基于BP神经网络预测热处理后35CrMoA钢的低温冲击性能

doi:10.13251/j.issn.0254-6051.2025.03.020

金属热处理 ›› 2025, Vol. 50 ›› Issue (3): 125-131.DOI: 10.13251/j.issn.0254-6051.2025.03.020

基于BP神经网络预测热处理后35CrMoA钢的低温冲击性能

金帅¹, 王会强¹, 崔建英², 王艳山³, 闫学兰⁴, 李文翔⁵

1.河北农业大学机电工程学院, 河北保定 071001;
2.巨力索具股份有限公司, 河北保定 072550;
3.保定市东利机械制造股份有限公司, 河北保定 071100;
4.保定金阳光能源装备科技有限公司, 河北保定 071000;
5.馆陶县飞翔机械装备制造有限公司, 河北邯郸 057750

收稿日期:2024-10-27 修回日期:2025-01-12 出版日期:2025-03-25 发布日期:2025-05-14
通讯作者: 王会强,教授,博士,E-mail:317395437@qq.com
作者简介:金帅(1998—),男,硕士研究生,主要研究方向为金属材料热处理,E-mail:2074265277@qq.com。
基金资助:
河北省科技计划(20312201D);河北省重大成果转化项目(21287001Z)

Prediction of low-temperature impact property of 35CrMoA steel after heat treatment based on BP neural network

Jin Shuai¹, Wang Huiqiang¹, Cui Jianying², Wang Yanshan³, Yan Xuelan⁴, Li Wenxiang⁵

1. College of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding Hebei 071001, China;
2. Juli Sling Co., Ltd., Baoding Hebei 072550, China;
3. Baoding Dongli Machinery Co., Ltd., Baoding Hebei 071100, China;
4. Baoding Golden Sunshine Energy Equipment Technology Co., Ltd., Baoding Hebei 071000, China;
5. Guantao Flying Machinery Equipment Manufacturing Co., Ltd., Handan Hebei 057750, China

Received:2024-10-27 Revised:2025-01-12 Online:2025-03-25 Published:2025-05-14

摘要/Abstract

摘要： 为了预测正火态35CrMoA钢试棒进行亚温淬火和高温回火后在-45 ℃的低温冲击性能,采用不同热处理温度下-45 ℃低温冲击性能实际状态参量作为学习样本,对3层BP人工神经网络(BPANN)进行训练和预测低温冲击性能。结果表明:BPANN能够对正火态35CrMoA钢试样在不同亚温淬火温度、回火温度下的-45 ℃低温冲击性能进行预测,误差范围区间为5%~9%;BPANN的预测值比实际值低,可通过增加训练样本提升预测精确度,预测数据变化趋势与实测变化趋势相同,能够实现具有参考意义的预测。本研究可通过预测减少实际生产中试验次数,节约试验成本,有助于35CrMoA钢在其他亚温淬火温度下的低温冲击性能预测的研究。

关键词: 35CrMoA钢, BP神经网络, 热稳定性, 亚温淬火, 预测

Abstract: In order to predict the low-temperature impact performance at -45 ℃ of normalized 35CrMoA steel test bars after subcritical quenching and high-temperature tempering, the actual state parameters of low-temperature impact property at -45 ℃ under different heat treatment temperatures were used as learning specimens to train and predict the low-temperature impact property using a three-layer back propagation artificial neural network (BPANN). The results show that the BPANN can predict the low-temperature impact property at -45 ℃ of the 35CrMoA steel specimens subcritical quenched at different temperatures and tempered at different temperatures, with an error range of 5% to 9%. The predicted values of the BPANN are lower than the actual values, and the prediction accuracy can be improved by increasing the training specimens. The trend of the predicted data is the same as that of the measured data, and it can achieve a meaningful prediction. This study can reduce the number of tests in actual production through prediction, save test costs, and is helpful for the research on the low-temperature impact property prediction of the 35CrMoA steel at other subcritical quenching temperatures.

Key words: 35CrMoA steel, BP neural network, thermal stability, subcritical quenching, prediction

中图分类号:

TG156

金帅, 王会强, 崔建英, 王艳山, 闫学兰, 李文翔. 基于BP神经网络预测热处理后35CrMoA钢的低温冲击性能[J]. 金属热处理, 2025, 50(3): 125-131.

Jin Shuai, Wang Huiqiang, Cui Jianying, Wang Yanshan, Yan Xuelan, Li Wenxiang. Prediction of low-temperature impact property of 35CrMoA steel after heat treatment based on BP neural network[J]. Heat Treatment of Metals, 2025, 50(3): 125-131.

参考文献

[1] 郎雪琴, 代琨. 亚温淬火回火的30CrMoA钢的显微组织和力学性能[J]. 热处理, 2023, 38(4): 44-45.
Lang Xueqin, Dai Kun. Microstructure and mechanical properties of 30CrMoA steel after sub-critical quenching and tempering[J]. Heat Treatment, 2023, 38(4): 44-45.
[2] 刘勇, 高文娟. 35CrMoA钢力学性能不合格原因分析[J]. 山东冶金, 2018, 40(1): 24-26.
Liu Yong, Gao Wenjuan. Cause analysis of failure of mechanical properties of 35CrMoA steel[J]. Shandong Metallurgy, 2018, 40(1): 24-26.
[3] 李丰德. 35CrMoA圆钢热顶锻开裂原因分析[J]. 物理测试, 2023, 41(3): 28-32.
Li Fengde. Cause analysis on upset forging cracking of 35CrMoA round steel[J]. Physics Examination and Testing, 2023, 41(3): 28-32.
[4] 黄玲, 向勇, 曾麟芳, 等. 不锈钢覆层抽油杆研发及其应用前景[J]. 金属材料与冶金工程, 2023, 51(3): 18-21.
Huang Ling, Xiang Yong, Zeng Linfang, et al. Development and application prospect of stainless steel clad sucker rod[J]. Metal Materials and Metallurgy Engineering, 2023, 51(3): 18-21.
[5] 倪彤元, 杜鑫, 莫云波, 等. 基于ANN的HVFAC拉伸性能预测评价[J]. 材料导报, 2024, 38(10): 79-87.
Ni Tongyuan, Du Xin, Mo Yunbo, et al. Prediction and evaluation of HVFAC tensile properties based on ANN[J]. Materials Reports, 2024, 38(10): 79-87.
[6] Huang Wenwen, Lu Miaomiao, Zeng Yuxuan, et al. Technical and tactical diagnosis model of table tennis matches based on BP neural network[J]. BMC Sports Science, Medicine Rehabilitation, 2021, 13(1): 54-54.
[7] 叶梯, 冯灏, 李果. 基于BP神经网络的复合材料螺栓连接强度预测[J]. 复合材料科学与工程, 2025(1): 29-34, 41.
Ye Ti, Feng Hao, Li Guo. Strength prediction of composite material bolted joints based on BP neural networks[J]. Composites Science and Engineering, 2025(1): 29-34, 41.
[8] 娄淑梅, 李一明, 李鑫, 等. 基于BP神经网络和Arrhenius本构模型的石墨烯/7075复合材料热变形行为[J]. 吉林大学学报(工学版), 2024, 54(5): 1237-1245.
Lou Shumei, Li Yiming, Li Xin, et al. Thermal deformation behavior of graphene nanosheets reinforced 7075Al based on BP neural network and Arrhenius constitutive equation[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1237-1245.
[9] 董文文, 尹延国, 张国涛, 等. 基于BP神经网络的粉末冶金铜基滑动轴承材料磨损量预测[J]. 轴承, 2021(2): 52-56.
Dong Wenwen, Yin Yanguo, Zhang Guotao, et al. Wear volume prediction of powder metallurgy copper-based sliding bearing material based on BP neural network[J]. Bearing, 2021(2): 52-56.
[10] 温然, 金志雄. 基于BP神经网络的齿轮材料热处理工艺优化[J]. 热加工工艺, 2018, 47(8): 175-178.
Wen Ran, Jin Zhixiong. Optimization of heat treatment process for gear materials based on BP neural network[J]. Hot Working Technology, 2018, 47(8): 175-178.
[11] 闫楚良, 郝云霄, 刘克格. 基于遗传算法优化的BP神经网络的材料疲劳寿命预测[J]. 吉林大学学报(工学版), 2014, 44(6): 1710-1715.
Yan Chuliang, Hao Yunxiao, Liu Kege. Fatigue life prediction of materials based on BP neural networks optimized by genetic algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(6): 1710-1715.
[12] 周惦武, 乔小杰, 张丽娟, 等. 镀锌钢/6016铝合金激光焊的BP神经网络工艺优化及组织和性能[J]. 中国有色金属学报, 2014, 24(3): 678-688.
Zhou Dianwu, Qiao Xiaojie, Zhang Lijuan, et al. Parameters optimization of laser welding process of galvanized steel and 6016 aluminum alloy based on BP neural network and its microstructure and mechanical properties[J]. The Chinese Journal of Nonferrous Metals, 2014, 24(3): 678-688.
[13] Teng Haihao, Xia Yufeng, Sun Tao, et al. Flow stress prediction of near-β Ti-55511 alloy during isothermal compression based on corrected Arrhenius model with material parameter evolution and BP-ANN model[J]. Rare Metal Materials and Engineering, 2023, 52(3): 823-833.
[14] 张乃千, 魏明霞, 赵君, 等. GA-BP神经网络在AgCuNi电接触材料的性能预测研究[J]. 贵金属, 2022, 43(S1): 15-21.
Zhang Naiqian, Wei Mingxia, Zhao Jun, et al. Optimal design of AgCuNi series electrical contact materials based on GA-BP neural network[J]. Precious Metals, 2022, 43(S1): 15-21.
[15] 霍冠良, 宁志华. 基于BP神经网络的含褶皱复合材料强度预测[J]. 南京航空航天大学学报, 2020, 52(3): 460-467.
Huo Guanliang, Ning Zhihua. Strength prediction of laminates containing embedded fiber wrinkles using bp neural networks[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2020, 52(3): 460-467.
[16] 王晶, 李维雅, 赵春旺. 时效处理对Ni-Ti-La合金微结构、相变及力学性能的影响[J]. 内蒙古工业大学学报(自然科学版), 2024, 43(1): 18-22.
Wang Jing, Li Weiya, Zhao Chunwang. Effect of aging treatment on microstructure, phase transformation and mechanical properties of Ni-Ti-La alloy[J]. Journal of Inner Mongolia University of Technology(Natural Science Edition), 2024, 43(1): 18-22.
[17] 李超群, 赵千水, 张凯伦. 应用JMatPro软件对重载齿轮用钢17CrNiMo6的分析[J]. 金属世界, 2024(3): 25-28.
Li Chaoqun, Zhao Qianshui, Zhang Kailun. Analysis of 17CrNiMo6 steel for overloaded gear using JMatPro software[J]. Metal World, 2024(3): 25-28.
[18] 凌文丹, 袁庆龙, 王海瑞. 35CrMoA钢亚温淬火强韧性研究[J]. 材料导报, 2010, 24(S2): 552-555.
Ling Wendan, Yuan Qinglong, Wang Hairui. Study on the strength and toughness of 35CrMoA steel by intercritical hardening[J]. Materials Reports, 2010, 24(S2): 552-555.
[19] 李旭辉. 亚温淬火对U20MnV钢轨钢力学性能影响及相关数值模拟研究[D]. 北京: 北京交通大学, 2023.
Li Xuhui. Effect of intercritical quenching on mechanical properties of U20MnV rail steel and related numerical simulation research[D]. Beijing: Beijing Jiaotong University, 2023.
[20] 朱必武, 蒋昊, 刘筱, 等. 基于改进PSO-BP神经网络预测中高应变速率轧制AZ31镁合金板的抗拉强度[J/OL]. 中国有色金属学报, 2024. DOI:10.11817/j.ysxb.1004.0609.2023-44555.
Zhu Biwu, Jiang Hao, Liu Xiao, et al. Prediction of the tensile strength of AZ31 magnesium alloy sheet rolled at medium-high strain rate based on improved PSO-BP neural network[J]. The Chinese Journal of Nonferrous Metals, 2024. DOI:10.11817/j.ysxb.1004.0609.2023-44555.
[21] 姬帅, 张佳乐, 王海丽. BP神经网络预测冲击强化45钢的中温热稳定性[J]. 热加工工艺, 2024, 53(23): 159-164.
Ji Shuai, Zhang Jiale, Wang Haili. Prediction of medium thermal stability of 45 steel after impact strengthening with BP artificial neural network[J]. Hot Working Technology, 2024, 53(23): 159-164.
[22] 杨强, 颜宗辉, 杜秀举, 等. 基于ANN架构的新能源发电预测模型的研究[J]. 电气应用, 2024, 43(2): 76-82.
Yang Qiang, Yan Zonghui, Du Xiuju, et al. Research on the prediction model of new energy power generation based on ANN architecture[J]. Electrotechnical Application, 2024, 43(2): 76-82.
[23] Liao Hengcheng, Gao Yuan, Wang Qigui, et al. Development of viscosity model for aluminum alloys using BP neural network[J]. Transactions of Nonferrous Metals Society of China, 2021, 31(10): 2978-2985.
[24] 范勇, 裴勇, 杨广栋, 等. 基于改进PSO-BP神经网络的爆破振动速度峰值预测[J]. 振动与冲击, 2022, 41(16): 194-203, 302.
Fan Yong, Pei Yong, Yang Guangdong, et al. Prediction of blasting vibration velocity peak based on an improved PSO-BP neural network[J]. Journal of Vibration and Shock, 2022, 41(16): 194-203, 302.
[25] 陈国强, 申正义, 孙利, 等. 基于BP神经网络优化遗传算法的智能座舱感性意象预测[J]. 汽车工程, 2023, 45(8): 1479-1488.
Chen Guoqiang, Shen Zhengyi, Sun Li, et al. Intelligent cockpit perceptual image prediction based on BP neural network optimization genetic algorithm[J]. Automotive Engineering, 2023, 45(8): 1479-1488.
[26] 胡昂, 吴润, 李忠波, 等. 亚温淬火对低合金耐磨钢增韧及性能的影响[J]. 金属热处理, 2024, 49(3): 22-27.
Hu Ang, Wu Run, Li Zhongbo, et al. Effect of intercritical quenching on toughening and properties of low alloy wear-resistant steel[J]. Heat Treatment of Metals, 2024, 49(3): 22-27.

基于BP神经网络预测热处理后35CrMoA钢的低温冲击性能

Prediction of low-temperature impact property of 35CrMoA steel after heat treatment based on BP neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	何潇, 许鸿翔, 师陆冰, 赵少甫, 戎泽玉, 关鹤, 陈治. 淬火工艺对渗碳18Cr2Ni4WA钢采煤机行走轮冲击性能的影响[J]. 金属热处理, 2025, 50(3): 69-73.
[2]	石磊, 田鹏勇, 温国强, 魏明江, 赵宇. 淬火工艺对铁素体/马氏体双相钢组织与性能的影响[J]. 金属热处理, 2025, 50(3): 138-142.
[3]	张英凡, 陈慧琴, 党淑娥, 陈娟, 徐全, 房晓天, 石腾龙, 代云云. 基于机器学习与遗传算法的Cu-Ni-Co-Si合金性能预测及机理[J]. 金属热处理, 2025, 50(1): 255-265.
[4]	蒙品品, 张晓波. 退火处理对纯铜微观组织及力学性能的影响[J]. 金属热处理, 2024, 49(7): 267-273.
[5]	胡昂, 吴润, 李忠波, 吴腾. 亚温淬火对低合金耐磨钢增韧及性能的影响[J]. 金属热处理, 2024, 49(3): 22-27.
[6]	刘艾, 张廷虎, 王忠亮. 基于CNN-LSTM的二阶段辊式淬火过程板形预测方法[J]. 金属热处理, 2024, 49(10): 295-300.
[7]	任芝兰, 唐明华, 毕红霞, 吴远志, 周勇. 37Mn5钢厚壁石油套管表面裂纹成因分析与控制[J]. 金属热处理, 2023, 48(7): 277-282.
[8]	李海涛, 于娟, 刘洪涛, 谢睿勋, 冯朝辉, 赵唯一. 新型高强韧铝锂合金的显微组织和性能[J]. 金属热处理, 2023, 48(4): 173-177.
[9]	卢茂勇, 徐乐, 李浩, 梁恩溥, 李若浩, 吴润. Ti微合金化对25Cr3Mo3NiNbZr钢碳化物析出行为和高温强度的影响[J]. 金属热处理, 2023, 48(11): 29-37.
[10]	王凯, 王荣吉, 周童, 彭松. Fe-Mn-C-Al系TWIP钢热处理工艺参数优化[J]. 金属热处理, 2022, 47(9): 31-35.
[11]	王军, 何博, 雷益宇, 贾文静, 兰亮, 高双. 增材制造钛合金激光喷丸组织及热稳定性研究进展[J]. 金属热处理, 2022, 47(8): 242-248.
[12]	李荣斌, 张霞, 蒋春霞. VNbMoTaWCo高熵合金氮化物扩散阻挡层的制备及其热稳定性[J]. 金属热处理, 2022, 47(6): 196-201.
[13]	蔡显杰, 吴博雅, 左鹏鹏, 黎军顽, 郭伟. 压铸模镶块的热疲劳失效行为[J]. 金属热处理, 2022, 47(2): 250-256.
[14]	沈俞涛, 左鹏鹏, 吴晓春. Mo对4Cr5Mo2V型热作模具钢热稳定性能的影响[J]. 金属热处理, 2022, 47(12): 168-174.
[15]	武斌, 伍金荣, 柴慧, 李永坤. 亚温淬火对NiCrMo-3堆焊层耐磨性能的影响[J]. 金属热处理, 2022, 47(1): 276-280.