Application of Sanger Operator with Lateral Connection in Fitting Micro-Drill’s Main Lips

Abstract:

A new approach for straightness fitting of micro-drill’s main lips is proposed. While its chips are measured, micro-drill’s projective images are collected with high precision automatic test system of PCB Micro-drill, and sub-pixel edge features are extracted. The sum of square distances' from the coordinates of sample points to fitted line is taken as objective function. Then a Sanger neural network with lateral connection is designed, where a self-adaptive minor component extracting method is adopted. When the system comes to equilibrium, the eigenvector of minimum eigen value is the fitted line coefficient, from which chips of micro-drill main lips are obtained. The proposed approach is the novel application of Sanger neural network in straightness fitting.

• Periodical: Applied Mechanics and Materials (Volumes 26-28)
• Pages: 1093-1098
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.26-28.1093
• Online since: June 2010
• Authors: Dong Yuan Ge, Xi Fan Yao, Wen Jiang Xiang, Ying Zhi Gu
• Keywords: Combined Vector Coordinates, Eigen Value, Eigenvectors, Main Lips, Micro-Drill, Sanger Neural Network

References

[1] Tien F C, Yeh C H and Hsieh K H. Automated visual inspection for micro-drills in printed circuit board production [J]. International Journal of Production Research, 2004, 2(12): 2477-2495.

DOI: 10.1080/00207540310001659656

[2] HU Songli, XU Li-ming and XU Kai-zhou, et al. Adaptive Contour Corner Detection of Micro-drill's First Facet [J]. Journal of Shanghai Jiao Tong University. 2009, 43(5): 825-829.

[3] HUANG Fugui, CUI Changcai. New Method for Evaluating Arbitrary Spatial Straightness Error[J]. Chinese Journal of Mechanical Engineering, 2008, 44(7): 221-224. (In Chinese).

DOI: 10.3901/jme.2008.07.221

[4] JIA Lide, ZHENG Ziwen and LI Shengyi, et al. Measurement Method of Straightness Error of a Long Ultra-precise Guideway with a Short Benchmark[J]. Chinese Journal of Mechanical Engineering, 2008, 44(9): 141-147. (In Chinese).

DOI: 10.3901/jme.2008.09.141

[5] HUANG Fu-gui, CUI Chang-cai. Comparison of evaluating precision of straightness error between least square method and least envelope zone method[J]. Optics and Precision Engineering, 2007, 15(6): 889-892. (In Chinese).

DOI: 10.1109/iita-grs.2010.5603259

[6] Sanger T D. Optimal Unsupervised Learning in a Single-Layer Linear Feedforward NN. Neural Networks, 1989, 2: 459-473.

DOI: 10.1016/0893-6080(89)90044-0

[7] S. Y. Kung. et al. A Neural Network Learning Algorithm for Adaptive Principle Components Extraction(APEX). Proc ICASSP, 1990, 2: 861-864.

[8] State L., Cocianu C., Vlamos P., et al. Neural approaches to image compression/decompression using PCA based learning algorithms[C]. Proc. Int. Workshop Pattern Recogn. Inf. Syst. - PRIS 2008, 187-192.

DOI: 10.5220/0001728701870192

[9] Palmieri F, et al. Anti-Hebbian Learning Algorithm for Adaptive Principle Components Extraction. Proc ICASSP, 1990, 2, 861-864.

[10] Hasan M. A., Hasan J. A. K. Sanger's type dynamical systems for canonical variate analysis[C]. Proceedings of the 2008 American Control Conference, 4087-4092.

DOI: 10.1109/acc.2008.4587133

[11] J. Canny. A Computational Approach to Edge Detection [J]. IEEE. Transactions on Analysis and Machine Intelligence, 1986, 8(6), 679-698.

DOI: 10.1109/tpami.1986.4767851

[12] Lin, C. C., Chen, Y. H. and Chang, C. C. LSB-based High-Capacity Data Embedding Scheme for Digital Images [J], Inter. Journal of Innovative Computing, Info. and Control. 5(11B): 4283-4289, (2009).