Academic Journal of Computing & Information Science, 2024, 7(2); doi: 10.25236/AJCIS.2024.070207.
Zhonghao Qiu1, Xixin Yang1,2, Yuanlin Guan3,4, Xiang Yuan1
1College of Computer Science & Technology, Qingdao University, Qingdao, China
2School of Automation, Qingdao University, Qingdao, China
3Key Lab of Industrial Fluid Energy Conservation and Pollution Control, Ministry of Education, Qingdao University of Technology, Qingdao, China
4School of Mechanical & Automotive Engineering, Qingdao University of Technology, Qingdao, China
With the development of Industry 4.0, real-time industrial inspection has been widely focused. Steel is a critical material, and steel surface defect recognition is of great significance to the production in plants. However, defect recognition models are usually based on deep learning methods, which leads to long training time and high hardware requirements. Hence, this article proposes a novel recognition scheme for steel surface defects based on Broad Learning System (BLS). This model takes the image features extracted by the convolutional neural network as input data and inherits the advantages of the BLS, which can classify images quickly. The results indicate that the new method outperforms both the original BLS and several mainstream algorithms.
Steel Surface, Defect Recognition, Broad Learning System, Convolutional Neural Network, Incremental Learning, Dropout Method
Zhonghao Qiu, Xixin Yang, Yuanlin Guan, Xiang Yuan. Recognition of Steel Surface Defects Based on Broad Learning System. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 2: 48-58. https://doi.org/10.25236/AJCIS.2024.070207.
[1] Song, G., Song, K., & Yan, Y. (2020). EDRNet: Encoder–decoder residual network for salient object detection of strip steel surface defects. IEEE Transactions on Instrumentation and Measurement, 69(12), 9709-9719.
[2] Satish, R., Murugabhoopathy, K., Rajendhiran, N., & Vijayan, V. (2020). Technology strategy for improved safety management in steel industry. Materials today: proceedings, 33, 2660-2664.
[3] Wen, X., Shan, J., He, Y., & Song, K. (2022). Steel surface defect recognition: A survey. Coatings, 13(1), 17.
[4] Zhao, W., Chen, F., Huang, H., Li, D., & Cheng, W. (2021). A new steel defect detection algorithm based on deep learning. Computational Intelligence and Neuroscience, 2021, 1-13.
[5] Demir, K., Ay, M., Cavas, M., & Demir, F. (2023). Automated steel surface defect detection and classification using a new deep learning-based approach. Neural Computing and Applications, 35(11), 8389-8406.
[6] Konovalenko, I., Maruschak, P., Brezinová, J., Viňáš, J., & Brezina, J. (2020). Steel surface defect classification using deep residual neural network. Metals, 10(6), 846.
[7] Li, S., Wu, C., & Xiong, N. (2022). Hybrid architecture based on CNN and transformer for strip steel surface defect classification. Electronics, 11(8), 1200.
[8] Zhang, J., Li, S., Yan, Y., Ni, Z., & Ni, H. (2022). Surface Defect Classification of Steel Strip with Few Samples Based on Dual‐Stream Neural Network. Steel research international, 93(5), 2100554.
[9] Liu, Y., Yuan, Y., Balta, C., & Liu, J. (2020). A light-weight deep-learning model with multi-scale features for steel surface defect classification. Materials, 13(20), 4629.
[10] Fu, G., Sun, P., Zhu, W., Yang, J., Cao, Y., Yang, M. Y., & Cao, Y. (2019). A deep-learning-based approach for fast and robust steel surface defects classification. Optics and Lasers in Engineering, 121, 397-405.
[11] Zhao, W., Song, K., Wang, Y., Liang, S., & Yan, Y. (2023). FaNet: Feature-aware network for few shot classification of strip steel surface defects. Measurement, 208, 112446.
[12] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
[13] Chen, C. P., & Liu, Z. (2017). Broad learning system: An effective and efficient incremental learning system without the need for deep architecture. IEEE transactions on neural networks and learning systems, 29(1), 10-24.
[14] Gong, X., Zhang, T., Chen, C. P., & Liu, Z. (2021). Research review for broad learning system: Algorithms, theory, and applications. IEEE Transactions on Cybernetics, 52(9), 8922-8950.
[15] Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580.
[16] Bao, Y., Song, K., Liu, J., Wang, Y., Yan, Y., Yu, H., & Li, X. (2021). Triplet-graph reasoning network for few-shot metal generic surface defect segmentation. IEEE Transactions on Instrumentation and Measurement, 70, 1-11.