This paper analyzes the potential of Artificial Neural Networks (ANNs) for the modeling and optimization of magnetic components and, specifically, inductors. After reviewing the basic properties of ANNs, several potential modeling and design workflows are presented. A hybrid method, which combines the accuracy of 3D Finite Element Method (FEM) and the low computational cost of ANNs, is selected and implemented. All relevant effects are considered (3D magnetic and thermal field patterns, detailed core loss data, winding proximity losses, coupled loss-thermal model, etc.) and the implemented model is extremely versatile (3030 input and 4040 output variables). The proposed ANN-based model can compute 50′00050^{\prime}000 designs per second with less than 3%3 \% deviation with respect to 3D FEM simulations. Finally, the inductor of a 22 kW DC-DC buck converter is optimized with the ANN-based workflow. From the Pareto fronts, a design is selected, measured, and successfully compared with the results obtained with the ANNs. The implementation (source code and data) of the proposed workflow is available under an open-source license.

中文翻译：

---

基于人工神经网络 (ANN) 的快速、准确的电感器建模和设计


本文分析了人工神经网络 (ANN) 在磁性元件（特别是电感器）建模和优化方面的潜力。在回顾了 ANN 的基本属性之后，提出了几种潜在的建模和设计工作流程。选择并实施了一种混合方法，该方法结合了 3D 有限元法 (FEM) 的准确性和 ANN 的低计算成本。考虑了所有相关影响（3D 磁场和热场模式、详细的磁芯损耗数据、绕组邻近损耗、耦合损耗热模型等），并且实现的模型非常通用（3030 个输入和 4040 个输出变量）。所提出的基于 ANN 的模型每秒可以计算 50′00050^{\prime}000 个设计，与 3D FEM 模拟相比偏差小于 3%3 \%。最后，使用基于 ANN 的工作流程对 22 kW DC-DC 降压转换器的电感器进行了优化。从帕累托前沿，选择、测量设计，并成功地与人工神经网络获得的结果进行比较。所提议的工作流程的实现（源代码和数据）可在开源许可下使用。