Research Papers

Profile Monitoring and Fault Diagnosis Via Sensor Fusion for Ultrasonic Welding

[+] Author and Article Information
Weihong (Grace) Guo

Department of Industrial and Systems Engineering,
Rutgers, The State University of New Jersey,
Piscataway, NJ 08854
e-mail: wg152@rutgers.edu

Jionghua (Judy) Jin

Fellow ASME
Department of Industrial and Operations Engineering,
The University of Michigan,
Ann Arbor, MI 48109
e-mail: jhjin@umich.edu

S. Jack Hu

Fellow ASME
Department of Mechanical Engineering,
The University of Michigan,
Ann Arbor, MI 48109
e-mail: jackhu@umich.edu

1Corresponding author.

Manuscript received May 17, 2018; final manuscript received May 1, 2019; published online June 10, 2019. Assoc. Editor: Dragan Djurdjanovic.

J. Manuf. Sci. Eng 141(8), 081001 (Jun 10, 2019) (13 pages) Paper No: MANU-18-1338; doi: 10.1115/1.4043731 History: Received May 17, 2018; Accepted May 03, 2019

Sensor signals acquired during the manufacturing process contain rich information that can be used to facilitate effective monitoring of operational quality, early detection of system anomalies, and quick diagnosis of fault root causes. This paper develops a method for effective monitoring and diagnosis of multisensor heterogeneous profile data based on multilinear discriminant analysis. The proposed method operates directly on the multistream profiles and then extracts uncorrelated discriminative features through tensor-to-vector projection, and thus, preserving the interrelationship of different sensors. The extracted features are then fed into classifiers to detect faulty operations and recognize fault types. The developed method is demonstrated with both simulated and real data from ultrasonic metal welding.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.


Woodall, W. H., Spitzner, D. J., Montgomery, D. C., and Gupta, S., 2004, “Using Control Charts to Monitor Process and Product Quality Profiles,” J. Qual. Technol., 36(3), pp. 309–320. [CrossRef]
Woodall, W. H., 2007, “Current Research on Profile Monitoring,” Produção, 17(3), pp. 420–425.
Lee, S. S., Shao, C., Kim, T. H., Hu, S. J., Kannatey-Asibu, E., Cai, W. W., Spicer, J. P., Wang, H., and Abell, J. A., 2014, “Characterization of Ultrasonic Metal Welding by Correlating Online Sensor Signals With Weld Attributes,” ASME J. Manuf. Sci. Eng., 136(5), p. 051019. [CrossRef]
Lee, S. S., Kim, T. H., Hu, S. J., Cai, W. W., and Abell, J. A., 2010, “Joining Technologies for Automotive Lithium-Ion Battery Manufacturing—A Review,” Proceedings of ASME 2010 International Manufacturing Science and Engineering Conference, Erie, PA, Oct. 12–15, pp. 541–549.
Kalpakjian, S., and Schmid, S. R., 2008, Manufacturing Processes for Engineering Materials, Pearson Education, Upper Saddle River, NJ.
Kim, T. H., Yum, J., Hu, S. J., Spicer, J. P., and Abell, J. A., 2011, “Process Robustness of Single Lap Ultrasonic Welding of Thin Dissimilar Materials,” CIRP Ann. Manuf. Technol., 60(1), pp. 17–20. [CrossRef]
Shao, C., Kim, T. H., Hu, S. J., Jin, J., Abell, J. A., and Spicer, J. P., 2015, “Tool Wear Monitoring for Ultrasonic Metal Welding of Lithium-Ion Batteries,” ASME J. Manuf. Sci. Eng., 138(5), p. 051005. [CrossRef]
Guo, W., Shao, C., Kim, T. H., Hu, S. J., Jin, J., Spicer, J. P., and Wang, H., 2016, “Online Process Monitoring With Near-Zero Misdetection for Ultrasonic Welding of Lithium-Ion Batteries: An Integration of Univariate and Multivariate Methods,” J. Manuf. Syst., 38, pp. 141–150. [CrossRef]
Kuljanic, E., Totis, G., and Sortino, M., 2009, “Development of an Intelligent Multisensor Chatter Detection System in Milling,” Mech. Syst. Signal Process., 23(5), pp. 1704–1718. [CrossRef]
Cho, S., Binsaeid, S., and Asfour, S., 2010, “Design of Multisensor Fusion-Based Tool Condition Monitoring System in End Milling,” Int. J. Adv. Manuf. Technol., 46, pp. 681–694. [CrossRef]
Noorossana, R., Saghaei, A., and Amiri, A., 2012, Statistical Analysis of Profile Monitoring, Wiley, New York.
Grasso, M., Albertelli, P., and Colosimo, B. M., 2013, “An Adaptive SPC Approach for Multi-Sensor Fusion and Monitoring of Time-Varying Processes,” Proc. CIRP, 12, pp. 61–66. [CrossRef]
Basir, O., and Yuan, X., 2007, “Engine Fault Diagnosis Based on Multisensory Information Fusion Using Dempster–Shafer Evidence Theory,” Inf. Fusion, 8(4), pp. 379–386. [CrossRef]
Kim, J., Huang, Q., Shi, J., and Chang, T.-S., 2006, “Online Multichannel Forging Tonnage Monitoring and Fault Pattern Discrimination Using Principal Curve,” ASME J. Manuf. Sci. Eng., 128(4), pp. 944–950. [CrossRef]
Amiri, A., Zou, C., and Doroudyan, M. H., 2013, “Monitoring Correlated Profile and Multivariate Quality Characteristics,” Qual. Reliab. Eng. Int., 30(1), pp. 133–142. [CrossRef]
Chou, S. H., Chang, S. I., and Tsai, T. R., 2014, “On Monitoring of Multiple Non-Linear Profiles,” Int. J. Prod. Res., 52(11), pp. 3209–3224. [CrossRef]
Paynabar, K., Jin, J., and Pacella, M., 2013, “Monitoring and Diagnosis of Multichannel Nonlinear Profile Variations Using Uncorrelated Multilinear Principal Component Analysis,” IIE Trans., 45(11), pp. 1235–1247. [CrossRef]
Lu, H., Plataniotis, K. N., and Venetsanopoulos, A. N., 2009, “Uncorrelated Multilinear Principal Component Analysis for Unsupervised Multilinear Subspace Learning,” IEEE Trans. Neural Netw., 20(11), pp. 1820–1836. [CrossRef] [PubMed]
Grasso, M., Colosimo, B. M., and Pacella, M., 2014, “Profile Monitoring Via Sensor Fusion: The Use of PCA Methods for Multi-Channel Data,” Int. J. Prod. Res., 52(20), pp. 6110–6135. [CrossRef]
Lu, H., Plataniotis, K. N., and Venetsanopoulos, A. N., 2008, “MPCA: Multilinear Principal Component Analysis of Tensor Objects,” IEEE Trans. Neural Netw., 19(1), pp. 18–39. [CrossRef] [PubMed]
Lu, H., Plataniotis, K. N., and Venetsanopoulos, A. N., 2009, “Uncorrelated Multilinear Discriminant Analysis With Regularization and Aggregation for Tensor Object Recognition,” IEEE Trans. Neural Netw., 20(1), pp. 103–123. [CrossRef] [PubMed]
De Lathauwer, L., De Moor, B., and Vandewalle, J., 2000, “A Multilinear Singular Value Decomposition,” SIAM J. Matrix Anal. Appl., 21(4), pp. 1253–1278. [CrossRef]
Kolda, T. G., and Bader, B. W., 2009, “Tensor Decompositions and Applications,” SIAM Rev., 51(3), pp. 455–500. [CrossRef]
Acar, E., and Yener, B., 2009, “Unsupervised Multiway Data Analysis: A Literature Survey,” IEEE Trans. Knowl. Data Eng., 21(1), pp. 6–20. [CrossRef]
Kiers, H. A. L., 2000, “Towards a Standardized Notation and Terminology in Multiway Analysis,” J. Chemom., 14(3), pp. 105–122. [CrossRef]
Jin, Z., Yang, J. Y., Hu, Z. S., and Lou, Z., 2001, “Face Recognition Based on the Uncorrelated Discriminant Transformation,” Pattern Recognit., 34(7), pp. 1405–1416. [CrossRef]
Duda, R. O., Hart, P. E., and Stork, D. G., 2012, Pattern Classification, John Wiley & Sons, New York.
Donoho, D. L., and Johnstone, I. M., 1994, “Ideal Spatial Adaptation by Wavelet Shrinkage,” Biometrika, 81(3), pp. 425–455. [CrossRef]
Ye, J., 2005, “Characterization of a Family of Algorithms for Generalized Discriminant Analysis on Undersampled Problems,” J. Mach. Learn. Res., 6, pp. 483–502.
Ye, J., Xiong, T., Li, Q., Janardan, R., Bi, J., Cherkassky, V., and Kambhamettu, C., 2006, “Efficient Model Selection for Regularized Linear Discriminant Analysis,” Proceedings of the 15th ACM International Conference on Information and Knowledge Management, Arlington, VA, Nov. 6–11, pp. 532–539.
Ho, T. K., 1998, “The Random Subspace Method for Constructing Decision Forests,” IEEE Trans. Pattern Anal. Mach. Intell., 20(8), pp. 832–844. [CrossRef]
Hastie, T., Tibshirani, R., and Friedman, J., 2008, The Elements of Statistical Learning, 2nd ed., Springer, New York.
BRANSON Ultrasonics Corporation, 2007, “BRANSON, BRANSON Ultraweld® L20,” BRANSON Ultrasonics Corporation.
Hu, S. J., 2011, Technical Report: On-Line Quality Monitoring System for Ultrasonic Battery Tab Welding, General Motors Collaborative Research Lab at the University of Michigan, Ann Arbor, MI.


Grahic Jump Location
Fig. 1

Ultrasonic metal welding process (adapted from Lee et al. [4])

Grahic Jump Location
Fig. 2

Examples of the power and displacement signals from ultrasonic welding

Grahic Jump Location
Fig. 3

Benchmark signals “blocks,” “heavysine,” and “bumps”

Grahic Jump Location
Fig. 4

Simulated 100 in-control profile samples

Grahic Jump Location
Fig. 5

Framework of profile monitoring and fault diagnosis using multistream signals

Grahic Jump Location
Fig. 6

Case A dataset: 1200 samples in 6 classes

Grahic Jump Location
Fig. 7

Eigentensors from R-UMLDA in simulation case A

Grahic Jump Location
Fig. 8

Classification performance of NNC for R-UMLDA features in case A test dataset

Grahic Jump Location
Fig. 9

Classification performance of NNC for various feature extractors in (a) case A test dataset, (b) case B test dataset, (c) case C test dataset, and (d) case C′ test dataset

Grahic Jump Location
Fig. 10

Classification performance of the random subspace method for multiple R-UMLDA extractors in case A test dataset

Grahic Jump Location
Fig. 11

Sensor signals and samples from ultrasonic metal welding processes. (a) Welds from the normal welding process and three faulty processes: surface contamination, abnormal thickness, and mislocated/edge weld (from left to right). (b) Sensor signals from the normal welding process and three faulty processes.

Grahic Jump Location
Fig. 12

Eigentensors from R-UMLDA in ultrasonic metal welding

Grahic Jump Location
Fig. 13

Classification results of NNC for UMLDA and VLDA in ultrasonic welding



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In