Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing

Zhe Gao, Weihong Guo, Jingjing Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Friction stir blind riveting (FSBR) is a recently developed manufacturing process for joining dissimilar lightweight materials. The objective of this study is to gain a better understanding of FSBR in joining carbon fiber-reinforced polymer composite and aluminum alloy sheets by developing a sensor fusion and process monitoring method. The proposed method establishes the relationship between the FSBR process and the quality of the joints by integrating feature extraction, feature selection, and classifier fusion. This study investigates the effectiveness of lower rank tensor decomposition methods in extracting features from multi-sensor, high-dimensional, heterogeneous profile data. The extracted features are combined with process parameters, material stack-up sequence, and engineering-driven features such as the peak force to provide rich information about the FSBR process. Sparse group lasso regression is adopted to select the optimal monitoring features. The selected features are fed into weighted classification fusion to estimate the quality of the joints. The fusion method integrates five individual classifiers with optimal weights. The correct classification rates resulted from various feature extraction and selection methods are assessed and compared. The proposed method can also be applied to other manufacturing processes with online sensing capabilities for the purpose of process monitoring and quality prediction.

Original languageEnglish (US)
Title of host publicationManufacturing Equipment and Systems
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Print)9780791851371
DOIs
StatePublished - Jan 1 2018
EventASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018 - College Station, United States
Duration: Jun 18 2018Jun 22 2018

Publication series

NameASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018
Volume3

Other

OtherASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018
CountryUnited States
CityCollege Station
Period6/18/186/22/18

Fingerprint

Riveting
Feature extraction
Fusion reactions
Friction
Monitoring
Process monitoring
Sensors
Joining
Classifiers
Dissimilar materials
Carbon fibers
Tensors
Aluminum alloys
Decomposition
Composite materials
Polymers

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Gao, Z., Guo, W., & Li, J. (2018). Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing. In Manufacturing Equipment and Systems (ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018; Vol. 3). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/MSEC2018-6507
Gao, Zhe ; Guo, Weihong ; Li, Jingjing. / Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing. Manufacturing Equipment and Systems. American Society of Mechanical Engineers (ASME), 2018. (ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018).
@inproceedings{26eff2b9a43d44a493d928e63911b9d6,
title = "Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing",
abstract = "Friction stir blind riveting (FSBR) is a recently developed manufacturing process for joining dissimilar lightweight materials. The objective of this study is to gain a better understanding of FSBR in joining carbon fiber-reinforced polymer composite and aluminum alloy sheets by developing a sensor fusion and process monitoring method. The proposed method establishes the relationship between the FSBR process and the quality of the joints by integrating feature extraction, feature selection, and classifier fusion. This study investigates the effectiveness of lower rank tensor decomposition methods in extracting features from multi-sensor, high-dimensional, heterogeneous profile data. The extracted features are combined with process parameters, material stack-up sequence, and engineering-driven features such as the peak force to provide rich information about the FSBR process. Sparse group lasso regression is adopted to select the optimal monitoring features. The selected features are fed into weighted classification fusion to estimate the quality of the joints. The fusion method integrates five individual classifiers with optimal weights. The correct classification rates resulted from various feature extraction and selection methods are assessed and compared. The proposed method can also be applied to other manufacturing processes with online sensing capabilities for the purpose of process monitoring and quality prediction.",
author = "Zhe Gao and Weihong Guo and Jingjing Li",
year = "2018",
month = "1",
day = "1",
doi = "10.1115/MSEC2018-6507",
language = "English (US)",
isbn = "9780791851371",
series = "ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "Manufacturing Equipment and Systems",

}

Gao, Z, Guo, W & Li, J 2018, Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing. in Manufacturing Equipment and Systems. ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018, vol. 3, American Society of Mechanical Engineers (ASME), ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018, College Station, United States, 6/18/18. https://doi.org/10.1115/MSEC2018-6507

Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing. / Gao, Zhe; Guo, Weihong; Li, Jingjing.

Manufacturing Equipment and Systems. American Society of Mechanical Engineers (ASME), 2018. (ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018; Vol. 3).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing

AU - Gao, Zhe

AU - Guo, Weihong

AU - Li, Jingjing

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Friction stir blind riveting (FSBR) is a recently developed manufacturing process for joining dissimilar lightweight materials. The objective of this study is to gain a better understanding of FSBR in joining carbon fiber-reinforced polymer composite and aluminum alloy sheets by developing a sensor fusion and process monitoring method. The proposed method establishes the relationship between the FSBR process and the quality of the joints by integrating feature extraction, feature selection, and classifier fusion. This study investigates the effectiveness of lower rank tensor decomposition methods in extracting features from multi-sensor, high-dimensional, heterogeneous profile data. The extracted features are combined with process parameters, material stack-up sequence, and engineering-driven features such as the peak force to provide rich information about the FSBR process. Sparse group lasso regression is adopted to select the optimal monitoring features. The selected features are fed into weighted classification fusion to estimate the quality of the joints. The fusion method integrates five individual classifiers with optimal weights. The correct classification rates resulted from various feature extraction and selection methods are assessed and compared. The proposed method can also be applied to other manufacturing processes with online sensing capabilities for the purpose of process monitoring and quality prediction.

AB - Friction stir blind riveting (FSBR) is a recently developed manufacturing process for joining dissimilar lightweight materials. The objective of this study is to gain a better understanding of FSBR in joining carbon fiber-reinforced polymer composite and aluminum alloy sheets by developing a sensor fusion and process monitoring method. The proposed method establishes the relationship between the FSBR process and the quality of the joints by integrating feature extraction, feature selection, and classifier fusion. This study investigates the effectiveness of lower rank tensor decomposition methods in extracting features from multi-sensor, high-dimensional, heterogeneous profile data. The extracted features are combined with process parameters, material stack-up sequence, and engineering-driven features such as the peak force to provide rich information about the FSBR process. Sparse group lasso regression is adopted to select the optimal monitoring features. The selected features are fed into weighted classification fusion to estimate the quality of the joints. The fusion method integrates five individual classifiers with optimal weights. The correct classification rates resulted from various feature extraction and selection methods are assessed and compared. The proposed method can also be applied to other manufacturing processes with online sensing capabilities for the purpose of process monitoring and quality prediction.

UR - http://www.scopus.com/inward/record.url?scp=85054988671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054988671&partnerID=8YFLogxK

U2 - 10.1115/MSEC2018-6507

DO - 10.1115/MSEC2018-6507

M3 - Conference contribution

AN - SCOPUS:85054988671

SN - 9780791851371

T3 - ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018

BT - Manufacturing Equipment and Systems

PB - American Society of Mechanical Engineers (ASME)

ER -

Gao Z, Guo W, Li J. Sensor fusion and on-line monitoring of friction stir blind riveting for lightweight materials manufacturing. In Manufacturing Equipment and Systems. American Society of Mechanical Engineers (ASME). 2018. (ASME 2018 13th International Manufacturing Science and Engineering Conference, MSEC 2018). https://doi.org/10.1115/MSEC2018-6507