Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning
This study delves into the analysis of boiling-induced vibrations observed during a flow boiling experiment and explores their potential in predicting heat load through machine learning models. The frequency spectral analysis revealed that the dominant frequency ranges between 6.5 – 12.5 kHz, deline...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/180737 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-180737 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1807372024-10-22T05:58:19Z Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning Barathula, Sreeram Kandasamy, Ranjith Fok, Priscilla Jia Yuan Wong, Teck Neng Leong, Kai Choong Srinivasan, K. School of Mechanical and Aerospace Engineering Engineering Boiling induced vibrations Flow boiling This study delves into the analysis of boiling-induced vibrations observed during a flow boiling experiment and explores their potential in predicting heat load through machine learning models. The frequency spectral analysis revealed that the dominant frequency ranges between 6.5 – 12.5 kHz, delineated into three distinct bands. Principal Component Analysis (PCA) underscored the significance of the 8 – 9 kHz peak, encapsulating around 65% of dataset variance. Diverse machine learning algorithms including decision tree regression, random forest regression, support vector regression, and multi-layer perceptron were rigorously evaluated. The Multi-Layer Perceptron (MLP) architecture with specific neuron configurations and a learning rate of 0.2 emerged as the superior model based on its minimal Mean Squared Error (MSE) and high R2 score. Notably, all models exhibited inference times within the microsecond range. This amalgamation of vibration spectral analysis, machine learning model assessments, and inference time evaluations underlines the promising prospect of utilizing boiling-induced vibrations for real-time heat load prediction, showcasing superior performance compared to conventional methods. The authors extend their sincere gratitude to Mr. Kris Gopalakrishnan for his invaluable financial support. 2024-10-22T05:58:18Z 2024-10-22T05:58:18Z 2024 Journal Article Barathula, S., Kandasamy, R., Fok, P. J. Y., Wong, T. N., Leong, K. C. & Srinivasan, K. (2024). Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning. International Journal of Heat and Mass Transfer, 232, 125890-. https://dx.doi.org/10.1016/j.ijheatmasstransfer.2024.125890 0017-9310 https://hdl.handle.net/10356/180737 10.1016/j.ijheatmasstransfer.2024.125890 2-s2.0-85198383583 232 125890 en International Journal of Heat and Mass Transfer © 2024 Published by Elsevier Ltd. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Boiling induced vibrations Flow boiling |
spellingShingle |
Engineering Boiling induced vibrations Flow boiling Barathula, Sreeram Kandasamy, Ranjith Fok, Priscilla Jia Yuan Wong, Teck Neng Leong, Kai Choong Srinivasan, K. Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
description |
This study delves into the analysis of boiling-induced vibrations observed during a flow boiling experiment and explores their potential in predicting heat load through machine learning models. The frequency spectral analysis revealed that the dominant frequency ranges between 6.5 – 12.5 kHz, delineated into three distinct bands. Principal Component Analysis (PCA) underscored the significance of the 8 – 9 kHz peak, encapsulating around 65% of dataset variance. Diverse machine learning algorithms including decision tree regression, random forest regression, support vector regression, and multi-layer perceptron were rigorously evaluated. The Multi-Layer Perceptron (MLP) architecture with specific neuron configurations and a learning rate of 0.2 emerged as the superior model based on its minimal Mean Squared Error (MSE) and high R2 score. Notably, all models exhibited inference times within the microsecond range. This amalgamation of vibration spectral analysis, machine learning model assessments, and inference time evaluations underlines the promising prospect of utilizing boiling-induced vibrations for real-time heat load prediction, showcasing superior performance compared to conventional methods. |
author2 |
School of Mechanical and Aerospace Engineering |
author_facet |
School of Mechanical and Aerospace Engineering Barathula, Sreeram Kandasamy, Ranjith Fok, Priscilla Jia Yuan Wong, Teck Neng Leong, Kai Choong Srinivasan, K. |
format |
Article |
author |
Barathula, Sreeram Kandasamy, Ranjith Fok, Priscilla Jia Yuan Wong, Teck Neng Leong, Kai Choong Srinivasan, K. |
author_sort |
Barathula, Sreeram |
title |
Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
title_short |
Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
title_full |
Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
title_fullStr |
Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
title_full_unstemmed |
Heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
title_sort |
heat load prediction in flow boiling using boiling-induced vibrations aided with machine learning |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/180737 |
_version_ |
1814047084877185024 |