Abstract
In narrow overlap welding, serious defects in the weld will lead to band breakage accident, and the whole hot dip galvanizing unit will be shut down. Laser vision inspection hardware is used to collect real-time image of weld surface, and image defect recognition and evaluation system is developed to real-time detect quality. Firstly, region division is implemented. In view of the characteristics of gray image such as large information, low contrast and blurred edge, an improved image segmentation algorithm is proposed by using image convolution to enhance edge features and combining with integral image, which can quickly and accurately extract the weld edge and divide the region, and the processing time can meet the real-time requirements. Then comparing the effect of traditional method and convolution neural network in identifying defects, VGG16 is used to identify weld defects. In order to ensure real-time performance, a two-stage weld defect recognition is proposed. First, the large defective area is identified, and then, the defect is accurately identified in the area. This method can quickly extract defect areas and complete weld defect classification. Experiments show that the accuracy can reach 97% and average running time takes 3.2 s, meeting the online detection requirements.
Similar content being viewed by others
References
Zhang, C.: Resistance welding technology and its application equipment. Electron. Technol. 24(5), 201–203 (2017)
Yang, J., Li, Z., Fan, L., et al.: Weld surface defect detection system based on linear laser scanning. Welding 2, 19–23 (2016)
Fei, Z., Yang, E., Hu, H., et al.: Review of machine vision-based electronic travel aids. In: Automation and Computing (ICAC), 23rd International Conference on. IEEE, 2017, pp. 1–7 (2017)
Singhka, D.K.H., Neogi, N., Mohanta, D.: Surface defect classification of steel strip based on machine vision. In: Computer and Communications Technologies (ICCCT), 2014 International Conference on IEEE, pp. 1–5 (2014)
Zhang, Y., Liu, S., Cao, J., et al.: Wood board image processing based on dual-tree complex wavelet feature selection and compressed sensing. Wood Sci. Technol. 50(2), 1–15 (2016)
Wang, H., Miao, R., Wu, X.S., et al.: Polycrystalline silicon wafer surface color defect inspection based on machine vision. Appl. Mech. Mater. 548–549, 48–52 (2014)
Hao, X., Li, B.: Detection of rail track surface defects based on machine vision. J. Beijing Jiaotong Univ. 39(2), 28 (2015)
He, D., Xu, K., Zhou, P.: Defect detection of hot rolled steels with a new object detection framework called classification priority network. Comput. Ind. Eng. 128, 290–297 (2019)
Kai, L.: Fingerprint feature fusion method based on local structure of minutiae and LBP. Inf. Technol. 9, 109–112 (2017)
Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2037–2041 (2006)
Hu, H., Peng, G., Wang, X., Zhou, Z.: Weld defect classification using 1-D LBP feature extraction of ultrasonic signals. Nondestr. Test. Eval. 33(1), 92–108 (2018)
Wang, L., Wang, X.-F.: Identification of weld defects based on rotation-invariant HOG feature. Comput. Syst. Appl. 27(02), 157–162 (2018)
Tamilselvan, P., Wang, P.: Failure diagnosis using deep belief learning based health state classification. Reliab. Eng. Syst. Saf. 115(Jul.), 124–135 (2013)
Bondarenko, A., Borisov, A.: Research on the classification ability of deep belief networks on small and medium datasets. Inf. Technol. Manag. Sci. 16(1), 60–65 (2013)
Krauss, C., Do, X.A., Huck, N.: Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur. J. Oper. Res. 259(2), 689–702 (2017)
Nie, Z., Ma, H., Lin, Y.: Structural damage detection with automatic feature-extraction through deep learning. Comput.-Aided Civ. Infrastruct. Eng. 32(12), 1025–1046 (2017)
Donahue, J., Hendricks, L.A., Rohrbach, M., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 677–691 (2017a)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Liu, Y., Yang, E., Fei, Y., et al.: Automated pixel-level pavement crack detection on 3D Asphalt surfaces using a deep-learning network. Comput.-Aided Civ. Infrastruct. Eng. 32(10), 805–819 (2017)
Wan, X., Wang, Y., Zhao, D., et al.: A comparison of two types of neural network for weld quality prediction in small scale resistance spot welding. Mech. Syst. Signal Process. 93, 634–644 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)
Rawat, W., Wang, Z.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29(9), 2352–2449 (2017). https://doi.org/10.1162/neco_a_00990
Cha, Y.-J., Choi, W., Buyukozturk, O.: Deep learning-based crack damage detection using convolutional neural networks. Comput.-Aided Civ. Infrastruct. Eng. 32(5), 361–378 (2017)
Zhiqiang, C., Chuan, L., Sanchez, R.-V.: Gearbox fault identification and classification with convolutional neural networks. Shock Vib. 2015, 1–10 (2015)
Chen, Z., Li, C., Sánchez, R.V.: Multi-layer neural network with deep belief network for gearbox fault diagnosis. J. Vibroeng. 17(5), 2379–2392 (2015)
Gan, M., Wang, C., Zhu, C.: Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mech. Syst. Signal Process. 72, 92–104 (2016)
Lin, Y., Nie, Z., Ma, H.: Structural damage detection with automatic feature-extraction through deep learning. Comput.-Aided Civ. Infrastruct. Eng. 32(12), 1025–1046 (2017)
Donahue, J., Hendricks, L.A., Rohrbach, M., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677–691 (2017b)
Fu, Y., Zhang, Y., Gao, Y., et al.: Machining vibration states monitoring based on image representation using convolutional neural networks. Eng. Appl. Artif. Intell. 65, 240–251 (2017)
Zhang, A., Wang, K.C.P., Li, B., Yang, E., Dai, X., Peng, Y., Fei, Y., Liu, Y., Li, J.Q., Chen, C.: Automated Pixel-level pavement crack detection on 3D Asphalt surfaces using a deep-learning network. Comput.-Aided Civ. Infrastruct. Eng. 32(10), 805–819 (2017)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2014)
Jiao, Z., Jia, G., Cai, Y.: A new approach to oil spill detection that combines deep learning with unmanned aerial vehicles. Comput. Ind. Eng. 135, 1300–1311 (2019)
Cha, Y.-J., Choi, W., Suh, G., et al.: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput.-Aided Civ. Infrastruct. Eng. 33(4), 1–17 (2018)
Kang, D., Benipal, S.S., Gopal, D.L., Cha, Y.-J.: Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning. Autom. Constr. 118, 103291 (2020)
Beckman, G.H., Polyzois, D., Cha, Y.-J.: Deep learning-based automatic volumetric damage quantification using depth camera. Autom. Constr. 99(MAR), 114–124 (2018)
Choi, W., Cha, Y.-J.: SDDNet: real-time crack segmentation. IEEE Trans. Ind. Electron. 67(9), 8016–8025 (2020)
Nakama, T.: Theoretical analysis of batch and on-line training for gradient descent learning in neural networks. Neurocomputing 73(1–3), 151–159 (2009)
Lin, G., Shen, W.: Research on convolutional neural network based on improved Relu piecewise activation function. Proc. Comput. Sci. 131, 977–984 (2018)
Li, X.B., Wang, W.Q.: Learning discriminative features via weights-biased softmax loss. Pattern Recogn. 2020, 107405 (2020)
Acknowledgements
The authors gratefully acknowledge the financial support of the National Natural Science foundation, China.
Funding
This work was supported by the National Natural Science Foundation, China (Nos. 51435009, 71971139).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Miao, R., Jiang, Z., Zhou, Q. et al. Online inspection of narrow overlap weld quality using two-stage convolution neural network image recognition. Machine Vision and Applications 32, 27 (2021). https://doi.org/10.1007/s00138-020-01158-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00138-020-01158-2