A Data-Driven Thermal Digital Twin of a 3-Phase Inverter Using Hi-Fidelity Multi-Physics Modelling

被引：0

作者：

Bhoi, Sachin Kumar ^{[1
]}

Frikha, Mohamed Amine ^{[1
,2
]}

Martin, Gamze Egin ^{[1
,2
]}

Hosseinabadi, Farzad ^{[1
,2
]}

Chakraborty, Sajib ^{[1
,2
]}

El Baghdadi, Mohamed ^{[1
,2
]}

Hegazy, Omar ^{[1
,2
]}

机构：

[1] Vrije Univ Brussel, ETEC Dept, MOBIE POWERS Res Grp, Pl Laan 2, B-1050 Brussels, Belgium

[2] Flanders Make, Gaston Geenslaan 8, B-3001 Heverlee, Belgium

来源：

2023 25TH EUROPEAN CONFERENCE ON POWER ELECTRONICS AND APPLICATIONS, EPE'23 ECCE EUROPE | 2023年

关键词：

Digital twin-based health monitoring; Reliability; Lifetime; Deep learning; POWER; INTELLIGENCE;

D O I：

暂无

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

The assessment of Power Electronics Converters (PECs) reliability is a crucial research area for the development of robust PECs. The key parameter for reliability assessment is the real-time junction temperature (T-j) profile for semiconductor power switches of PECs. While complex high-fidelity simulation models with electro-thermal models can accurately predict T-j during the offline design phase, their computational requirements make them impractical for real-time applications. This paper proposes a methodology to develop a real-time hardware deployable model for estimating the junction temperature of an Insulated Gate Bipolar Transistor (IGBT) power device. A data-driven reduced-order model (ROM) of an industrial inverter setup based on a high-fidelity multiphysics simulation model is presented in the article. This work also contributes to the realization of virtual sensors and digital twins for PECs.

引用

页数：8

共 12 条

[1] Intelligent feedrate optimization using a physics-based and data-driven digital twin
Kim, Heejin
Okwudire, Chinedum E.
CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2023, 72 (01) : 325 - 328
[2] Optimizing thermal stress distribution in heat-pipe-cooled microreactors using multi-physics data-driven methods
Zhang, Junda
Chen, Yinuo
Liu, Xiaojing
Chai, Xiang
He, Hui
Xiong, Jinbiao
Zhang, Tengfei
ENERGY, 2025, 323
[3] Data-driven identification of partial differential equations for multi-physics systems using stochastic optimization
Im, Jinwoo
de Barros, Felipe P. J.
Masri, Sami F.
NONLINEAR DYNAMICS, 2023, 111 (03) : 1987 - 2007
[4] Data-driven identification of partial differential equations for multi-physics systems using stochastic optimization
Jinwoo Im
Felipe P. J. de Barros
Sami F. Masri
Nonlinear Dynamics, 2023, 111 : 1987 - 2007
[5] Comprehensive Comparison of Multi-Physics and Deep Learning Modelling Approaches for Data-Driven Prediction of Traction Energy Demand
Reimann, Sebastian
Tesar, Markus
Gratzfeld, Peter
2022 IEEE VEHICLE POWER AND PROPULSION CONFERENCE (VPPC), 2022,
[6] Data-driven prognostics with low-fidelity physical information for digital twin: physics-informed neural network
Seokgoo Kim
Joo-Ho Choi
Nam Ho Kim
Structural and Multidisciplinary Optimization, 2022, 65
[7] Data-driven prognostics with low-fidelity physical information for digital twin: physics-informed neural network
Kim, Seokgoo
Choi, Joo-Ho
Kim, Nam Ho
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2022, 65 (09)
[8] A digital twin modeling approach cooperating design and manufacturing using knowledge graph and Multi-physics field modelling
Han, Xu
Liu, Xinyu
Wang, Honghui
Liu, Guijie
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2025, : 3423 - 3442
[9] A kd-tree-accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
Bahmani, Bahador
Sun, WaiChing
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2021, 382
[10] UNCERTAINTY QUANTIFICATION IN METALLIC ADDITIVE MANUFACTURING THROUGH DATA-DRIVEN MODELLING BASED ON MULTI-SCALE MULTI-PHYSICS MODELS AND LIMITED EXPERIMENT DATA
Wang, Zhuo
Jiang, Chen
Horstemeyer, Mark F.
Hu, Zhen
Chen, Lei
PROCEEDINGS OF THE ASME 2020 15TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE (MSEC2020), VOL 1A, 2020,

← 1 2 →