arXiv：cs.LG· Samuela Rokocakau, Panagiotis Kakosimos, Giulia Tresca, Pericle Zanchetta·· 4 小时前
基于顺序学习的物理信息神经网络用于功率变换器参数估计
Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter
AI 导读
一种分阶段物理信息神经网络（PINN）被提出，用于从时域数据中辨识 DC buck 变换器的电感、电容及寄生电阻：梯度按 L→C→rL→rC 的顺序释放，该顺序由灵敏度分析得出。
正文
Abstract:A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter from time-domain data. Gradients are released in the order of L to C to rL to rC, a sequence derived from sensitivity analysis. The five-stage schedule recovers L and C to within 5% and the series ESR to 10%, while a three-stage variant attains the same accuracy 11% faster. An 84 factorial sweep confirms that the trained PINN remains accurate for simultaneous 8% perturbations of all four components, achieving a waveform RMSE of 2.6 x 10-2 over 5 ms-an order-of-magnitude better than a simultaneous-training baseline.
| Comments: | IEEE ECCE 2026 |
| Subjects: | Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2610.20041 [cs.LG] |
| (or arXiv:2610.20041v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20041 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Panagiotis Kakosimos [view email]
[v1]
Wed, 14 Oct 2026 11:48:19 UTC (993 KB)
来源：arXiv：cs.LG · arxiv.org