一个动态的物理导向组合模型,用于在IGBT中进行非侵入性的纽带电线健康监测
Xinyi Yang1, Zhen Hu1, Yizhi Bo1
1College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
Micromachines
|January 28, 2026
概括
这项研究引入了一个物理受约束的集体学习框架,用于预测IGBT模块中的粘接线退化. 该方法通过准确评估债券线的健康状况而提高可靠性,而不是侵入性.
科学领域:
- 电力电子 电力电子 电力电子
- 可靠性工程可靠性工程
- 机器学习 机器学习
背景情况:
- 结合线退化是绝缘门双极晶体管 (IGBT) 模块的主要故障模式,导致功率转换器的可靠性问题.
- 目前用于结合线状况的监测技术在准确性,复杂性和电磁兼容性方面存在局限性.
研究的目的:
- 开发一个非侵入性的框架来评估IGBT模块中的结合线状况,通过预测当前状态的收集器-发射器电压 (Vce-on).
- 通过将基于物理的约束与集体学习相结合,提高连接线状况监测的准确性和稳定性.
主要方法:
- 开发了一个物理受约束的集体学习框架,集成多维特征工程和自适应集体融合.
- 使用电,热和老化参数创建了一个16维特征向量,包括电热应力合的新术语.
- 三种梯度增强模型 (CatBoost,LightGBM,XGBoost) 被自适应地融合,结合了基于物理的规范化以实现热力学一致性.
主要成果:
- 拟议的框架在Vce-on预测中实现了高精度,平均绝对误差为0.0066V,R2为0.9998.
- 在保持99.1%的物理约束合规的同时,表现出比单个基准模型有48.4%的改进.
- 该方法有效地将数据驱动的学习与强有力的健康监测的物理原则相协调.
结论:
- 开发的框架为在电力电子系统中准确和实用的结合线状况评估提供了一个模式转变的方法.
- 这种方法通过早期检测降解来提高IGBT模块的可靠性和寿命.
- 基于物理学的约束与集体学习的整合为下一代动力电子的可靠性提供了强大的解决方案.
相关概念视频
02:32Bonding in Metals
52.3K
Metallic bonds are formed between two metal atoms. A simplified model to describe metallic bonding has been developed by Paul Drüde called the “Electron Sea Model”.
52.3K
01:28Physical Assessment of the Respiratory Tract I: Health History
899
Physical assessment of the respiratory tract is critical to patient care. It allows healthcare professionals to identify and manage various respiratory conditions. The process involves a combination of subjective and objective data collection.
Subjective Data
Subjective data provides vital information about the patient's health history and symptoms. This data is typically collected through interviews in which patients describe their experiences, symptoms, and concerns.
Health history and...
Subjective Data
Subjective data provides vital information about the patient's health history and symptoms. This data is typically collected through interviews in which patients describe their experiences, symptoms, and concerns.
Health history and...
899
02:49Bond Energies and Bond Lengths
31.5K
Stable molecules exist because covalent bonds hold the atoms together. The strength of a covalent bond is measured by the energy required to break it, that is, the energy necessary to separate the bonded atoms. Separating any pair of bonded atoms requires energy — the stronger a bond, the greater the energy required to break it.
31.5K
02:43Peptide Bonds
82.8K
A peptide bond covalently attaches amino acids through a dehydration reaction. One amino acid's carboxyl group and another amino acid's amino group combine, releasing a water molecule. The resulting bond is the peptide bond. The products that such linkages form are peptides. As more amino acids join this growing chain, the resulting chain is a polypeptide. Each polypeptide has a free amino group at one end. This end has the N-terminal, or the amino-terminal, and the other end has a free...
82.8K
02:45Valence Bond Theory
50.0K
Overview of Valence Bond Theory
50.0K
00:42Ionic Bonds
130.3K
Overview
When atoms gain or lose electrons to achieve a more stable electron configuration they form ions. Ionic bonds are electrostatic attractions between ions with opposite charges. Ionic compounds are rigid and brittle when solid and may dissociate into their constituent ions in water. Covalent compounds, by contrast, remain intact unless a chemical reaction breaks them.
Opposing Charges Hold Ions Together in Ionic Compounds
Ionic bonds are reversible electrostatic interactions between ions...
When atoms gain or lose electrons to achieve a more stable electron configuration they form ions. Ionic bonds are electrostatic attractions between ions with opposite charges. Ionic compounds are rigid and brittle when solid and may dissociate into their constituent ions in water. Covalent compounds, by contrast, remain intact unless a chemical reaction breaks them.
Opposing Charges Hold Ions Together in Ionic Compounds
Ionic bonds are reversible electrostatic interactions between ions...
130.3K