Research on Classification and Recognition Method of Steel Metallographic Structure Based on Transfer Learning
ZHANG Yongzhi1, XIN Quanzhong2, WANG Yongliang2, KONG Xiangming2, LIU Fang2, YANG Zaisheng2
1 College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China 2 Inner Mongolia Energy Power Investment Group Co., Ltd., Electric Power Engineering and Technology Institute, Hohhot 010090, China
Abstract: Metallographic examination is a common method to analyze the internal micro-structure of steel, in which the image discrimination is manually processed and is consequently prone to result uncertainty due to subjective factors. Recently, convolutional neural networks (CNN) in the deep learning(DL) method is widely used in the field of image classification and recognition for its capability of learning complex features from raw images. CNN modelling requires large training samples to make a good generalization ability while in material science and engineering, data set for specific actual problems are usually too small to make a good modelling and hence put limit to the DL application.In this study, VGG19 model was pre-trained based on ImageNet dataset to classify and recognize images of heat resisting steel for thermal-electric generator,using two transfer learning methods: freezing all convolutional layers' weights and fine-tuning partial convolutional layers' weights, which realized the deep learning modeling of small sample data sets, overcome the problem of small metallographic set, and identify the metallographic inspection images of heat-resistant steel of thermal power generating units, with the accuracy rates of 92.5% and 94.2%, respecfively. The transfer learning CNN model with fine-tuning has fast convergence speed, high training accuracy and generalization ability, which can accurately classify and identify metallographic images. It is a method for intelligently identifying the metallographic structure of steel, and also a new method for automatic classification and identification of steel metallographic organization.
张永志, 辛全忠, 王永亮, 孔祥明, 刘昉, 杨再胜. 基于迁移学习的钢金相组织分类与识别方法的研究[J]. 材料导报, 2021, 35(24): 24152-24157.
ZHANG Yongzhi, XIN Quanzhong, WANG Yongliang, KONG Xiangming, LIU Fang, YANG Zaisheng. Research on Classification and Recognition Method of Steel Metallographic Structure Based on Transfer Learning. Materials Reports, 2021, 35(24): 24152-24157.
1 Bhadeshia H. Honeycombe R. Steels: microstructure and properties. Elesevier-Butterworth-Heinemann Press, Holland, 2017. 2 Tasan C, Diehl M, Yan D, et al. Annual Review of Materials Research, 2015, 45(1),391. 3 Zhu Q, Sellars C, Bhadeshia H. Materials Science and Technology, 2007, 23(7),757. 4 Kesireddy A, Mccaslin S. Application of image processing techniques to the identification of phases in steel metallographic specimens, Springer Press, Switzerland, 2015. 5 Lecun Y, Bengio Y, Hinton G. Nature, 2015, 521(7553), 436. 6 Decost B, Lei B, Francis T, et al. Microscopy and Microanalysis, 2019, 25(1),21. 7 Chowdhury A, Kautz E, Yener B, et al. Computational Materials Science, 2016, 123,176. 8 Decost B L, Holm E A. Computational materials science, 2015, 110,126. 9 Naik D L, Sajid H U, Kiran R. Metals, 2019, 9(5), 546. 10 Kusche C, Reclik T, Freund M, et al. PloS One, 2019, 14(5),1. 11 Dimiduk D M, Holm E A, Niezgoda S R. Integrating Materials and Manufacturing Innovation, 2018, 7(3), 157. 12 Decost B L, Francis T, Holm E A. Acta Materialia, 2017, 133,30. 13 Adachi Y, Taguchi M, Hirokawa S. Tetsu to Hagane-journal of the Iron and Steel Institute of Japan, 2016, 102(12), 722. 14 Dimiduk D M, Holm E A, Niezgoda S R. Integrating Materials and Manu-facturing Innovation, 2018, 7(3), 157. 15 Zhuang F Z, Luo P, He Q, et al. Ruan Jian Xue Bao/Journal of Software, 2015,26(1),26(in Chinese). 庄福振,罗平,何清,等. 软件学报, 2015, 26(1), 26. 16 Deng J, Dong W, Socher R, et al. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, 2009,pp.248. 17 Krizhevsky A, Sutskever I, Hinton G E, et al. In: Proceedings of the 25th International Conference on Neural Information Processing Systems.Nevada, 2012,pp.1097. 18 Simonyan K, Zisserman A. In:3rd International Conference on Learning Representations(ICLR). San Diego, 2015. 19 Tian J L, Deng L G. Information Technology and Network Security, 2020, 39(5),6(in Chinese). 田佳鹭,邓立国. 信息技术与网络安全, 2020, 39(5), 6. 20 Yang G C, Yang J, Li S B, et al. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2018, 46(7),127(in Chinese). 杨观赐, 杨静, 李少波,等. 华中科技大学学报(自然科学版), 2018, 46(7),127. 21 Srivastava R K, Greff K, Schmidhuber J. In:Proceedings of the 28th International Conference on Neural Information Processing Systems.Nevada, 2015,pp. 2377. 22 Liu Y, Lei Y B, Fan J L, et al. Acta Automatica Sinica, DIO:10.16383/j.aas.c190720(in Chinese). 刘颖,雷研博,范九伦,等. 自动化学报,DIO:10.16383/j.aas.c190720. 23 Fu S, Zhong S S, Lin L, et al. Computer Integrated Manufacturing Systems, http,//kns.cnki.net/kcms/detail/11.5946.tp.20200420.1333.004.html(in Chinese) 付松,钟诗胜,林琳,等. 计算机集成制造系统, http,//kns.cnki.net/kcms/detail/11.5946.tp.20200420.1333.004.html 24 Zhao L X, Hou F D, Lv Z C, et al. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(7), 184.(in Chinese). 赵立新,侯发东,吕正超,等. 农业工程学报, 2020, 36(7), 184. 25 Liu D D, Li Y R, Xu B. Machinery Design ＆ Manufacture.2020, 5, 28(in Chinese). 刘冬冬,李友荣,徐增丙. 机械设计与制造, 2020, 5, 28. 26 Hu Fang K. Microstructure recognition of high-strength steel materials based on texture recognition and deep convolutional neural network.Ph.D. Thesis, Huazhong University of Science and Technology, 2019(in Chinese). 胡方康. 基于纹理识别和深度卷积神经网络的高强钢材料显微组织识别.硕士学位论文, 华中科技大学, 2019. 27 Wang H. Computer Knowledge and Technology, 2017, 13(32),203(in Chinese). 王惠. 电脑知识与技术, 2017, 13(32),203. 28 Torrey L, Shavlik J. Handbook of research on machine learning applications and trends, algorithms, methods, and techniques, Information Science Reference Press, US, 2010. 29 Gopalakrishnan K, Khaitan S K, Choudhary A, et al. Construction and Building Materials, 2017,157(30),322. 30 Shin H C, Roth H R, Gao M, et al. Transactions on Medical Imaging, 2016, 35(5),1285. 31 He K, Zhang X, Rer S, et al. In:ICCV'15, Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV).NW Washington, 2015, pp. 1026.
渝公网安备50019002502923号 版权所有：《材料导报》编辑部
2021, Vol. 35 
