High Heat Flux Cooling Technologies Using Microchannel Evaporators: Fundamentals and Challenges

Cheng, Lixin

doi:10.1080/01457632.2022.2140639

“…Two-phase flow boiling in microchannel heat sinks is one of the most important topics in the field of fluid flow and heat transfer, especially due to the promising application in high heat flux cooling [ 1 , 2 , 3 ]. It offers significant advantages for the cooling of power electronics, computer chips, laser diodes, and other electronic components due to its large heat transfer surface area and compact design.…”

Section: Introductionmentioning

confidence: 99%

Computer-Vision- and Deep-Learning-Based Determination of Flow Regimes, Void Fraction, and Resistance Sensor Data in Microchannel Flow Boiling

Schepperle,

Junaid,

Woias

2024

Sensors

1

0

View full text Add to dashboard Cite

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6.

show abstract

“…T WO-phase flow boiling in microchannel heat sinks is one of the most important topics in the field of fluid flow and heat transfer, especially due to the promising application in high heat flux cooling [1]- [3]. It offers significant advantages for the cooling of power electronics, computer chips, laser diodes and other electronic components due to its large heat transfer surface area and compact design.…”

Section: Introductionmentioning

confidence: 99%

Computer Vision and Deep Learning Based Determination Of Flow Regimes, Void Fraction And Resistance Sensor Data In Microchannel Flow Boiling

Schepperle,

Junaid,

Woias

2023

Preprint

0

View full text Add to dashboard Cite

<p>The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection and histogram comparison to separate vapour from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called Unet to extract meaningful features from video frames. Both approaches enabled automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially the CNN has demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1 % and classify the above flow regimes with an overall classification accuracy of 91 %. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. This sensor signal prediction is a promising first step towards automated, imageless prediction of two-phase flow in microchannels using only the measurement data from resistance sensors. The approaches discussed in this paper were performed on an ordinary 6 GB NVIDIA laptop GPU using Python and are general enough to be applied to other similar applications. The deep learning model can be downloaded from: github.com/schepperlemark</p>

show abstract

“…T WO-phase flow boiling in microchannel heat sinks is one of the most important topics in the field of fluid flow and heat transfer, especially due to the promising application in high heat flux cooling [1]- [3]. It offers significant advantages for the cooling of power electronics, computer chips, laser diodes and other electronic components due to its large heat transfer surface area and compact design.…”

Section: Introductionmentioning

confidence: 99%

Computer Vision and Deep Learning Based Determination Of Flow Regimes, Void Fraction And Resistance Sensor Data In Microchannel Flow Boiling

Schepperle,

Junaid,

Woias

2023

Preprint

0

View full text Add to dashboard Cite

<p>The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection and histogram comparison to separate vapour from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called Unet to extract meaningful features from video frames. Both approaches enabled automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially the CNN has demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1 % and classify the above flow regimes with an overall classification accuracy of 91 %. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. This sensor signal prediction is a promising first step towards automated, imageless prediction of two-phase flow in microchannels using only the measurement data from resistance sensors. The approaches discussed in this paper were performed on an ordinary 6 GB NVIDIA laptop GPU using Python and are general enough to be applied to other similar applications. The deep learning model can be downloaded from: github.com/schepperlemark</p>

show abstract

High Heat Flux Cooling Technologies Using Microchannel Evaporators: Fundamentals and Challenges

Cited by 18 publications

References 102 publications

Computer-Vision- and Deep-Learning-Based Determination of Flow Regimes, Void Fraction, and Resistance Sensor Data in Microchannel Flow Boiling

Computer-Vision- and Deep-Learning-Based Determination of Flow Regimes, Void Fraction, and Resistance Sensor Data in Microchannel Flow Boiling

Computer Vision and Deep Learning Based Determination Of Flow Regimes, Void Fraction And Resistance Sensor Data In Microchannel Flow Boiling

Computer Vision and Deep Learning Based Determination Of Flow Regimes, Void Fraction And Resistance Sensor Data In Microchannel Flow Boiling

Contact Info

Product

Resources

About