Abstract
To achieve online testing of high-frequency electric resistance welding (HF-ERW) tube quality, forecasting models were established for welding defect conditions with collected high-speed images of the joint melting phenomenon, based on a radial basis function neural network (RBFNN). Firstly, the dimensions of the collected image samples were deduced by principal component analysis (PCA). Then, the reduced-dimension image samples were set as inputs of both BPNN (back-propagation neural network) and, for comparison, RBFNN, which were trained so that the model parameters were optimized. Finally, the testing sample set was identified by trained networks. The experimental results show that RBFNN had better generalization ability for HF-ERW images than BPNN, which meant that the recognition rate of low-heat input status reached 100%, while the recognition rate of overheating input status reached 97.67%. They also show that the welding quality detection system based on a neural network is very effective and has a strong guiding significance for welding quality control.
Similar content being viewed by others
Abbreviations
- a:
-
directional orientation of the system
- h:
-
strip thickness with strip thickness and strip thickness strip thickness
- λ :
-
eigenvalue vector of square matrix
- V:
-
eigenvector matrix of square matrix
- k:
-
the number of eigenvalue of image covariance matrix needed to meet the PCA dimensionality reduction effect
References
Kim, C.-M. and Kim, J.-K., “The Effect of Electromagnetic Forces on the Penetrator Formation during High-Frequency Electric Resistance Welding,” Journal of Materials Processing Technology, Vol. 209, No. 2, pp. 838–846, 2009.
Kim, D., Kim, T., Park, Y., Sung, K., Kang, M., et al., “Estimation of Weld Quality in High-Frequency Electric Resistance Welding with Image Processing,” Welding Journal-New York-, Vol. 86, No. 3, pp. 71–75, 2007.
Hu, S., “Discussing Technical Innovation of National ERW Pipe Based on Japanese Developments of Welded Pipe Technology,” Welded Pipe and Tube, Vol. 29, No. 6, pp. 52–58, 2006.
Wang, H. F., Li, Y. L., Li, J. K., “High Frequency Resistance Welding Condition Monitoring Based on Digital Image Technology,” Journal of South China University of Technology (Natural Science Edition), Vol. 40, No. 11, pp. 84–88+93, 2012.
Mihara, Y., Suzuki, K., Ohkawa, T., Harada, N., Komine, I., and Ishiro, S., “A New Automatic Heat Input Control for Production of Electric Resistance Welded Pipe,” Transactions of the Iron and Steel Institute of Japan, Vol. 26, No. 5, pp. 476–483, 1986.
Gan, Z., Fang, X., Yu, G., Yu, Y., Su, J., et al., “Creeping Wave Testing for Weld of Thin-Walled High-Frequency Electric Resistance Welded Pipe,” Welded Pipe and Tube, Vol. 37, No. 2, pp. 33–37, 2014.
Babu, G. S. and Suresh, S., “Sequential Projection-Based Metacognitive Learning in a Radial Basis Function Network for Classification Problems,” IEEE Transactions on Neural Networks and Learning Systems, Vol. 24, No. 2, pp. 194–206, 2013.
Han, L., “Artificial Neural Network Theory. Design and Application (Chinese Edition),” Chemical Industry Press, 2000.
Javed, A., “Face Recognition Based on Principal Component Analysis,” International Journal of Image, Graphics and Signal Processing, Vol. 5, No. 2, pp. 38–44, 2013.
Qiu, Z., Zhang, X., and Ye, C., “Vibration Suppression of a Flexible Piezoelectric Beam Using BP Neural Network Controller,” Acta Mechanica Solida Sinica, Vol. 25, No. 4, pp. 417–428, 2012.
Sánchez-Maroño, N., Alonso-Betanzos, A., and Pérez-Sánchez, B., “An Improved Version of the Wrapper Feature Selection Method Based on Functional Decomposition,” Artificial Neural Networks-ICANN 2007, pp. 240–249 2007.
Giraud-Carrier, C., “On the Dangers of Default Implementations: The Case of Radial Basis Function Networks,” Intelligent Data Analysis, Vol. 18, No. 2, pp. 261–279, 2014.
Masala, G. L., Golosio, B., Cutzu, R., and Pola, R., “A Two-Layered Classifier Based on the Radial Basis Function for the Screening of Thalassaemia,” Computers in Biology and Medicine, Vol. 43, No. 11, pp. 1724–1731, 2013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, HF., Cao, J., Zhao, XM. et al. Detection of HF-ERW status by neural network on imaging. Int. J. Precis. Eng. Manuf. 18, 931–936 (2017). https://doi.org/10.1007/s12541-017-0110-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12541-017-0110-8