The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model

Yangyang Lai; Ke Pan; Jonghwan Ha; Chongyang Cai; Junbo Yang; Pengcheng Yin; Jiefeng Xu; Seungbae Park

doi:10.1109/iTherm54085.2022.9899644

The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model

Yangyang Lai
, Ke Pan
, Jonghwan Ha
, Chongyang Cai
, Junbo Yang
, Pengcheng Yin
, Jiefeng Xu
, Seungbae Park

Mechanical Engineering

Binghamton University

State University of New York Binghamton University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

This paper presents a physics-guided machine learning model to provide the optimal reflow recipe for a 7-zone oven. The numerical method based on the computational fluid dynamics (CFD) simulation was used to predict reflow profiles of a BGA package. After validating the CFD model with the measurement results, an automated system was programmed to collect profiles subjected to 81 sets of boundary conditions (reflow recipe). A machine learning model trained by 81 sets of input data was employed to predict profiles subjected to 148,176 sets boundary conditions rapidly. The peak temperature and time above liquidous of output profiles were extracted to quantify the performance of the corresponding boundary conditions. The boundary condition with the best reflow performance was regarded as the optimal recipe.

Original language	English
Title of host publication	Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665485036
DOIs	https://doi.org/10.1109/iTherm54085.2022.9899644
State	Published - 2022
Event	21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022 - San Diego, United States Duration: May 31 2022 → Jun 3 2022

Publication series

Name	InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM
Volume	2022-May

Conference

Conference	21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022
Country/Territory	United States
City	San Diego
Period	05/31/22 → 06/3/22

Keywords

Surface-mount technology
artificial neural network (ANN)
computational fluid dynamics (CFD)
reflow soldering process

Access to Document

10.1109/iTherm54085.2022.9899644

Cite this

Lai, Y., Pan, K., Ha, J., Cai, C., Yang, J., Yin, P., Xu, J., & Park, S. (2022). The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model. In Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022 (InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM; Vol. 2022-May). IEEE Computer Society. https://doi.org/10.1109/iTherm54085.2022.9899644

Lai, Yangyang ; Pan, Ke ; Ha, Jonghwan et al. / The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model. Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022. IEEE Computer Society, 2022. (InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM).

@inproceedings{42b77ecf2a1b4af88ce62cb6ba95be67,

title = "The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model",

abstract = "This paper presents a physics-guided machine learning model to provide the optimal reflow recipe for a 7-zone oven. The numerical method based on the computational fluid dynamics (CFD) simulation was used to predict reflow profiles of a BGA package. After validating the CFD model with the measurement results, an automated system was programmed to collect profiles subjected to 81 sets of boundary conditions (reflow recipe). A machine learning model trained by 81 sets of input data was employed to predict profiles subjected to 148,176 sets boundary conditions rapidly. The peak temperature and time above liquidous of output profiles were extracted to quantify the performance of the corresponding boundary conditions. The boundary condition with the best reflow performance was regarded as the optimal recipe.",

keywords = "Surface-mount technology, artificial neural network (ANN), computational fluid dynamics (CFD), reflow soldering process",

author = "Yangyang Lai and Ke Pan and Jonghwan Ha and Chongyang Cai and Junbo Yang and Pengcheng Yin and Jiefeng Xu and Seungbae Park",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022 ; Conference date: 31-05-2022 Through 03-06-2022",

year = "2022",

doi = "10.1109/iTherm54085.2022.9899644",

language = "English",

series = "InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022",

}

Lai, Y, Pan, K, Ha, J, Cai, C, Yang, J, Yin, P, Xu, J & Park, S 2022, The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model. in Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022. InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM, vol. 2022-May, IEEE Computer Society, 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022, San Diego, United States, 05/31/22. https://doi.org/10.1109/iTherm54085.2022.9899644

The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model. / Lai, Yangyang; Pan, Ke; Ha, Jonghwan et al.
Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022. IEEE Computer Society, 2022. (InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM; Vol. 2022-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model

AU - Lai, Yangyang

AU - Pan, Ke

AU - Ha, Jonghwan

AU - Cai, Chongyang

AU - Yang, Junbo

AU - Yin, Pengcheng

AU - Xu, Jiefeng

AU - Park, Seungbae

PY - 2022

Y1 - 2022

N2 - This paper presents a physics-guided machine learning model to provide the optimal reflow recipe for a 7-zone oven. The numerical method based on the computational fluid dynamics (CFD) simulation was used to predict reflow profiles of a BGA package. After validating the CFD model with the measurement results, an automated system was programmed to collect profiles subjected to 81 sets of boundary conditions (reflow recipe). A machine learning model trained by 81 sets of input data was employed to predict profiles subjected to 148,176 sets boundary conditions rapidly. The peak temperature and time above liquidous of output profiles were extracted to quantify the performance of the corresponding boundary conditions. The boundary condition with the best reflow performance was regarded as the optimal recipe.

AB - This paper presents a physics-guided machine learning model to provide the optimal reflow recipe for a 7-zone oven. The numerical method based on the computational fluid dynamics (CFD) simulation was used to predict reflow profiles of a BGA package. After validating the CFD model with the measurement results, an automated system was programmed to collect profiles subjected to 81 sets of boundary conditions (reflow recipe). A machine learning model trained by 81 sets of input data was employed to predict profiles subjected to 148,176 sets boundary conditions rapidly. The peak temperature and time above liquidous of output profiles were extracted to quantify the performance of the corresponding boundary conditions. The boundary condition with the best reflow performance was regarded as the optimal recipe.

KW - Surface-mount technology

KW - artificial neural network (ANN)

KW - computational fluid dynamics (CFD)

KW - reflow soldering process

UR - https://www.scopus.com/pages/publications/85140739730

U2 - 10.1109/iTherm54085.2022.9899644

DO - 10.1109/iTherm54085.2022.9899644

M3 - Conference contribution

T3 - InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM

BT - Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022

PB - IEEE Computer Society

T2 - 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022

Y2 - 31 May 2022 through 3 June 2022

ER -

Lai Y, Pan K, Ha J, Cai C, Yang J, Yin P et al. The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model. In Proceedings of the 21st InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2022. IEEE Computer Society. 2022. (InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM). doi: 10.1109/iTherm54085.2022.9899644

The Optimal Solution of Reflow Oven Recipe based on Physics-guided Machine Learning Model

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this