Design of an Intelligent System Using RNNs to Detect Steel Plate Surface Defects
DOI:
https://doi.org/10.22399/ijcesen.2217Keywords:
Defect detection, Classification, Convolution Neural Network , Recurrent Convolution Neural NetworkAbstract
For the steel manufacturing sector, steel defect diagnostics is crucial since it has a direct impact on both production efficiency and product quality. Although product quality control is less automated and unreliable in identifying steel imperfections in the surface, it suffers from a real-time diagnostic capacity. This paper introduces a Recurrent Neural Network (RNN) approach for detecting defects in steel plate manufacturing. The steel manufacturing plants may encounter a variety of flaws, including scratches, holes, crazing, and dirt. In the proposal, the first step is to take a different number of defective and non-defective images and then extract the feature using the wavelet transform. Prepare a feature matrix with 13 features for each image. The completed data set is fed into an RNN to assess the suggested algorithm's effectiveness during testing and training. The proposed method is evaluated using both online and industry data. Also feeding different numbers of images to determine the accuracy of suggested algorithms. The proposed approach is implemented using MATLAB software. The proposed strategies have an accuracy of 98.25% based on empirical data.
References
[1]YANG WANG et. Al. Efficient Detection Model of Steel Strip Surface Defects Based on YOLO-V7.
[2]Yan Zhang et. Al. Design of Steel Surface Defect Detection System Based on deep Learning.
[3]Lih-Ping Huang et. Al. Comparison of Different Types of Lenses for Defect Detection of Inner Thread Based on Deep Learning.
[4]Lingyun Zhu et. Al. An Improved YOLOv5-based Method for Surface Defect Detection of Steel Plate.
[5]Shibo Liu et. al. An Adaptive Shunt Model for Steel Defect Detection based on YOLOX
[6]Ricardo Buettner et. Al. A Systematic Literature Review of Medical Image Analysis Using Deep Learning.
[7]Haohan Wang et. Al. Few-Shot Steel Surface Defect Detection
[8]Qianqian Jiao et. Al. Surface Defect Detection of Steel Based on Improved
[9]Ge Jin et. Al. Research on Steel Surface Defect Algorithm Based on Deep Residual Network.
[10]Xin Zhang et. al. Reinforcement Learning Based Neural Architecture Search for Flaw Detection in Intelligent Ultrasonic Imaging NDE System.
[11]Lakshmi Hanne et. Al. Perception of Flaws in Steel using ResNet50 Algorithm.
[12]Hepzibah Elizabeth David et. Al. Literature Review of Disease Detection in Tomato Leaf using Deep Learning Techniques.
[13]TANG YU et. Al Intelligent Detection Method of Forgings Defects Detection Based on Improved Efficient Net and Memetic Algorithm
[14]Wu YiNan et. al., YOLOv5 detection algorithm of Steel defects based on introducing light convolution network and DIOU function.
[15]Graves, A.-R. Mohamed, and G. Hinton. (2013) Speech recognition with deep recurrent neural networks. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pages 6645–6649.
[16]S. Hochreiter and J. Schmidhuber. (1997) Long short-term memory. Neural computation, 9(8):1735–1780.
[17]P. Le and W. Zuidema. (2015) Compositional distributional semantics with long short-term memory. arXiv preprint arXiv:1503.02510.
[18]M. Sundermeyer, R. Schluter, and H. Ney. (2012) LSTM neural net- ¨ works for language modeling. In INTERSPEECH.
[19]Sutskever, O. Vinyals, and Q. V. Le. (2014) Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems, 3104–3112.
[20]R. Pascanu, T. Mikolov, and Y. Bengio. (2012). On the difficulty of training recurrent neural networks. arXiv preprint arXiv:1211.5063.
[21]Q. Xie, W. Zhou, H. Tan and X. Wang, (2022), Surface Defect Recognition in Steel Plates Based on Impoved Faster R-CNN, 2022 41st Chinese Control Conference (CCC), Hefei, China, pp. 6759-6764.
[22]X. Li, Y. Zhu, Y. Yi, Y. Ding and K. Zhu, (2021) Application of vision technology in metal surface defect detection," 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Chongqing, China, pp. 50-54.
[23]Z. Huang, H. Xiao, R. Zhang, H. Wang, C. Zhang and X. Shi, (2019). Multi-Scale Feature Pair Based R-CNN Method for Defect Detection," 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA, 2019, pp. 46-51.
[24]W. Abbes, J. F. Elleuch and D. Sellami, (2024) Defect-Net: a new CNN model for steel surface defect classification, 2024 IEEE 12th International Symposium on Signal, Image, Video and Communications (ISIVC), Marrakech, Morocco, pp. 1-5.
[25]Y. Liu, Y. Liu and L. Sun, (2009) Heat Affected Zone in the MEMS Wire Bonding, 2009 International Conference on Measuring Technology and Mechatronics Automation, Zhangjiajie, China, pp. 825-828.
[26]J. Tao, Y. Zhu, F. Jiang, H. Liu and H. Liu, Rolling Surface Defect Inspection for Drum-Shaped Rollers Based on Deep Learning, in IEEE Sensors Journal, 22(9);8693-8700.
[27]Y. Zhou and S. F. Stiemer, (2008) Evaluation of metal fatigue problems using qualitative reasoning approach, in Tsinghua Science and Technology, 13(S1); 96-101.
[28]X. Zhang, H. Chen, X. Ye and Z. Zhang, (2023) An Improved YOLOv5 Metal Surface Defect Detection Model, 2023 7th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE), Xi'an, China, pp. 1-4
[29]Z. Li, Y. Zhang, X. Fu and C. Wang, (2023) Metal surface defect detection based on improved YOLOv5, 2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS), Chengdu, China, 2023, pp. 1147-1150.
[30]X. Su, F. Zhang, Y. Zhang, H. Xu and X. Chen, (2023). Metal Surface Defect Detection Algorithm Based on Improved YOLOv5, 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2023, pp. 2133-2137.
[31]C. Li, J. Cai, S. Qiu and H. Liang, (2021). Defects detection of steel based on YOLOv4, 2021 China Automation Congress (CAC), Beijing, China, 2021, pp. 5836-5839.
[32]X. Xikun, L. Changjiang and X. Meng, (2021). Application of attention YOLOV 4 algorithm in metal defect detection, 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT), Chongqing, China, 2021, pp. 465-468.
[33]Y. Wang, H. Wang and Z. Xin, (2022). Efficient Detection Model of Steel Strip Surface Defects Based on YOLO-V7, in IEEE Access, 10;133936-133944.
[34]Li, Q., Huang, Q., Zhou, Y., Yang, T., Ran, M., & Liu, X. (2021). Combined convolutional and LSTM recurrent neural networks for internal defect detection of arc magnets under strong noises and variable object types. IEEE Access, 9, 71446-71460.
[35]Zhang, Yahui & Zhou, Taotao & Huang, Xufeng & Longchao, Cao & Zhou, Qi. (2020). Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement. 171. 10.1016/j.measurement.2020.108774.
[36]Kim, S. W., Kong, J. H., Lee, S. W., & Lee, S. (2022). Recent advances of artificial intelligence in manufacturing industrial sectors: A review. International Journal of Precision Engineering and Manufacturing, 1-19.
[37]Pan, Yue & Zhang, Limao. (2021). Dual attention deep learning network for automatic steel surface defect segmentation. Computer-Aided Civil and Infrastructure Engineering. 37. 10.1111/mice.12792.
[38]X. Zhou, M. Chen, W. Shang, H. Shen and H. Xu, (2023),Real time Monitoring Method of Welding Defects Based on LSTM Sequence Model, 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Chongqing, China, pp. 1203-1207, doi: 10.1109/ICIBA56860.2023.10165203.
[39]Nian-Zhong Chen, Zhimin Zhao, Lin Lin, (2024) A hybrid deep learning method for AE source localization for heterostructure of wind turbine blades, Marine Structures, 94;103562, https://doi.org/10.1016/j.marstruc.2023.103562.
[40]Patel, Xu K, Xu J. (2019) Periodic Surface Defect Detection in Steel Plates Based on Deep Learning. Applied Sciences. 9(15):3127. https://doi.org/10.3390/app9153127.
[41]Ren, Zhonghe & Fang, Fengzhou & Yan, Ning & Wu, You. (2022). State of the Art in Defect Detection Based on Machine Vision. International Journal of Precision Engineering and Manufacturing-Green Technology. 9;661–691. 10.1007/s40684-021- 00343-6.
[42]Zixiang Yue, Youliang Ding, Hanwei Zhao, Zhiwen Wang, (2022). Mechanics-Guided optimization of an LSTM network for Real- Time modeling of Temperature-Induced deflection of a Cable-Stayed bridge, Engineering Structures, 252;113619, https://doi.org/10.1016/j.engstruct.2021.113619.
[43]Alaa Aldein M.S. Ibrahim, Jules R. Tapamo, (2024). Transfer learning-based approach using new convolutional neural network classifier for steel surface defects classification, Scientific African, 23;e02066, https://doi.org/10.1016/j.sciaf.2024.e02066.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
