Abstract
Certain applications have recently appeared in industry where a traditional bar code printed on a label will not survive because the item to be tracked has to be exposed to harsh environments. Laser direct-part marking is a manufacturing process used to create permanent marks on a substrate that could help to alleviate this problem. In this research, artificial neural networks were employed to model the laser direct-part marking process of Data Matrix symbols on carbon steel substrates. Several experiments were conducted to study the laser direct-part marking process and to generate data to serve as training, validation and testing data sets in the artificial neural networks modeling process. Two performance measures, mean squared error and correlation coefficient, were utilized to assess the performance of the artificial neural network models. Single-output artificial neural network models corresponding to four performance measures specific to the Data Matrix bar code symbology were found to have good learning and predicting capabilities. The single-output artificial neural network models were compared to equivalent multiple linear regression models for validation purposes. The prediction capability of the single-output artificial neural network models with respect to laser direct-part marking of Data Matrix symbols on carbon steel substrates was superior to that of the multiple linear regression models.
Similar content being viewed by others
References
AIM (2004) X5-XC Set USS (6) Dot & matrix symbologies—data matrix, MaxiCode, Dot Code A, Code One, QR Code and Aztec Mesas.
F. Ba (1998) ArticleTitleTechnical study on laser marking of slide calipers Proceedings of SPIE 3550 336–341
Cherniavsky, O. (1999) New data encoding technology improves part tracking. Quality Digest Magazine. http://www.qualitydigest.com/mar99/html/datamat.html
R. C. Crafer P. J. Oakley (Eds) (1993) Laser Processing in Manufacturing Chapman & Hall London
J. R. Davis (Eds) (1996) ASM Specialty Handbook: Carbon and Alloy Steels ASM International Ohio
G. Garman J. H. Ponce (1986) ArticleTitleYAG laser marking The Industrial Laser Annual Handbook 1986 IssueIDEdition 629 121–131
D. Graupe (1997) Advanced Series on Circuits and Systems—Vol. 3: Principles of al Networks World Scientific NJ
H. Hayakawa (2000) ArticleTitleA laser method for marking bar codes on glass substrates Proceedings of SPIE 4088 363–366
S. Haykin (1999) Neural Networks: A Comprehensive Foundation EditionNumber2 Prentice Hall NJ
International Standard (ISO/IEC). (2000) ISO/IEC 16022 Information Technology—International Symbology Specification—Data Matrix.
Jangsombatsiri, W. and Porter, J.D. (2004) Issues in direct-part marking of data matrix bar codes, Proceedings of the 13th Industrial Engineering Research Conference, Houston, TX.
J. Y. Jeng T. F. Mau S. M. Leu (2000) ArticleTitlePrediction of laser butt joint welding parameters using back propagation and learning vector quantization networks Journal of Materials Processing Technology 99 207–218 Occurrence Handle10.1016/S0924-0136(99)00424-0
B. H. Klimt (1988) ArticleTitleReview of laser marking and engraving Lasers and Optronics 7 IssueID9 61–67
T. J. McKee (1996) ArticleTitleHow lasers mark Electrotechnology 7 IssueID2 27–31
National Aeronautics and Space Administration (NASA). (2001) NASA technical handbook: application of data of data matrix identification symbols to aerospace parts using direct part marking methods/techniques.
Navas, D. (2001) The extended electronics supply chain. ID Systems, 21(2) http://www.idsystems.com/ reader/2001/2001 02/exte0201/index.htm
T. W. Ng S. C. Yeo (2001) ArticleTitleAesthetic laser marking assessment using luminance ratios Optics and Lasers in Engineering 35 177–186
J. M. O’Reilly R. A. Mosher W. L. Goffe (1979) ArticleTitleScanned laser marking of metallic and organic films Photographic Science and Engineering 23 IssueID5 314–318
S. J. Parnas (1989) ArticleTitleUsing lasers for changeable marking of PCBs and components Electronic Manufacturing 35 IssueID6 15–17
Payne, P. (1999) Direct marking trends. ID Systems, 19(2) http://www.idsystems.com/reader/ 1999_02/dir0299.htm
P. Picton (2000) Neural Networks Palgrave New York
J. Qi K. Wang M. Liang Y. Zhu M. Fang (1998) ArticleTitleLaser marking of stainless steel with a Q-switched Nd:YAG Laser SPIE 3550 311–315
RVSI (2004) http://www.rvsi.com/ACUITYCIMATRIX/index.htm
M. A. Saifi U. Paek (1973) ArticleTitleScribing glass with pulsed and Q-switched CO2 laser American Ceramic Society Bulletin 52 IssueID11 838–841
Sharp, K. R. (2001) 2-D is starting to measure up. Supply Chain Systems Magazines, 21(10) http://209.35.212.232/reader/2001/2001_10/ 2d1001/index.htm
D. D. Sheu (2000) ArticleTitleA laser marking system for flexible circuit identification Journal of Manufacturing Systems 19 IssueID3 202–212
B. Williams L. H. Healy SuffixJr. (1988) ArticleTitleLasers maker their mark Circuit Manufacturing 28 IssueID4 29–32
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jangsombatsiri, W., Porter, J.D. Artificial Neural Network Approach to Data Matrix Laser Direct Part Marking. J Intell Manuf 17, 133–147 (2006). https://doi.org/10.1007/s10845-005-5517-x
Issue Date:
DOI: https://doi.org/10.1007/s10845-005-5517-x