Semi Supervised Learning of Metallographic Data Based on Self-organizing Incremental and Graph Convolution Neural Network

Weigang LI; Jingcheng SHEN; Lu XIE; Yuntao ZHAO

doi:10.11999/JEIT201029

Volume 43 Issue 11

Nov. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2021 > 43(11): 3301-3308

Weigang LI, Jingcheng SHEN, Lu XIE, Yuntao ZHAO. Semi Supervised Learning of Metallographic Data Based on Self-organizing Incremental and Graph Convolution Neural Network[J]. Journal of Electronics & Information Technology, 2021, 43(11): 3301-3308. doi: 10.11999/JEIT201029

Citation:

Weigang LI, Jingcheng SHEN, Lu XIE, Yuntao ZHAO. Semi Supervised Learning of Metallographic Data Based on Self-organizing Incremental and Graph Convolution Neural Network[J]. Journal of Electronics & Information Technology, 2021, 43(11): 3301-3308. doi: 10.11999/JEIT201029

Citation:

Weigang LI, Jingcheng SHEN, Lu XIE, Yuntao ZHAO. Semi Supervised Learning of Metallographic Data Based on Self-organizing Incremental and Graph Convolution Neural Network[J]. Journal of Electronics & Information Technology, 2021, 43(11): 3301-3308. doi: 10.11999/JEIT201029

PDF( 2476 KB)

Semi Supervised Learning of Metallographic Data Based on Self-organizing Incremental and Graph Convolution Neural Network

doi: 10.11999/JEIT201029

Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan 430081, China

Funds: The National Natural Science Foundation of China (51774219)

Received Date: 2020-12-07
Rev Recd Date: 2021-03-21

Available Online: 2021-04-09

Publish Date: 2021-11-23

Abstract

Abstract

It needs a large number of training sets with annotation information to classify microstructure images of steel materials by deep learning. To solve the problem of low efficiency of manual image annotation, a new semi-supervised learning method combining self-organizing incremental neural network and graph convolutional neural network is proposed. Firstly, it uses transfer learning to obtain the feature vector set of images. Secondly, it obtains the topology structure by adopting the Weighted Self-Organizing Incremental Neural Network(WSOINN) based on connection weight strategy to learn feature data, and manually annotates a small number of nodes which are selected by the number of victories of node. Then, a Graph Convolution Network (GCN) is built to mine the potential connections of nodes in the graph, dropout is used to improve the generalization ability of the network, and the remaining nodes are automatically annotated to obtain the classification results of the metallograph. Experiment on the metallographic data collected from a state key laboratory, the accuracy of automatic classification under different manual annotation ratio is compared. The results show when the image annotation amount is only 12% of the traditional model, and the classification accuracy of the proposed model can reach up to 91%.
- Self-Organizing Incremental Neural Network(SOINN),
- Graph Convolution Network(GCN),
- Automatic annotation,
- Steel material microstructure

FullText(HTML)

References(19)

References

[1]	ZHAO H, WYNNE B P, and PALMIERE E J. A phase quantification method based on EBSD data for a continuously cooled microalloyed steel[J]. Materials Characterization, 2017, 123: 339–348. doi: 10.1016/j.matchar.2016.11.024
[2]	YANG Youwen, HE Chongxian, E Dianyu, et al. Mg bone implant: Features, developments and perspectives[J]. Materials & Design, 2020, 185: 108259. doi: 10.1016/j.matdes.2019.108259
[3]	TERASAKI H, MIYAHARA Y, HAYASHI K, et al. Digital identification scheme for steel microstructures in low-carbon steel[J]. Materials Characterization, 2017, 129: 305–312. doi: 10.1016/j.matchar.2017.05.021
[4]	PANCHAL J H, KALIDINDI S R, and MCDOWELL D L. Key computational modeling issues in Integrated Computational Materials Engineering[J]. Computer-Aided Design, 2013, 45(1): 4–25. doi: 10.1016/j.cad.2012.06.006
[5]	LU Xiaochong, ZHANG Xu, SHI Mingxing, et al. Dislocation mechanism based size-dependent crystal plasticity modeling and simulation of gradient nano-grained copper[J]. International Journal of Plasticity, 2019, 113: 52–73. doi: 10.1016/j.ijplas.2018.09.007
[6]	WANG Hongda, RIVENSON Y, JIN Yiyin, et al. Deep learning enables cross-modality super-resolution in fluorescence microscopy[J]. Nature Methods, 2019, 16(1): 103–110. doi: 10.1038/s41592-018-0239-0
[7]	DECOST B L, LEI Bo, FRANCIS T, et al. High throughput quantitative metallography for complex microstructures using deep learning: A case study in ultrahigh carbon steel[J]. Microscopy and Microanalysis, 2019, 25(1): 21–29. doi: 10.1017/S1431927618015635
[8]	PAULY J, BRITZ D, and MÜCKLICH F. Advanced microstructure classification using data mining methods[C]. In TMP - 5th International Conference on TermoMechanical Processing, Milan, Italy, 2016: 12–25.
[9]	CHOWDHURY A, KAUTZ E, YENER B, et al. Image driven machine learning methods for microstructure recognition[J]. Computational Materials Science, 2016, 123: 176–187. doi: 10.1016/j.commatsci.2016.05.034
[10]	AZIMI S M, BRITZ D, ENGSTLER M, et al. Advanced steel microstructural classification by deep learning methods[J]. Scientific Reports, 2018, 8(1): 2128. doi: 10.1038/s41598-018-20037-5
[11]	李维刚, 谌竟成, 范丽霞, 等. 基于卷积神经网络的钢铁材料微观组织自动辨识[J]. 钢铁研究学报, 2020, 32(1): 33–43. doi: 10.13228/j.boyuan.issn1001-0963.20190147 LI Weigang, SHEN Jingcheng, FAN Lixia, et al. Automatic identification of microstructure of iron and steel material based on convolutional neural network[J]. Journal of Iron and Steel Research, 2020, 32(1): 33–43. doi: 10.13228/j.boyuan.issn1001-0963.20190147
[12]	LI Bentian and PI Dechang. Network representation learning: A systematic literature review[J]. Neural Computing and Applications, 2020, 32(21): 16647–16679. doi: 10.1007/s00521-020-04908-5
[13]	康世泽, 吉立新, 张建朋. 一种基于图注意力网络的异质信息网络表示学习框架[J]. 电子与信息学报, 2021, 43(4): 915–922. doi: 10.11999/JEIT200034 KANG Shize, JI Lixin, and ZHANG Jianpeng. Heterogeneous information network representation learning framework based on graph attention network[J]. Journal of Electronics &Information Technology, 2021, 43(4): 915–922. doi: 10.11999/JEIT200034
[14]	李世宝, 张益维, 刘建航, 等. 基于知识图谱共同邻居排序采样的推荐模型[J]. 电子与信息学报, 待发表. doi: 10.11999/JEIT200735. LI Shibao, ZHANG Yiwei, LIU Jianhang, et al. Recommendation model based on public neighbor sorting and sampling of knowledge graph[J]. Journal of Electronics & Information Technology, To be published. doi: 10.11999/JEIT200735.
[15]	ORTEGA A, FROSSARD P, KOVAČEVIĆ J, et al. Graph signal processing: Overview, challenges, and applications[J]. Proceedings of the IEEE, 2018, 106(5): 808–828. doi: 10.1109/JPROC.2018.2820126
[16]	HAMILTON W L, YING R, and LESKOVEC J. Inductive representation learning on large graphs[J]. arXiv preprint arXiv: 1706.02216, 2017.
[17]	KIPF T N and WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016.
[18]	CHEN Jie, MA Tengfei, and XIAO Cao. FastGCN: Fast learning with graph convolutional networks via importance sampling[J]. arXiv preprint arXiv: 1801.10247, 2018.
[19]	SHEN Furao and HASEGAWA O. An incremental network for on-line unsupervised classification and topology learning[J]. Neural Networks, 2006, 19(1): 90–106. doi: 10.1016/j.neunet.2005.04.006