📄 中文摘要
该研究提出了一种利用物理信息神经网络（PINNs）的方法，以确定在给定热流下，考虑进出口温度的冷却剂所需速度。MOSFET是电力电子建筑块（PEBBs）的核心组件，承受了大部分热负荷，因此有效的冷却对于防止过热和潜在的烧毁至关重要。确定有效冷却所需的冷却剂速度是一个重要但难以解决的逆问题，传统方法难以应对。MOSFET由多个具有不同热导率的层组成，研究通过PINNs提供了一种新的解决方案，旨在提高散热效率并优化冷却设计。
利用物理信息神经网络提高MOSFET散热器效率：冷却剂速度估算的系统研究
📄 English Summary
Enhancing Heat Sink Efficiency in MOSFETs using Physics Informed Neural Networks: A Systematic Study on Coolant Velocity Estimation
This study presents a methodology using Physics Informed Neural Networks (PINNs) to estimate the required coolant velocity based on inlet and outlet temperatures for a specified heat flux in multilayered metal-oxide-semiconductor field-effect transistors (MOSFETs). MOSFETs are crucial components of Power Electronic Building Blocks (PEBBs) and bear the majority of thermal loads, making effective cooling essential to prevent overheating and potential burnout. Determining the necessary coolant velocity for effective cooling is significant but poses an ill-posed inverse problem that is challenging for traditional methods. The multilayer structure of MOSFETs, with varying thermal conductivities, complicates this task. The research provides a novel solution through the application of PINNs, aiming to enhance heat sink efficiency and optimize cooling designs.