ABSTRACT
To improve automation, increase efficiency, and maintain high quality in the production of steel, applying modern machine learning techniques to help detect steel defects has been the research focus in the steel industry, since an unprecedented revolution in image semantic segmentation has been witnessed in the past few years. In the traditional production process of steel materials, localizing and classifying surface defects manually on a steel sheet is inefficient and error-prone. Therefore, it's a key challenge to achieve automated detection of steel surface defects in image pixel level, leaving an urgent and critical issue to be addressed. In this paper, to accomplish this crucial task, we apply a series of machine learning algorithms of real-time semantic segmentation, utilizing neural networks with encoder-decoder architectures based on Unet and feature pyramid network (FPN). The image dataset of steel defects is provided by Severstal, the largest steel company in Russia, through a featured code competition in the Kaggle community. The results show that the ensemble algorithm of several neural networks with encoder-decoder architectures has a decent performance regarding both time cost and segmentation accuracy. Our machine learning algorithms achieve dice coefficients over 0.915 and 0.905 at a speed of over 1.5 images per second on the public test set and private test set on the Kaggle platform, respectively, which locates at the top 2% among all teams in the competition.
- Halawani, S. M. 2014. A study of decision tree ensembles and feature selection for steel plates faults detection. International Journal of Technical Research and Applications, Volume 2, Issue 4 (July-Aug 2014), PP 127--131.Google Scholar
- Song, K., and Yan, Y. 2013. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Applied Surface Science, vol. 285, pp. 858--864, Nov. 2013.Google ScholarCross Ref
- Public available at the UCI machine learning homepage: https://archive.ics.uci.edu/ml/index.phpGoogle Scholar
- Srivastava, A. K. 2019. Comparison analysis of machine learning algorithms for steel plate fault detection. International Research Journal of Engineering and Technology (IRJET). Volume: 06 Issue: 05 (May 2019).Google Scholar
- Public available at the Kaggle platform: https://www.kaggle.com/c/severstal-steel-defect-detection/Google Scholar
- Ronneberger, O., Fischer, P., and Brox, T. 2015. U-net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597v1 [cs.CV] 18 May 2015.Google Scholar
- Kollem, S., Reddy, K.R.L., and Rao, D.S. 2019. A Review of Image Denoising and Segmentation Methods Based on Medical Images. International Journal of Machine Learning and Computing, Vol. 9, No. 3, (June 2019).Google ScholarCross Ref
- Sathya, P., and Malathi, L. 2011. Classification and Segmentation in Satellite Imagery Using Back Propagation Algorithm of ANN and K-Means Algorithm. International Journal of Machine Learning and Computing, Vol. 1, No. 4 (October 2011).Google Scholar
- Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. 2017. Feature pyramid networks for object detection. arXiv:1612.03144v2 [cs.CV] 19 Apr 2017.Google Scholar
- Kirillov, A., Girshick, R., He, K., and Dollár, P. 2019. Panoptic Feature Pyramid Networks. arXiv:1901.02446v2 [cs.CV] 10 Apr 2019.Google Scholar
- He, K., Zhang, X., Ren, S., and Sun, J. 2016. Deep residual learning for image recognition. In CVPR, 2016. 2, 6.Google Scholar
- Hu, J., Shen, L., and Sun, G. 2018. Squeeze-and-excitation networks. In CVPR, 2018. 2, 6, 7.Google Scholar
- Xie,S., Girshick, R., Dollr, P., Tu, Z., and He, K. 2017. Aggregated residual transformations for deep neural networks. In CVPR, 2017. 2, 6, 7.Google Scholar
- Tan, M. and Le, Q. V. 2019. EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946v2 [cs.LG] 10 Jun 2019Google Scholar
- Huang, Y., Cheng, Y., Bapna, A., Firat, O., Chen, M., Chen, D., Lee, H., Ngiam, J., Le, Q. V., Wu, Y., and Chen, Z. 2018. GPipe: Efficient training of giant neural networks using pipeline parallelism. arXiv:1811.06965v5 [cs.CV]Google Scholar
- Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q. V. 2018. LeMnasNet: Platform-Aware Neural Architecture Search for Mobile. arXiv:1807.11626v3 [cs.CV]Google Scholar
- Hinton, G., Vinyals, O., and Dean, J. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531v1 [stat.ML] 9 Mar 2015.Google Scholar
Index Terms
- Automated Detection of Steel Defects via Machine Learning based on Real-Time Semantic Segmentation
Recommendations
A Review and Benchmark on State-of-the-Art Steel Defects Detection
AbstractSteel, a critical material in construction, automobile, and railroad manufacturing industries, often presents defects that can lead to equipment failure, significant safety risks, and costly downtime. This research aims to evaluate the performance ...
Improving numerical methods for the steel yield strain calculation in reinforced concrete members with Machine Learning algorithms
AbstractIn the context of reinforced concrete members subjected to shear, the steel behaviour, assumed as embedded in the concrete, has been modelled through different strategies. One of them, the so-called Refined Compression Field Theory (RCFT), is ...
Graphical abstractDisplay Omitted
Highlights- Accurate calculation of steel yield strain in reinforced concrete is tackled.
- Iterative numerical methods usually present convergence problems.
- Machine Learning algorithms may improve the calculation of steel yield strain.
- ...
Bond Properties of Plain Steel Bar with Machine-made Sand Concrete (MSC)
ICETCE '12: Proceedings of the 2012 Second International Conference on Electric Technology and Civil EngineeringTo meet the requirement of machine-made sand application in concrete structures, it is necessary to understand the bond properties of steel bar with machine-made sand concrete (MSC). Therefore, the experimental studies were carried out on the bond of ...
Comments