Predicting model of gear steel hardenability based on extreme learning machine

doi:10.13251/j.issn.0254-6051.2022.03.042

Abstract

Abstract: Prediction of end-quenching hardness curve and chemical composition of 20Cr gear steel was studied by using extreme learning machine(ELM), and the prediction results were compared with the traditional prediction models. The results show that the ELM not only can predict the hardenability of the gear steel according to the chemical composition with calculation accuracy significantly higher than that of the traditional linear fitting and neural network models,but also can be used to backward predict the chemical composition from the hardenability curve with the element content error within 5%.

Key words: extreme learning machine (ELM), gear steel, hardenability

CLC Number:

TG154.4

Zhao Yiqi, Nie Xiaolong, Zhao Sixin, Gao Jiaqiang, Liu Xinkuan. Predicting model of gear steel hardenability based on extreme learning machine[J]. Heat Treatment of Metals, 2022, 47(3): 227-233.

References

[1]曹燕光. 渗碳齿轮钢淬透性及其热处理变形和疲劳性能研究[D]. 北京: 钢铁研究总院, 2017.
[2]王晓英, 颜慧成, 仇圣桃. 基于微观偏析模型的Mn-Cr系齿轮钢淬透性带宽[J]. 钢铁, 2016, 51(10): 54-61.
Wang Xiaoying, Yan Huicheng, Qiu Shengtao. Hardenability bandwidth of Mn-Cr gear steel based on microsegregation model[J]. Iron and Steel, 2016, 51(10): 54-61.
[3]余柏海. 计算淬透性及机械性能的非线性方程[J]. 钢铁, 1985, 20(3): 40-49.
Yu Baihai. Nonlinear equations for calculating hardenability and mechanical property[J]. Iron and Steel, 1985, 20(3): 40-49.
[4]《机械工程手册》编委会. 机械工程手册(3)[M]. 2版. 北京: 机械工业出版社, 1996.
[5]美国金属学会. 金属手册(1)[M]. 9 版. 北京: 机械工业出版社, 1998.
[6]Huang G, Huang G B, Song S, et al. Trends in extreme learning machines: A review[J]. Neural Networks, 2015, 61: 32-48.
[7]晏梦凡. 改进的多隐藏层极限学习机及其应用[D]. 湘潭: 湘潭大学, 2020.
[8]Gao Xiuhua, Qi Kemin, Deng Tianyong, et al. Application of artificial neural network to predicting hardenability of gear steel[J]. Journal of Iron and Steel Research(International), 2006(6): 71-73.
[9]Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[10]Kasun L, Zhou H, Huang G B, et al. Representational learning with ELMs for big data[J]. Intelligent Systems, IEEE, 2013, 28(6): 31-34.
[11]Tang J, Deng C, Huang G B. Extreme learning machine for multilayer perceptron[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 27(4): 809-821.
[12]余柏海. 钢的计算机设计及冶炼成分微调[J]. 特殊钢, 1997, 18(5): 45-48.
Yu Bohai. Computer designing of steel and precise analysis control during melting[J]. Special Steel, 1997, 18(5): 45-48.

[1]	Dai Jianke, Han Shun, Li Yong, Liu Xianmin, Wang Chunxu, Pang Xuedong, Li Jianxin. Microstructure and properties of C69 gear steel for aviation after high temperature carburizing [J]. Heat Treatment of Metals, 2022, 47(4): 219-225.
[2]	Zhang Ning, Gao Xing, Wang Zhilin, Jiang Bo, Liu Yazheng. Analysis of abnormal microstructure and properties of 18CrNiMo7-6 steel gear [J]. Heat Treatment of Metals, 2022, 47(4): 268-273.
[3]	Hai Xianü, Yang Yang, Huang Taiwei, Fan Wangzhan, Gui Weimin, He Liangliang. Heat treatment properties of 8620H steel with refined graded hardenability [J]. Heat Treatment of Metals, 2022, 47(3): 155-158.
[4]	Hu Fangzhong, Yang Shaopeng, Jin Guozhong, Hu Naiyue, Wang Kaizhong, Yang Zhiqiang, Chen Shijie. Effect of quenching temperature on microstructure evolution and mechanical properties of Nb microalloyed gear steel 18CrNiMo7-6 [J]. Heat Treatment of Metals, 2022, 47(2): 105-111.
[5]	Zang Yan, Wang Jianjun. Simulation of end quenching process and prediction of hardenability of Cr-Ni-Mo gear steel [J]. Heat Treatment of Metals, 2022, 47(2): 257-261.
[6]	Dai Yanzhang, Han Shun, Li Yong, Zhou Min, Wang Chunxu. Effect of tempering temperature on microstructure and properties of a new generation transmission gear steel C61 [J]. Heat Treatment of Metals, 2022, 47(1): 49-55.
[7]	Wang Yujing, Wu Guangliang. Prediction of heat treatment parameters and thermophysical properties of Q1100 high strength steel for construction machinery [J]. Heat Treatment of Metals, 2021, 46(6): 172-176.
[8]	Liang Xiaodong, Ju Zhe, Liu Ji, Wang Chenchong, Wang Xu. Effect of quenching temperature on microstructure and mechanical properties of gear steel C64 [J]. Heat Treatment of Metals, 2021, 46(4): 88-94.
[9]	Cheng Yuan, Hu Fangzhong, Hu Naiyue, Wang Kaizhong, Wang Lianglin, Jin Guozhong, Hao Zhenyu. Failure analysis of driving bevel gear of heavy truck rear axle [J]. Heat Treatment of Metals, 2021, 46(2): 218-222.
[10]	Dong Mingzhen, Ouyang Xuemei, Liu Yangming, Gou Lei, Yuan Wufeng, Yan Yongming. Dynamic recrystallization behavior and processing map of 17Cr2Ni2MoVNb and 20Cr2Ni4A gear steels [J]. Heat Treatment of Metals, 2021, 46(12): 81-86.
[11]	Zhang Wei, Shen Kang, Li Huichao, Wang Maoqiu. Effect of Nb on carburizing depth and hardness of 20CrMo gear steel [J]. Heat Treatment of Metals, 2021, 46(10): 31-33.
[12]	Sun Yiqiang. Effect of Cr content on hardenability of 65Mn steel [J]. Heat Treatment of Metals, 2020, 45(7): 163-166.
[13]	Chen Yuanqing, He Kezhun, Yao Xiang, Wei Xiuxun, Zhang Hang, Chen Shaowen. Hardenability of 7A04 Al alloy super thick plate [J]. Heat Treatment of Metals, 2020, 45(5): 166-171.
[14]	Lü Chaojun, Tang Lina, Ren Wei, Wang Jianbo, Zhang Tiande. Hardenability of D406A steel after vacuum high-pressure gas quenching [J]. HTM, 2020, 45(2): 189-192.
[15]	Wang Huizhen, Zhai Yuewen, Zhou Leyu. Isothermal normalizing process of 18CrNiMo7-6 gear steel directly after warm forging [J]. Heat Treatment of Metals, 2020, 45(11): 78-82.