Machine learning-based predictive modeling of contact heat transfer

Vu, Anh Tuan; Gulati, Shrey; Vogel, Paul-Alexander; Grunwald, Tim; Bergs, Thomas

doi:10.1016/j.ijheatmasstransfer.2021.121300

Cited by 31 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the first-principles calculation method is computationally demanding and time consuming. In recent years, machine learning has emerged as a novel approach for TBR prediction [48][49][50][51][52][53][54][55][56][57], and it has been demonstrated to achieve higher predictive accuracy than the conventionally used AMM and DMM methods [48]. Figure 3b shows the comparison of the correlation between the experimental values and the values predicted by the AMM, DMM, and machine learning method using Gaussian process regression (GPR).…”

Section: Theoretical and Computational Methods For Tbr Predictionmentioning

confidence: 99%

Effects of Thermal Boundary Resistance on Thermal Management of Gallium-Nitride-Based Semiconductor Devices: A Review

Zhan,

Xu,

Cao

et al. 2023

Micromachines

View full text Add to dashboard Cite

Wide-bandgap gallium nitride (GaN)-based semiconductors offer significant advantages over traditional Si-based semiconductors in terms of high-power and high-frequency operations. As it has superior properties, such as high operating temperatures, high-frequency operation, high breakdown electric field, and enhanced radiation resistance, GaN is applied in various fields, such as power electronic devices, renewable energy systems, light-emitting diodes, and radio frequency (RF) electronic devices. For example, GaN-based high-electron-mobility transistors (HEMTs) are used widely in various applications, such as 5G cellular networks, satellite communication, and radar systems. When a current flows through the transistor channels during operation, the self-heating effect (SHE) deriving from joule heat generation causes a significant increase in the temperature. Increases in the channel temperature reduce the carrier mobility and cause a shift in the threshold voltage, resulting in significant performance degradation. Moreover, temperature increases cause substantial lifetime reductions. Accordingly, GaN-based HEMTs are operated at a low power, although they have demonstrated high RF output power potential. The SHE is expected to be even more important in future advanced technology designs, such as gate-all-around field-effect transistor (GAAFET) and three-dimensional (3D) IC architectures. Materials with high thermal conductivities, such as silicon carbide (SiC) and diamond, are good candidates as substrates for heat dissipation in GaN-based semiconductors. However, the thermal boundary resistance (TBR) of the GaN/substrate interface is a bottleneck for heat dissipation. This bottleneck should be reduced optimally to enable full employment of the high thermal conductivity of the substrates. Here, we comprehensively review the experimental and simulation studies that report TBRs in GaN-on-SiC and GaN-on-diamond devices. The effects of the growth methods, growth conditions, integration methods, and interlayer structures on the TBR are summarized. This study provides guidelines for decreasing the TBR for thermal management in the design and implementation of GaN-based semiconductor devices.

show abstract

Section: Theoretical and Computational Methods For Tbr Predictionmentioning

confidence: 99%

Effects of Thermal Boundary Resistance on Thermal Management of Gallium-Nitride-Based Semiconductor Devices: A Review

Zhan,

Xu,

Cao

et al. 2023

Micromachines

View full text Add to dashboard Cite

show abstract

“…Prediction of thermal boundary resistance by using linear regression, decision tree, random forest algorithm, and machine-learning potential-driven molecular dynamics simulations. Reprinted with permission from refs and . Copyright 2021 Elsevier and 2021 Springer Nature.…”

Section: Thermophysical Properties Of Materialsmentioning

confidence: 99%

“…Even for the same pair of interface materials, ML can also be applied to study the dependence of interface conditions such as temperature, defects, bonding strength, etc. Vu et al constructed the mapping between the TBR of a glass/steel interface and descriptors including temperature, pressure, and surface roughness by using linear regression, decision tree, and random forest algorithm to train their own experimental results and achieved a coefficient of determination up to 0.99, as illustrated in Figure c . In addition, ML algorithms can also be combined with classical MD simulations to accelerate the optimization of fine structure at the interface for thermal transport. − …”

Section: Thermophysical Properties Of Materialsmentioning

confidence: 99%

Machine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization

Dai

2022

ACS Energy Lett.

View full text Add to dashboard Cite

Recent advances in machine learning (ML) have impacted research communities based on statistical perspectives and uncovered invisibles from conventional standpoints. Though the field is still in the early stage, this progress has driven the thermal science and engineering communities to apply such cutting-edge toolsets for analyzing complex data, unraveling abstruse patterns, and discovering non-intuitive principles. In this work, we present a holistic overview of the applications and future opportunities of ML methods on crucial topics in thermal energy research, from bottom-up materials discovery to top-down system design across atomistic levels to multi-scales. In particular, we focus on a spectrum of impressive ML endeavors investigating the state-of-the-art thermal transport modeling (density functional theory, molecular dynamics, and Boltzmann transport equation), different families of materials (semiconductors, polymers, alloys, and composites), assorted aspects of thermal properties (conductivity, emissivity, stability, and thermoelectricity), and engineering prediction and optimization (devices and systems). We discuss the promises and challenges of current ML approaches and provide perspectives for future directions and new algorithms that could make further impacts on thermal energy research.

show abstract

“…The latter is influenced both by process parameters, e.g. temperature and molding force (e.g., Maxwell [15,16] or Burgers' models [17,18]), the heat transfers at the glassmold interface [19][20][21] and by system variables such as the geometry of the blank and that of the mold, as well as the surface properties [22]. Another challenge is the control of shrinkage, which is also significantly influenced by thermal and system parameters [23].…”

Section: Fig 4 Process Chain Of the Wafer Scale Processmentioning

confidence: 99%

Enabling Sustainability in Glass Optics Manufacturing by Wafer Scale Molding

Strobl

Vogel

et al. 2022

KEM

Self Cite

View full text Add to dashboard Cite

Numerous optical applications have rising demands for ever increasing quantities from lighting and projection optics for modern vehicles to home or street lighting using LED technology. Glass is the material of choice for most of those application fields. It has several advantages over polymers, including heat and scratch resistance as well as longevity and recyclability. Non-isothermal glass molding has become a viable hot forming technology for mass production of optics. The major challenge is enabling a scalable replication process allowing the optical glass elements to be manufactured with high form accuracy and at low-cost production with low reject rates. This work introduces recent developments in glass optics manufacturing that allow the fulfilment of seemingly contradicting criteria: the economic growth and the need for less consumption of resources and energy. While single cavity non-isothermal molding is state-of-the-art, a manufacturing innovation through wafer-scale molding enables an exponentially increasing number of optics to be produced per production shift, allowing a significant reduction of unit costs. In parallel, as multiple optics are produced in one manufacturing cycle, the energy consumption and the consequent CO2 emission can be reduced. In contrast, the technological development arises several challenges that will be discussed in this work. Besides the selection of suitable mold concepts and materials, the challenges also include the temperature control of the mold and the blank up to the optimization of flow and shrinking mechanisms of the glass during rapid forming. Another difficulty in the non-isothermal glass molding is to maintain the low form deviation required for precision optics, repeatability, and low failure rates through process optimization. Finally, detail calculations of cost, energy and CO2 consumption, in comparison with conventional fabrication of glass components using grinding and polishing as well as single cavity molding, will be demonstrated. The non-isothermal wafer-level glass molding is a new technological solution for the sustainable manufacturing of optics at large-scaled production.

show abstract

Machine learning-based predictive modeling of contact heat transfer

Cited by 31 publications

References 39 publications

Effects of Thermal Boundary Resistance on Thermal Management of Gallium-Nitride-Based Semiconductor Devices: A Review

Effects of Thermal Boundary Resistance on Thermal Management of Gallium-Nitride-Based Semiconductor Devices: A Review

Machine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization

Enabling Sustainability in Glass Optics Manufacturing by Wafer Scale Molding

Contact Info

Product

Resources

About