Multi-sensor data fusion for online quality assurance in flash welding

Yun Chen, Shijie Su, Qiao Li, Hui Yang

Research output: Contribution to journalConference article

Abstract

The flash welding process is a mainstream to manufacture anchor chains in the shipbuilding industry. However, traditional quality control approaches only use the tension test of the whole chain. This cannot adequately guarantee the quality of each anchor chain. Also, the incurred cost of post-build repair is far more than production. There is an urgent need to design and develop new quality control methods for real-time monitoring and control of flash welding processes. In this investigation, we firstly develop a data acquisition and control system to collect sensor data pertinent to process dynamics (i.e., electrode-position and electric-current profiles) and monitor the flash welding process in real time. Then a novel spatiotemporal warping approach is proposed to quantify the dissimilarity of electric-current and electrode-position signals collected in the flash welding process. Further, we embed the resulted warping matrix into feature vectors in the low-dimensional space that preserves the dissimilarity distances. Finally, Dirichlet Process (DP) models are proposed to cluster embedded features (coordinates in low-dimensional space). Experimental results demonstrated that the proposed methodology not only effectively reveals the directional differences among flash welding profiles, but also significantly outperforms traditional clustering algorithms such as the K-means approach, i.e., 13.25%, 1.67% and 12.33% increases in the prediction performance with the use of electric-current, electrode-position and combination recordings, respectively.

Original languageEnglish (US)
Pages (from-to)857-866
Number of pages10
JournalProcedia Manufacturing
Volume34
DOIs
StatePublished - Jan 1 2019
Event47th SME North American Manufacturing Research Conference, NAMRC 2019 - Erie, United States
Duration: Jun 10 2019Jun 14 2019

Fingerprint

Flash welding
Sensor data fusion
Quality assurance
Electric currents
Anchors
Electrodes
Quality control
Shipbuilding
Clustering algorithms
Data acquisition
Repair
Control systems
Monitoring
Sensors
Costs
Industry

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Cite this

Chen, Yun ; Su, Shijie ; Li, Qiao ; Yang, Hui. / Multi-sensor data fusion for online quality assurance in flash welding. In: Procedia Manufacturing. 2019 ; Vol. 34. pp. 857-866.
@article{e645b60372c34d8aab8588534777e10c,
title = "Multi-sensor data fusion for online quality assurance in flash welding",
abstract = "The flash welding process is a mainstream to manufacture anchor chains in the shipbuilding industry. However, traditional quality control approaches only use the tension test of the whole chain. This cannot adequately guarantee the quality of each anchor chain. Also, the incurred cost of post-build repair is far more than production. There is an urgent need to design and develop new quality control methods for real-time monitoring and control of flash welding processes. In this investigation, we firstly develop a data acquisition and control system to collect sensor data pertinent to process dynamics (i.e., electrode-position and electric-current profiles) and monitor the flash welding process in real time. Then a novel spatiotemporal warping approach is proposed to quantify the dissimilarity of electric-current and electrode-position signals collected in the flash welding process. Further, we embed the resulted warping matrix into feature vectors in the low-dimensional space that preserves the dissimilarity distances. Finally, Dirichlet Process (DP) models are proposed to cluster embedded features (coordinates in low-dimensional space). Experimental results demonstrated that the proposed methodology not only effectively reveals the directional differences among flash welding profiles, but also significantly outperforms traditional clustering algorithms such as the K-means approach, i.e., 13.25{\%}, 1.67{\%} and 12.33{\%} increases in the prediction performance with the use of electric-current, electrode-position and combination recordings, respectively.",
author = "Yun Chen and Shijie Su and Qiao Li and Hui Yang",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.promfg.2019.06.162",
language = "English (US)",
volume = "34",
pages = "857--866",
journal = "Procedia Manufacturing",
issn = "2351-9789",
publisher = "Elsevier BV",

}

Multi-sensor data fusion for online quality assurance in flash welding. / Chen, Yun; Su, Shijie; Li, Qiao; Yang, Hui.

In: Procedia Manufacturing, Vol. 34, 01.01.2019, p. 857-866.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Multi-sensor data fusion for online quality assurance in flash welding

AU - Chen, Yun

AU - Su, Shijie

AU - Li, Qiao

AU - Yang, Hui

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The flash welding process is a mainstream to manufacture anchor chains in the shipbuilding industry. However, traditional quality control approaches only use the tension test of the whole chain. This cannot adequately guarantee the quality of each anchor chain. Also, the incurred cost of post-build repair is far more than production. There is an urgent need to design and develop new quality control methods for real-time monitoring and control of flash welding processes. In this investigation, we firstly develop a data acquisition and control system to collect sensor data pertinent to process dynamics (i.e., electrode-position and electric-current profiles) and monitor the flash welding process in real time. Then a novel spatiotemporal warping approach is proposed to quantify the dissimilarity of electric-current and electrode-position signals collected in the flash welding process. Further, we embed the resulted warping matrix into feature vectors in the low-dimensional space that preserves the dissimilarity distances. Finally, Dirichlet Process (DP) models are proposed to cluster embedded features (coordinates in low-dimensional space). Experimental results demonstrated that the proposed methodology not only effectively reveals the directional differences among flash welding profiles, but also significantly outperforms traditional clustering algorithms such as the K-means approach, i.e., 13.25%, 1.67% and 12.33% increases in the prediction performance with the use of electric-current, electrode-position and combination recordings, respectively.

AB - The flash welding process is a mainstream to manufacture anchor chains in the shipbuilding industry. However, traditional quality control approaches only use the tension test of the whole chain. This cannot adequately guarantee the quality of each anchor chain. Also, the incurred cost of post-build repair is far more than production. There is an urgent need to design and develop new quality control methods for real-time monitoring and control of flash welding processes. In this investigation, we firstly develop a data acquisition and control system to collect sensor data pertinent to process dynamics (i.e., electrode-position and electric-current profiles) and monitor the flash welding process in real time. Then a novel spatiotemporal warping approach is proposed to quantify the dissimilarity of electric-current and electrode-position signals collected in the flash welding process. Further, we embed the resulted warping matrix into feature vectors in the low-dimensional space that preserves the dissimilarity distances. Finally, Dirichlet Process (DP) models are proposed to cluster embedded features (coordinates in low-dimensional space). Experimental results demonstrated that the proposed methodology not only effectively reveals the directional differences among flash welding profiles, but also significantly outperforms traditional clustering algorithms such as the K-means approach, i.e., 13.25%, 1.67% and 12.33% increases in the prediction performance with the use of electric-current, electrode-position and combination recordings, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85072391056&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072391056&partnerID=8YFLogxK

U2 - 10.1016/j.promfg.2019.06.162

DO - 10.1016/j.promfg.2019.06.162

M3 - Conference article

AN - SCOPUS:85072391056

VL - 34

SP - 857

EP - 866

JO - Procedia Manufacturing

JF - Procedia Manufacturing

SN - 2351-9789

ER -