A Vision Inspection System for the Defects of Resistance Spot Welding Based on Neural Network

The appearance of spot welding reflects the quality of welding to a large extent. In this study, we developed a vision inspection system, which recognizes the defects of weld in electronic components based on neural network. First, the images of weld are acquired by color camera. Then, we extracted 15 features from the welding images that had been corrected and enhanced. Finally, we used 1800 training samples to train the neural network. And then we got a accuracy of 95.82% under 407 testing samples by the neural network classifier, which had 15 input nodes, 4 hidden nodes and 2 output nodes.

[2]  Zhongqin Lin,et al.  Neuro-Fuzzy Hybrid Intelligent Industrial Control and Monitoring Study on Weld Quality Control of Resistance Spot Welding Using a Neuro-Fuzzy Algorithm , 2004, KES.

[3]  A. Kokabi,et al.  Metallurgical characteristics and failure mode transition for dissimilar resistance spot welds between ultra-fine grained and coarse-grained low carbon steel sheets , 2015 .

[4]  Jürgen Biber,et al.  Quality evaluation in resistance spot welding by analysing the weld fingerprint on metal bands by computer vision , 2007 .

[5]  Yaowu Shi,et al.  Ultrasonic nondestructive evaluation of spot welds for zinc-coated high strength steel sheet based on wavelet packet analysis , 2009 .

[6]  Li Yu,et al.  The research of defect recognition for radiographic weld image based on fuzzy neural network , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[7]  A. Kokabi,et al.  On the Failure Behavior of Highly Cold Worked Low Carbon Steel Resistance Spot Welds , 2014, Metallurgical and Materials Transactions A.

[8]  Zhou Jing-li.  A Local-Threshold Segment Algorithm Based on Edge-detection , 2003 .

[9]  Sehun Rhee,et al.  New technology for measuring dynamic resistance and estimating strength in resistance spot welding , 2000 .

[10]  Hao Wang,et al.  Detection of line weld defects based on multiple thresholds and support vector machine , 2008 .

[11]  Óscar Martín,et al.  Artificial neural networks for quality control by ultrasonic testing in resistance spot welding , 2007 .