种材料都从零开始训练一个模型，而拓扑结构保持不变。研究展示了模型规模与估计精度之间的Pareto式权衡：在样本充足的最差材料上，最优模型仅需1755个参数，且相对误差第95百分位可降至8%以下。
英文摘要：
The MagNet Challenge 2023 calls upon competitors to develop data-driven models for the material-specific, waveform-agnostic estimation of steady-state power losses in toroidal ferrite cores. The following HARDCORE (H-field and power loss estimation for Arbitrary waveforms with Residual, Dilated convolutional neural networks in ferrite COREs) approach shows that a residual convolutional neural network with physics-informed extensions can serve this task efficiently when trained on observational data beforehand. One key solution element is an intermediate model layer which first reconstructs the bh curve and then estimates the power losses based on the curve's area rendering the proposed topology physically interpretable. In addition, emphasis was placed on expert-based feature engineering and information-rich inputs in order to enable a lean model architecture. A model is trained from scratch for each material, while the topology remains the same. A Pareto-style trade-off between model size and estimation accuracy is demonstrated, which yields an optimum at as low as 1755 parameters and down to below 8\,\% for the 95-th percentile of the relative error for the worst-case material with sufficient samples.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
