铝锂合金疲劳性能及预测研究-基于试验和“浅层”+“深度”混合神经网络方法

doi:10.3901/JME.2024.16.190

机械工程学报 ›› 2024, Vol. 60 ›› Issue (16): 190-199.doi: 10.3901/JME.2024.16.190

扫码分享

铝锂合金疲劳性能及预测研究-基于试验和“浅层”+“深度”混合神经网络方法

赵德望¹, 姜超¹, 赵延广², 杨文平³, 樊俊铃⁴

1. 安徽理工大学机电工程学院淮南 232000;
2. 大连理工大学工程力学系大连 116024;
3. 哈尔滨工程大学航天与建筑工程学院哈尔滨 150001;
4. 中国飞机强度研究所强度与结构完整性全国重点实验室西安 710065

收稿日期:2023-11-07 修回日期:2024-04-15 出版日期:2024-08-20 发布日期:2024-10-21
作者简介:赵德望,男,1986年出生,博士,副教授,硕士研究生导师。主要研究方向为成形制造、制造工艺力学。E-mail:dewangzhao@qq.com
赵延广(通信作者),男,1981年出生,博士,高级工程师。主要研究方向为疲劳、断裂及损伤容限性能测试与分析。E-mail:ygzhao81@dlut.edu.cn
基金资助:
安徽省自然科学基金(2308085ME166)、安徽省高校科学研究重点(KJ2021A0417)、航空科学基金(20200009023004)和中国博士后科学基金面上(2020M680947)资助项目。

Fatigue Performance Prediction Study of Al-Li Alloy-based on Experimental and “Shallow” + “Deep” Hybrid Neural Network Methods

ZHAO Dewang¹, JIANG Chao¹, ZHAO Yanguang², YANG Wenping³, FAN Junling⁴

1. School of Mechatronics Engineering, Anhui University of Science and Technology, Huainan 232000;
2. Department of Engineering Mechanics, Dalian University of Technology, Dalian 116024;
3. Department of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001;
4. National Key Laboratory of Strength and Structural Integrity, Aircraft Strength Research Institute, Xi'an 710065

Received:2023-11-07 Revised:2024-04-15 Online:2024-08-20 Published:2024-10-21

摘要/Abstract

摘要： 铝锂合金以其优异的力学性能在航空航天领域有着愈发重要的应用，是目前发展最为迅速的轻量化材料之一。疲劳与断裂是引起航空航天结构件失效的主要原因之一，且疲劳破坏具有很强的不确定性和突发性，因此针对铝锂合金疲劳性能评估及预测成为研究热点。开展考虑取样方向、缺口等因素的2A97铝锂合金疲劳试验，获得8组完整S-N曲线，分析相关因素对铝锂合金疲劳性能的影响；提出一种基于浅层网络＋深度学习的混合神经网络模型，首先利用浅层算法对低周疲劳试验数据进行训练，实现了数据衍生，进而通过深度学习精准预测出不同工况下的铝锂合金疲劳极限。该方法为快速精确评估材料疲劳性能研究提供新的解决思路。

关键词: 铝锂合金, 疲劳性能, 浅层网络, 深度学习

Abstract: With its excellent mechanical properties, aluminum-lithium alloy has increasingly important in aerospace field and is one of the most rapidly developing lightweight materials. Fatigue and fracture are one of the main causes of failure of aerospace structural components, and fatigue damage is highly uncertain and sudden, so its fatigue performance evaluation and prediction has become a hot research topic. The fatigue experiments of 2A97 aluminum-lithium alloy considering the sampling direction, notch, etc. are carried out to obtain eight sets of complete S-N curves and the influence of relevant factors on the fatigue performance of aluminum-lithium alloy are analyzed. A hybrid neural network model based on shallow network and deep learning is innovatively proposed. The shallow algorithm is used to train the low cycle fatigue experimental data to realize data derivation at first, and then accurately predict the fatigue limit of aluminum-lithium alloy under different working conditions by deep learning. This method provides a new way for the research of fast and accurate evaluation of fatigue properties of materials.

Key words: aluminum-lithium alloy, fatigue performance, shallow networks, deep learning

中图分类号:

O346

赵德望, 姜超, 赵延广, 杨文平, 樊俊铃. 铝锂合金疲劳性能及预测研究-基于试验和“浅层”+“深度”混合神经网络方法[J]. 机械工程学报, 2024, 60(16): 190-199.

ZHAO Dewang, JIANG Chao, ZHAO Yanguang, YANG Wenping, FAN Junling. Fatigue Performance Prediction Study of Al-Li Alloy-based on Experimental and “Shallow” + “Deep” Hybrid Neural Network Methods[J]. Journal of Mechanical Engineering, 2024, 60(16): 190-199.

参考文献

[1] 徐佳辉,黄亮,谢冰鑫,等. 铝锂合金电磁形变复合热处理工艺研究[J]. 机械工程学报,2022,58(16):58-67. XU Jiahui, HUANG Liang, XIE Bingxin,et al. Study on electromagnetic deformation combined with heat treatment process of Al-Li alloy[J]. Journal of Mechanical Engineering,2022,58(16):58-67.
[2] 李飘,姚卫星. 铝锂合金材料发展及综合性能评述[J].航空工程进展,2019,10(1):12-20. LI Piao,YAO Weixing. Review on the development and comprehensive properties of Al-Li alloy materials[J]. Advances in Aeronautical Science and Engineering,2019,10(1):12-20.
[3] DI Z,SAJI S,HORI S. Effect of microstructure on high cycle fatigue behaviour of AL-Li binary alloy[J]. Le Journal de Physique Colloques,1987,48(3):753-759.
[4] ALEXOPOULOS N D,MIGKLIS E,STYLIANOS A,et al. Fatigue behavior of the aeronautical Al-Li(2198) aluminum alloy under constant amplitude loading[J]. International Journal of Fatigue,2013,56:95-105.
[5] 艾素华,吴细毛,张匀. S'和T₂相对8090铝锂合金低周疲劳行为的影响[J]. 机械工程材料,1998,22(2):6-9. AI Suhua,WU Ximao,ZHANG Yun. Effected of precipitated phase S' and T₂ on the low cycle fatigue behaviour of 8090 Al-Li alloy[J]. Materials for Mechanical Engineering,1998,22(2):6-9.
[6] 郝敏,王亮,陈军洲,等. 2060-T8E30铝锂合金平面各向异性和断裂破坏机制研究[J]. 稀有金属,2021,45(6):641-649. HAO Min,WANG Liang,CHEN Junzhou,et al. Research on 2060-T8E30 Aluminum-Lithium alloy plane anisotropy and fracture failure mechanism[J]. Chinese Journal of Rare Metals,2021,45(6):641-649.
[7] 张雪洋,钟振东,潘雪纯,等. 划痕损伤对含铆钉孔2198-T8铝锂合金疲劳性能的影响[J]. 塑性工程学报,2022,29(9):199-206. ZHANG Xueyang,ZHONG Zhendong,PAN Xuechun,et al. Effect of scratch damage on fatigue performance of 2198-T8 aluminum-lithium alloy with rivet holes[J].Journal of Plasticity Engineering,2022,29(9):199-206.
[8] 杨文平,郭杏林,赵延广. 对流和辐射换热对金属高周疲劳能量耗散估计的影响[J]. 机械工程学报,2021,57(10):187-195. YANG Wenping,GUO Xinglin,ZHAO Yanguang. Effects of convection and radiation heat transfer on energy dissipation estimation of metal in high-cycle fatigue[J]. Journal of Mechanical Engineering,2021,57(10):187-195.
[9] RAMACHANDRA S,DURODOLA J F,FELLOWS N A,et al. Experimental validation of an ANN model for random loading fatigue analysis[J]. International Journal of Fatigue,2019,126:112-121.
[10] FENG C,XU L Y,ZHAO L,et al. Prediction of welded joint fatigue properties based on a novel hybrid SPDTRS-CS-ANN method[J]. Engineering Fracture Mechanics,2022,275:108824.
[11] BRITO O G A,FREIRE J R C S,CONTE M V L A,et al. A hybrid ANN-multiaxial fatigue nonlocal model to estimate fretting fatigue life for aeronautical Al alloys[J]. International Journal of Fatigue,2022,162:107011.
[12] ZHANG X,GONG J G,XUAN F Z. A deep learning based life prediction method for components under creep, fatigue and creep-fatigue conditions[J]. International Journal of Fatigue,2021,148:106236.
[13] YANG Jingye,KANG Guozheng,LIU Yujie,et al. A novel method of multiaxial fatigue life prediction based on deep learning[J]. International Journal of Fatigue,2021,151:106356.
[14] 王刚,高琛,王书艳,等. 频率及应力比对18CrNiMo7-6合金钢疲劳性能的影响[J]. 热加工工艺,2022,51(2):51-55. WANG Gang,GAO Chen,WANG Shuyan,et al. Effects of frequency and stress ratio on fatigue performance of 18CrNiMo7-6 alloy steel[J]. Hot Working Technology,2022,51(2):51-55.
[15] MANNO A,MARTELLI E,AMALDI E. A shallow neural network approach for the short-term forecast of hourly energy consumption[J]. Energies,2022,15:958.
[16] XIAO Z,YE S J,ZHONG B,et al. BP neural network with rough set for short term load forecasting[J]. Expert Systems with Applications,2009,36(1):273-279.
[17] ZHAO Dewang,ZHAO Kunmin,REN Daxin,et al. Ultrasonic welding of magnesium-titanium dissimilar metals:A study on influences of welding parameters on mechanical property by experimentation and artificial neural network[J]. Journal of Manufacturing Science and Engineering-Transactions of the ASME,2017,139(3):031019.
[18] ZHAO Dewang,REN Daxin,ZHAO Kunmin,et al. Effect of welding parameters on tensile strength of ultrasonic spot welded joints of aluminum to steel-By experimentation and artificial neural network[J]. Journal of Manufacturing Processes,2017,30(12):63-74.
[19] ZHAO Dewang,REN Daxin,SONG Gang,et al. Comparison of mechanical properties and the nugget formation of composite ceramic-centered annular welding and traditional resistance spot welding[J]. International Journal of Mechanical Sciences,2020,187(5):105933.
[20] GERS F A,SCHMIDHUBER E. LSTM recurrent networks learn simple context-free and context-sensitive languages[J]. IEEE Transactions on Neural Networks,2001,12(6):1333-1340.

铝锂合金疲劳性能及预测研究-基于试验和“浅层”+“深度”混合神经网络方法

Fatigue Performance Prediction Study of Al-Li Alloy-based on Experimental and “Shallow” + “Deep” Hybrid Neural Network Methods

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]	吴吉展, 魏沛堂, 吴少杰, 刘怀举, 朱才朝. 航空齿轮钢滚动接触疲劳性能预测与表面完整性优化[J]. 机械工程学报, 2024, 60(8): 81-93.
[2]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[3]	褚强, 杨夏炜, 李文亚, 范文龙, 邹阳帆, 郝思洁. 铝锂合金无针搅拌摩擦点焊接头组织演变与强化机制研究[J]. 机械工程学报, 2024, 60(2): 150-158.
[4]	付玲, 佘玲娟, 颜镀镭, 张鹏, 龙湘云. 基于内嵌物理信息与注意力机制BiLSTM神经网络的臂架系统疲劳损伤预测模型[J]. 机械工程学报, 2024, 60(13): 205-215.
[5]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.
[6]	刘岳开, 王天杨, 褚福磊. 基于低延迟可解释性深度学习的复杂旋转机械关键部件知识嵌入与诊断方法研究[J]. 机械工程学报, 2024, 60(12): 107-115.
[7]	赖旭伟, 丁昆, 张楷, 黄锋飞, 郑庆, 李致萱, 丁国富. 基于可解释物理引导空间注意力改进的跨工艺参数立铣刀磨损辨识[J]. 机械工程学报, 2024, 60(12): 147-157.
[8]	林昕, 毛杨坤, 傅盈西, 朱锟鹏. 基于图像语义分割与图卷积的选区激光熔融成形过程羽流运动特征分析[J]. 机械工程学报, 2024, 60(12): 168-182.
[9]	邵海东, 肖一鸣, 邓乾旺, 任颖莹, 韩特. 基于不确定性感知网络的可信机械故障诊断[J]. 机械工程学报, 2024, 60(12): 194-206.
[10]	李玖法, 邹博文, 任玥. 考虑车-路交互作用的车辆轨迹预测算法研究[J]. 机械工程学报, 2024, 60(10): 76-85.
[11]	许思远, 张卫东, 毛玉明, 牛斌. 数据驱动的指定变形非均质多胞结构优化设计[J]. 机械工程学报, 2024, 60(1): 85-95.
[12]	何赟泽, 李响, 王洪金, 侯岳骏, 张帆, 牟欣颖, 刘浩, 程豪, 李时华, 李杰. 基于可见光和热成像的风机叶片全周期无损检测综述[J]. 机械工程学报, 2023, 59(6): 32-45.
[13]	张吉银, 姚倡锋, 谭靓, 崔敏超, 周征, 孙蕴齐, 李国喜, 樊怡. 喷丸强化残余应力对疲劳性能和变形控制影响研究进展[J]. 机械工程学报, 2023, 59(6): 46-60.
[14]	毕思源, 张新瑞, 雷正龙, 黎炳蔚, 夏佩云. 光束摆动方式对2195铝锂合金T型接头双侧激光焊接裂纹的影响[J]. 机械工程学报, 2023, 59(22): 245-253.
[15]	冯晓慧, 高飞, 赵阳, 关雪飞, 何晶靖, 林京. 电弧增材再制造低碳钢疲劳性能研究[J]. 机械工程学报, 2023, 59(14): 151-158,168.