基于IWOA-BP的MgNdGdZnZr镁合金疲劳寿命预测方法

doi:10.11896/cldb.25120069

材料导报

2026, Vol. 40

Issue (10): 25120069-7 https://doi.org/10.11896/cldb.25120069

金属与金属基复合材料

基于IWOA-BP的MgNdGdZnZr镁合金疲劳寿命预测方法

魏振伟^1,2,3,4,5,*, 王晓明⁶, 申发明⁶, 张根苗⁷, 杨光山⁶, 蔡增辉⁶, 康洪岩⁶, 刘昌奎^1,2,3,4,5

1 中国航发北京航空材料研究院,北京 100095
2 中航工业失效分析中心,北京 100095
3 航空材料检测与评价北京市重点实验室,北京 100095
4 材料检测与评价航空科技重点实验室,北京 100095
5 中国航空发动机集团材料检测与评价重点实验室,北京 100095
6 中国航发哈尔滨东安发动机有限公司,哈尔滨 150066
7 中国航发湖南动力机械研究所,湖南株洲 412002

Fatigue Life Prediction Method for the MgNdGdZnZr Magnesium Alloy Based on IWOA-BP

WEI Zhenwei^1,2,3,4,5,*, WANG Xiaoming⁶, SHEN Faming⁶, ZHANG Genmiao⁷, YANG Guangshan⁶, CAI Zenghui⁶, KANG Hongyan⁶, LIU Changkui^1,2,3,4,5

1 AECC Beijing Institute of Aeronautical Materials, Beijing 100095, China
2 Failure Analysis Center of Aviation Industry Corporation of China, Beijing 100095, China
3 Beijing Key Laboratory of Aeronautical Materials Testing and Evaluation, Beijing 100095, China
4 Key Laboratory of Aeronautical Science and Technology for Material Testing and Evaluation, Beijing 100095, China
5 Key Laboratory of Material Testing and Evaluation, AECC, Beijing 100095, China
6 AECC Harbin Dongan Engine Co.,Ltd., Harbin 150066, China
7 AECC Hunan Power Machinery Research Institute, Zhuzhou 412002, Hunan, China

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

全文 ( PDF ) ( 6336KB )
输出: BibTeX | EndNote (RIS)

摘要利用升降法和成组法得到不同温度下MgNdGdZnZr镁合金材料的四参数S-N曲线和双对数S-N曲线模型,提出了一种采用改进鲸鱼优化算法(IWOA)优化的反向传播神经网络(IWOA-BP)的疲劳寿命预测模型,对不同温度、不同最大应力下材料的疲劳寿命进行更为精确的预测。结果表明:室温条件下材料的中值疲劳强度为165 MPa,高温条件下材料的中值疲劳强度为66.5 MPa。两种S-N曲线的拟合程度均在0.922～0.961之间。当温度相同时,四参数模型的拟合结果优于双对数参数模型。IWOA-BP模型预测结果的决定系数R²为0.989 92,均方根误差RMSE为0.113 56,平均绝对误差MAE为0.094 846,平均绝对百分比误差MAPE为1.854 4%。与BP神经网络对比,IWOA-BP的R²最大,提高了7.01%;IWOA-BP的RMSE、MAE和MAPE最小,分别降低了42.76%、25.64%和27.82%。

	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
	魏振伟
	王晓明
	申发明
	张根苗
	杨光山
	蔡增辉
	康洪岩
	刘昌奎

关键词: MgNdGdZnZr镁合金 S-N曲线疲劳寿命预测改进鲸鱼优化算法反向传播神经网络

Abstract: The fatigue properties of MgNdGdZnZr magnesium alloy were investigated at different temperatures using both the step-loading method and the group method. Four-parameter and double logarithmic S-N curve models were developed based on the experimental data. An improved whale optimization algorithm (IWOA) optimized backpropagation neural network (IWOA-BP) model was proposed for more accurate fatigue life prediction under varying temperatures and maximum stress levels. The results indicated that the median fatigue strength of the material was 165 MPa at room temperature and 66.5 MPa at elevated temperature. The goodness-of-fit for both S-N curve models ranged between 0.922 and 0.961. At the same temperature, the four-parameter model demonstrated superior fitting performance compared to the double logarithmic para-meter model. The IWOA-BP model achieved a coefficient of determination (R²) of 0.989 92, with a root mean square error (RMSE) of 0.113 56, a mean absolute error (MAE) of 0.094 846, and a mean absolute percentage error (MAPE) of 1.854 4%. Compared with the conventional BP neural network, the IWOA-BP model exhibited the highest R² value, representing an improvement of 7.01%, while achieving the lowest RMSE, MAE, and MAPE, which were reduced by 42.76%, 25.64%, and 27.82%, respectively.

Key words: MgNdGdZnZr magnesium alloy S-N curve fatigue life prediction improved whale optimization algorithm backpropagation neural network

发布日期: 2026-06-03

ZTFLH:

TB31

基金资助: 国家自然科学基金(AA202402025)

通讯作者: *魏振伟,博士,高级工程师,硕士研究生导师。就职于中国航发北京航空材料研究院,主要从事飞行事故调查、失效分析、材料检测与评价研究。2280608064@qq.com

引用本文:

魏振伟, 王晓明, 申发明, 张根苗, 杨光山, 蔡增辉, 康洪岩, 刘昌奎. 基于IWOA-BP的MgNdGdZnZr镁合金疲劳寿命预测方法[J]. 材料导报, 2026, 40(10): 25120069-7.
WEI Zhenwei, WANG Xiaoming, SHEN Faming, ZHANG Genmiao, YANG Guangshan, CAI Zenghui, KANG Hongyan, LIU Changkui. Fatigue Life Prediction Method for the MgNdGdZnZr Magnesium Alloy Based on IWOA-BP. Materials Reports, 2026, 40(10): 25120069-7.

链接本文:

https://www.mater-rep.com/CN/10.11896/cldb.25120069 或 https://www.mater-rep.com/CN/Y2026/V40/I10/25120069

1 Liu Z Y, Hu J Q, Wang S, et al. Rare Metal Materials and Engineering, 2025, 54(5), 1377 (in Chinese).
刘泽宇, 胡佳其, 王帅, 等. 稀有金属材料与工程, 2025, 54(5), 1377.
2 Wang S, Liu Z Y, Ye J L, et al. Rare Metal Materials and Engineering, 2025, 54(6), 1630 (in Chinese).
王帅, 刘泽宇, 叶建林, 等. 稀有金属材料与工程, 2025, 54(6), 1630.
3 Wei Z W, Chen H H, Shen J M, et al. Failure Analysis and Prevention, 2022, 17(5), 328 (in Chinese).
魏振伟, 陈皓晖, 沈佳萌, 等. 失效分析与预防, 2022, 17(5), 328.
4 Guo Y C, Pan H M, Shen A Q, et al. Structures, 2023, 56, 105018.
5 Sung-Ju Park. Engineering Fracture Mechanics, 2023, 289, 109469.
6 Akhavan-Safar A, Jalali S, Da Silva L F M, et al. International Journal of Adhesion and Adhesives, 2023, 126, 103455.
7 Li W, Cheng L Y, Zeng F, et al. Journal of Manufacturing Processes, 2023, 106, 393.
8 Li H, Luo X, Zhang Y Q, et al. Engineering Fracture Mechanics, 2023, 292, 109589.
9 Mohammad A, Khonsari M M. International Journal of Fatigue, 2023, 168, 107411.
10 Zheng S K, Shen J, Wang W, et al. Materials Science and Engineering: A, 2023, 876, 145157.
11 Chen C L, Shang D G, Xiao N M, et al. International Journal of Fatigue, 2024, 184, 108312.
12 Tao Z Q, Wang Z B, Pan X N, et al. International Journal of Fatigue, 2024, 183, 108262.
13 Zhou X, Li K E, Zhao D X, et al. Journal of Alloys and Compounds, 2023, 967, 171753.
14 Gu B, Dang N, Zhang J J, et al. Materials Characterization, 2024, 207, 113541.
15 Mahmood A, Sun C W, Li W, et al. Engineering Failure Analysis, 2024, 162, 108433.
16 Feng R, Chen M H, Xie L S. Engineering Fracture Mechanics, 2024, 295, 109804.
17 Li Y X, Zhan M, Jiang X Q, et al. Journal of Materials Research and Technology, 2023, 23, 954.
18 Zhang X, Yao J Y, Liu X Y, et al. Journal of Aeronautical Materials, 2024, 44(6), 107 (in Chinese).
张旭, 姚建尧, 刘许旸, 等. 航空材料学报, 2024, 44(6), 107.
19 Wei Z W, Wang Z F, Zou A H, et al. Chinese Journal of Rare Metals, 2025, 49(2), 153 (in Chinese).
魏振伟, 王子峰, 邹爱华, 等. 稀有金属, 2025, 49(2), 153.
20 Cheng R X, Duan G S, Zhang Y Y, et al. Acta Aeronautica et Astronautica Sinica, 2025, 46(12), 312 (in Chinese).
程容湘, 段国升, 张月盈, 等. 航空学报, 2025, 46(12), 312.
21 Zhu S Y, Zhang Y, Zhu B C, et al. International Journal of Fatigue, 2024, 182, 108206.
22 Zhao B F, Song J X, Xie L Y, et al. International Journal of Fatigue, 2023, 166, 107274.
23 Dang L W, He X F, Tang D C, et al. International Journal of Fatigue, 2022, 159, 106748.
24 Kashvzadeh K R, Ghorbani S. Engineering Failure Analysis, 2023, 146, 107128.
25 Mirjalili S, Lewis A. Advances in Engineering Software, 2016, 95, 51.
26 Lin J, Zhang S X, Zheng S Y, et al. Journal of Computational Science, 2022, 63, 101746.

[1]	董俊涛, 安宗文, 马强, 白学宗. 改进的北方苍鹰算法优化BP神经网络在风电叶片复合材料疲劳预测中的应用[J]. 材料导报, 2026, 40(7): 25020176-7.
[2]	冷建成, 赵雷, 张新, 许宏伟. 基于磁记忆在线监测的再制造毛坯疲劳寿命预测方法[J]. 材料导报, 2025, 39(2): 23040250-6.
[3]	李莉佳, 刘振晖, 尹晓静, 严文强, 郝兆朋. 轨道车辆零部件材料多轴疲劳寿命预测理论与方法研究进展[J]. 材料导报, 2025, 39(12): 23100024-11.
[4]	梁宁慧, 毛金旺, 游秀菲, 刘新荣, 周侃. 多尺度聚丙烯纤维混凝土弯曲疲劳寿命试验及数值模拟[J]. 材料导报, 2024, 38(4): 22040023-8.
[5]	孙冠泽, 曹睿, 周鑫, 王红卫. TNM-TiAl合金室温高周疲劳性能研究[J]. 材料导报, 2023, 37(12): 21090297-7.
[6]	吴涛, 姚卫星, 黄杰. 纤维增强树脂基复合材料超高周疲劳研究进展[J]. 材料导报, 2022, 36(6): 20050117-9.
[7]	孙昊飞, 肖志, 韦凯, 杨旭静, 齐军. 预弯曲变形对复相钢CP800疲劳性能影响的实验研究及数值仿真计算[J]. 材料导报, 2022, 36(10): 20100259-6.
[8]	沙建芳, 夏中升, 刘建忠, 郭飞, 徐海源. 超高强水泥基灌浆材料疲劳性能研究综述[J]. 材料导报, 2021, 35(11): 11013-11026.
[9]	张明义, 袁帅, 钟敏, 柏劲松. 金属材料和结构的疲劳寿命预测概率模型及应用研究进展[J]. 《材料导报》期刊社, 2018, 32(5): 808-814.
[10]	周磊, 宋亚南, 王海斗, 李国禄, 张建军. 超高周疲劳的影响因素及疲劳机理的研究进展^*[J]. 《材料导报》期刊社, 2017, 31(17): 84-89.

[1]	Yanzhen WANG, Mingming CHEN, Chengyang WANG. Preparation and Electrochemical Properties Characterization of High-rate SiO₂/C Composite Materials[J]. Materials Reports, 2018, 32(3): 357 -361 .
[2]	Yimeng XIA, Shuai WU, Feng TAN, Wei LI, Qingmao WEI, Chungang MIN, Xikun YANG. Effect of Anionic Groups of Cobalt Salt on the Electrocatalytic Activity of Co-N-C Catalysts[J]. Materials Reports, 2018, 32(3): 362 -367 .
[3]	Lijing YANG,Zhengxian LI,Chunliang HUANG,Pei WANG,Jianhua YAO. Producing Hard Material Coatings by Laser-assisted Cold Spray:a Technological Review[J]. Materials Reports, 2018, 32(3): 412 -417 .
[4]	Zhiqiang QIAN,Zhijian WU,Shidong WANG,Huifang ZHANG,Haining LIU,Xiushen YE,Quan LI. Research Progress in Preparation of Superhydrophobic Coatings on Magnesium Alloys and Its Application[J]. Materials Reports, 2018, 32(1): 102 -109 .
[5]	Laima LUO, Mengyao XU, Xiang ZAN, Xiaoyong ZHU, Ping LI, Jigui CHENG, Yucheng WU. Progress in Irradiation Damage of Tungsten and Tungsten AlloysUnder Different Irradiation Particles[J]. Materials Reports, 2018, 32(1): 41 -46 .
[6]	Hong ZHANG,Ping ZHOU,Lan SUN,Hongyuan FAN. Effect of Solution Temperature on Microstructure and Properties of TP347HFG Heat Resistant Steel[J]. Materials Reports, 2018, 32(2): 234 -237 .
[7]	Huimin PAN,Jun FU,Qingxin ZHAO. Sulfate Attack Resistance of Concrete Subjected to Disturbance in Hardening Stage[J]. Materials Reports, 2018, 32(2): 282 -287 .
[8]	Acidifier at High Temperature SiO2Bearing, , , , . Research on Stabilization of Free CaO in Basic Oxygen Furnace Slag with[J]. Materials Reports, 2018, 32(2): 301 -306 .
[9]	Guang MA,Xin CHEN,Licheng LU,Dongqun XIN,Li MENG,Hao WANG,Ling CHENG,Fuyao YANG. Monte Carlo Simulation of the Evolution of Goss Texture in Secondary Recrystallization of Thin Gauge Grain Oriented Silicon Steel[J]. Materials Reports, 2018, 32(2): 313 -315 .
[10]	YAN Erhu, HUANG Haoran, LIU Guizhong, BAN Yufeng, XU Fen, SUN Lixian. Construction of a Hydrogen Permeation Model and with an Application to Nb-based Hydrogen Permeable Alloy[J]. Materials Reports, 2018, 32(5): 725 -729 .

Viewed

Full text

Abstract

Cited

Shared

Discussed