Please wait a minute...
材料导报  2022, Vol. 36 Issue (12): 21030032-6    https://doi.org/10.11896/cldb.21030032
  金属与金属基复合材料 |
自组织CNN建模识别耐热钢金相组织研究
张永志1, 李旭英1, 辛全忠2, 孔祥明2, 王永亮2
1 内蒙古农业大学机电工程学院,呼和浩特 010018
2 内蒙古能源发电投资集团有限公司电力工程技术研究院,呼和浩特 010090
Research on Self-organized CNN Modeling to Identify Metallographic Structure of Heat-resistant Steel
ZHANG Yongzhi1, LI Xuying1, XIN Quanzhong2, KONG Xiangming2, WANG Yongliang2
1 College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China
2 Electric Power Engineering and Technology Institute, Inner Mongolia Energy Power Investment Group Co., Ltd., Hohhot 010090, China
下载:  全 文 ( PDF ) ( 7993KB ) 
输出:  BibTeX | EndNote (RIS)      
摘要 耐热钢金相组织结构复杂,传统的图像分析方法特征提取困难,难以对其进行准确的自动识别,而人工识别易受主观因素影响,导致识别精度波动大,结果重复性差。卷积神经网络(Convolutional neural networks,CNN)能够从原始图像中提取复杂的特征,但是CNN建模需要的训练与拓扑超参数选择和优化困难。本工作利用基于超参数组合计算资源分配的Hyperband算法来优化CNN模型的超参数,克服了网格搜索、随机搜索及贝叶斯优化效率低、计算资源消耗量大以及优化不稳定等问题,实现自组织CNN建模。基于Hyperband算法优化得到33层CNN模型,进行训练与仿真,并结合混淆矩阵对模型的识别结果进行评价。结果表明,所建模型对耐热钢金相组织识别的准确率、精确度、灵敏度、特异度的均值分别为94.2%、94.1%、94.2%和98.1%,表明模型具有较高的泛化能力,能够较为准确地识别金相组织,为复杂金相组织的智能识别提供新方法。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张永志
李旭英
辛全忠
孔祥明
王永亮
关键词:  计算材料学  耐热钢  金相组织  深度学习  卷积神经网络  超参数优化  识别    
Abstract: Heat-resistant steel has complex metallographic structure, hence it is difficult to extract features using traditional image processing methods to accurately achieve auto recognition. Manual recognition is susceptible to subjective factors and thus resulting in poor accuracy and repeatability. Convolutional neural networks (CNN) can extract complex features from raw images, only with the problem of difficulty in model training and selection and optimization of topological hyperparameters. In this work, a Hyperband algorithm, which calculates resource allocation based on hyperparameter sets, was used to optimize hyperparameter in CNN model and finally the self-organizing modelling was achieved. Relevant problems were solved such as low efficiency and large consumption in computing resources due to grid searching, random searching and Bayesian optimization as well as optimization instability. Based on above-mentioned Hyperband algorithm optimization, a 33 layers' CNN model was constructed, trained, simulated and its recognition performance evaluated with confusion matrix analysis. Results showed that, in recognition of metallographic structure for heat-resistant steel, an average accuracy of 94.2%, an average precision of 94.1%, an average sensitivity of 94.2 and an average specificity of 98.1% were obtained after using the established model. Our model demonstrated a good generalization ability and could be used to recognize metallagraphic structure accurately. This approach provided a new method in intelligent recognition of complex metallagraphic structures.
Key words:  computational materials science    heat-resistant steel    metallographic structure    deep learning    convolutional neural network    hyperparameter optimization    identification
出版日期:  2022-06-25      发布日期:  2022-06-24
ZTFLH:  TG142.1+5  
基金资助: 国家自然科学基金(52061037);内蒙古农业大学高层次人才引进科研启动项目(NDYB2016-20)
通讯作者:  lixuy2000@imau.edu.cn   
作者简介:  张永志,2014年毕业于内蒙古工业大学,获得工学博士学位。2008—2016年在内蒙古能源发电投资集团有限公司电力工程技术研究院从事火力发电厂金属与焊接检验与理化分析工作,2016年开始在内蒙古农业大学机电工程学院从事人工智能技术在材料科学与工程领域的应用研究。发表学术论文20余篇,其中EI收录7篇。
李旭英,内蒙古农业大学教授、博士研究生导师。2006年6月毕业于内蒙古农业大学农业机械化工程专业,获工学博士学位。主要致力于现代农牧业装备设计与制造、性能测试、仿真技术及人工智能技术在农业装备方面的研究。发表论文40余篇,其中EI收录10篇。
引用本文:    
张永志, 李旭英, 辛全忠, 孔祥明, 王永亮. 自组织CNN建模识别耐热钢金相组织研究[J]. 材料导报, 2022, 36(12): 21030032-6.
ZHANG Yongzhi, LI Xuying, XIN Quanzhong, KONG Xiangming, WANG Yongliang. Research on Self-organized CNN Modeling to Identify Metallographic Structure of Heat-resistant Steel. Materials Reports, 2022, 36(12): 21030032-6.
链接本文:  
http://www.mater-rep.com/CN/10.11896/cldb.21030032  或          http://www.mater-rep.com/CN/Y2022/V36/I12/21030032
1 Sosa J M, Huber D E, Welk B, et al. Integrating Materials & Manufacturing Innovation, 2014, 3(1), 1.
2 Kotas P, Praks P, Valek L, et al. Advances in Electrical & Electronic Engineering, 2012, 10(1), 50.
3 Domínguez R G, Gonzalez S J A, Rosado C J, et al. Metals and Materials International, 2019, 7, 1.
4 Ontman A Y M, Shiflet G J. JOM: the Journal of the Minerals, Metals & Materials Society, 2011, 63(7), 44.
5 Magdeev R G, Tashlinskiy A G. In: 3rd International Conference Information Technology and Nanotechnology. Samara, 2017, pp. 158.
6 Iacoviello F, De S A, Iacoviello D, et al. Metallurgia Italiana, 2007, 99(6), 15.
7 Lecun Y, Bengio Y, Hinton G E. Nature, 2015, 521(7553), 436.
8 Decost B L, Lei B, Francis T, et al. Microsc Microanal, 2019, 25(1), 21.
9 Chowdhury A, Kautz E, Yener B, et al. Computational Materials Science, 2016, 123, 176.
10 Decost B L, Holm E A. Computational Materials Science, 2015, 110, 126.
11 Naik D L, Sajid H U, Kiran R. Metals-Open Access Metallurgy Journal, 2019, 9(5), 546.
12 Kusche C, Reclik T, Freund M, et al. PLos One, 2019, 14(5), 1.
13 Wang L Y, Tong Z N, Liu Y W, et al. In: The 16th China Conference on Stereology and Image Analysis. Haikou, China, 2019, pp. 330 (in Chinese).
王乐耘, 童周诺, 刘言伟,等. 第十六届中国体视学与图像分析学术会议.海口, 2019, pp. 330.
14 Hu F K. Microstructure recognition of high-strength steel materials based on texture recognition and deep convolutional neural network.Master's Thesis, Huazhong University of Science and Technology, China, 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.
15 Dimiduk D M, Holm E A, Niezgoda S R. Integrating Materials and Manufacturing Innovation, 2018, 7(3), 157.
16 Decost B L, Francis T, Holm E A. Acta Materialia, 2017, 133, 30.
17 Adachi Y, Taguchi M, Hirokawa S. Tetsu to Hagane, 2016, 102(12), 722.
18 Srivastava R K, Greff K, Schmidhuber J. In: NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada, 2015, pp. 2377.
19 Ioffe S, Szegedy C. In: ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, 2015, pp. 448.
20 Domhan T, Springenberg J T, Hutter F. In: IJCAI'15: Proceedings of the 24th International Conference on Artificial Intelligence. Buenos Aires, 2015, pp. 3460.
21 Hesterman J Y, Caucci L, Kupinski M A, et al. IEEE Transactions on Nuclear Science, 2010, 57(3), 1077.
22 Solis F J, Wets R J B. Mathematics of Operations Research, 1981, 6(1), 19.
23 Spall J C. Introduction to stochastic search and optimization: estimation, simulation, and control, John Wiley & Sons, Inc Press, US, 2003.
24 Bergstra J, Bengio Y. Journal of Machine Learning Research, 2012, 13, 281.
25 Jones D R, Schonlau M, Welch W J. Journal of Global Optimization, 1998, 13(4), 455.
26 Snoek J, Larochelle H, Adams R P. Advances in Neural Information Processing Systems, 2012, 25, 2960.
27 Snoek J, Rippel O, Swersky K, et al. Statistics, 2015, 57(3), 1861.
28 Springenberg J T, Klein A, Falkner S, et al. In: NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems.Barcelona, Spain, 2016, pp. 4141.
29 Kandasamy K, Schneider J, Poczos B. In: ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, France, 2015, pp. 295.
30 Wang Z Y, Zoghi M, Hutter F, et al. In: IJCAI'13: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Beijing, China, 2013, pp. 1778.
31 Li L S, Jamieson K, Desalvo G, et al. Journal of Machine Learning Research, 2018, 18, 1.
32 Jamieson K, Talwalkar A. In: the 19th International Conference on Artificial Intelligence and Statistics. Guilin, China, 2016, pp. 240.
33 Simonyan K, Zisserman A. arXiv Preprint arXiv, DOI:org/10.48550/arXiv.1409.1556
34 He K M, Zhang X Y, Ren S Q, et al. In: ICCV'15: Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015, pp. 1026.
35 Foody G M. Remote Sensing of Environment, 2002, 80(1), 185.
[1] 刘鹏, 马吉恩, 方攸同, 李刚. 多次补焊对304不锈钢焊接接头性能的影响[J]. 材料导报, 2022, 36(Z1): 21120176-5.
[2] 史天宇, 孔维雄, 陈雨琳, 宁保群, 董治中. 新型高氮马氏体耐热铸钢的热处理及相变解析[J]. 材料导报, 2022, 36(Z1): 20120084-6.
[3] 李翠芹, 裴玉冰, 范华, 郭维华, 王天剑, 吴比, 巩秀芳. 火电机组高中压转子选材的研究进展[J]. 材料导报, 2022, 36(Z1): 22010097-7.
[4] 商怀帅, 邵姝文, 冯海暴, 李永升. NPR钢筋力学性能试验研究[J]. 材料导报, 2022, 36(10): 21010164-7.
[5] 封帆, 王美玲, 李振华, 陆永浩. 超超临界机组用HR3C奥氏体耐热钢研究进展[J]. 材料导报, 2021, 35(9): 9186-9195.
[6] 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.
[7] 涂有旺, 朱丽慧, 柯志刚, 周任远, 宋明. 钒的添加对S30432奥氏体耐热钢影响的研究[J]. 材料导报, 2021, 35(20): 20113-20118.
[8] 黄炜, 葛培, 李萌, 许洪飞. 混杂纤维再生砖骨料混凝土正交试验及卷积神经网络预测分析[J]. 材料导报, 2021, 35(19): 19022-19029.
[9] 张度宝, 李成涛, 方可伟, 罗坤杰, 王力, 武焕春, 薛飞. 回火温度对42CrMo4高强钢力学性能及应力腐蚀敏感性的影响[J]. 材料导报, 2021, 35(16): 16133-16137.
[10] 陈灵芝, 周张健, CarstenSchroer. 铅冷能源系统中液态金属与铁基合金相容性的研究进展[J]. 材料导报, 2020, 34(5): 5096-5101.
[11] 吕鹏, 陈亚楠, 关庆丰, 李姚君, 许亮, 丁佐军. 新型超超临界机组用叶片钢11Cr12Ni3Mo2VN的热变形行为[J]. 材料导报, 2020, 34(4): 4113-4117.
[12] 江旭, 马煜林, 刘越. 回火温度对CB2钢的含硼M23C6相析出及力学性能的影响[J]. 材料导报, 2019, 33(12): 2062-2066.
[13] 张建斌, 刘帆, 薛飞. 热处理工艺对P91耐热钢中δ-铁素体和冲击性能的影响[J]. 《材料导报》期刊社, 2018, 32(8): 1318-1322.
[14] 张文凤, 邹爱成, 刘运强, 叶东, 刘晓刚, 严伟. 新型多尺度碳氮化物强化马氏体耐热钢的稳定性[J]. 材料导报, 2018, 32(20): 3606-3611.
[15] 马玉聪, 樊保民, 郝华, 吕金玉, 杨彪, 冯云皓. 肉桂醛超分子缓蚀剂对冷凝水中铁含量的净化机理[J]. 材料导报, 2018, 32(20): 3660-3666.
[1] Wei ZHOU, Xixi WANG, Yinlong ZHU, Jie DAI, Yanping ZHU, Zongping SHAO. A Complete Review of Cobalt-based Electrocatalysts Applying to Metal-Air Batteries and Intermediate-Low Temperature Solid Oxide Fuel Cells[J]. Materials Reports, 2018, 32(3): 337 -356 .
[2] Dongyong SI, Guangxu HUANG, Chuanxiang ZHANG, Baolin XING, Zehua CHEN, Liwei CHEN, Haoran ZHANG. Preparation and Electrochemical Performance of Humic Acid-based Graphitized Materials[J]. Materials Reports, 2018, 32(3): 368 -372 .
[3] Yunzi LIU,Wei ZHANG,Zhanyong SONG. Technological Advances in Preparation and Posterior Treatment of Metal Nanoparticles-based Conductive Inks[J]. Materials Reports, 2018, 32(3): 391 -397 .
[4] Bingwei LUO,Dabo LIU,Fei LUO,Ye TIAN,Dongsheng CHEN,Haitao ZHOU. Research on the Two Typical Infrared Detection Materials Serving at Low Temperatures: a Review[J]. Materials Reports, 2018, 32(3): 398 -404 .
[5] Yingke WU,Jianzhong MA,Yan BAO. Advances in Interfacial Interaction Within Polymer Matrix Nanocomposites[J]. Materials Reports, 2018, 32(3): 434 -442 .
[6] Zhengrong FU,Xiuchang WANG,Qinglin JIN,Jun TAN. A Review of the Preparation Techniques for Porous Amorphous Alloys and Their Composites[J]. Materials Reports, 2018, 32(3): 473 -482 .
[7] Fangyuan DONG,Shansuo ZHENG,Mingchen SONG,Yixin ZHANG,Jie ZHENG,Qing QIN. Research Progress of High Performance ConcreteⅡ: Durability and Life Prediction Model[J]. Materials Reports, 2018, 32(3): 496 -502 .
[8] Lixiong GAO,Ruqian DING,Yan YAO,Hui RONG,Hailiang WANG,Lei ZHANG. Microbial-induced Corrosion of Concrete: Mechanism, Influencing Factors,Evaluation Indices, and Proventive Techniques[J]. Materials Reports, 2018, 32(3): 503 -509 .
[9] Ningning HE,Chenxi HOU,Xiaoyan SHU,Dengsheng MA,Xirui LU. Application of SHS Technique for the High-level Radioactive Waste Disposal[J]. Materials Reports, 2018, 32(3): 510 -514 .
[10] Haoran CHEN, Yingdong XIA, Yonghua CHEN, Wei HUANG. Low-dimensional Perovskites: a Novel Candidate Light-harvesting Material for Solar Cells that Combines High Efficiency and Stability[J]. Materials Reports, 2018, 32(1): 1 -11 .
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed