Prediction of Mechanical Properties of 6061 aluminum Alloy After Heat Treatment Based on GA-BP Neural Network

Zhenyu Long; Feng Xiao; Wangli Xu

doi:10.62051/ijcsit.v4n3.09

Authors

Zhenyu Long
Feng Xiao
Wangli Xu

DOI:

https://doi.org/10.62051/ijcsit.v4n3.09

Keywords:

6061 aluminum alloy, Heat treatment process, GA-BP neural network, Mechanical properties

Abstract

To study the influence of the heat treatment process on the mechanical properties of 6061 aluminum alloy, a prediction model of the mechanical properties of 6061 aluminum alloy after heat treatment based on the GA-BP neural network was established. Based on this model, a set of simple and easy-to-operate built-in data prediction systems was designed. The correlation coefficient R of the GA-BP model was 0.98869, 0.98282, 0.93975, and 0.95657, respectively, and the prediction effect was good. Comparing the predicted value with the experimental value in the prediction system, it is concluded that the prediction accuracy reaches 95.6%, which proves that the model and system have certain stability and feasibility. In addition, this study provides an empirical reference for exploring the effects of solution temperature, cooling rate, aging temperature, and aging duration on the properties of aluminum alloys.

Downloads

Download data is not yet available.

References

[1] L. Natrayan, M. Senthilkumar, an integrated artificial neural network and Taguchi approach to optimize the squeeze cast process parameters of AA6061/Al2O3/SiC/Gr hybrid composites prepared by novel encapsulation feeding technique, Materials Today Communications, 25, 2020, 101586, ISSN2352-4928, https://doi.org/10.1016/j.mtcomm.2020.101586

[2] ZHANG Z Q, ZHOU X M, ZHENG S C, et al. Prediction of mechanical properties of aluminum alloy for arc additive manufacturing based on neural network [J]. Precision Forming Engineering, 2024, 16(01):43-51. https://doi.org/10.3969/j.issn.1674-6457.2024.01.005

[3] WEI M, XIAO L. Prediction of forging performance of aluminum alloy based on BP neural network [J]. HotWorkingechnology, 2021, 50(21):105-107+112. https://doi.org/10.14158/j.cnki.1001-3814.20191404

[4] NIU Qiulin, DAI Fupeng, JING Lu, et al. Optimization of multi-objective parameters for longitudinal-torsional ultrasonic vibration-assisted milling of 60% SiCp /Al [J]. Aeronautical Manufacturing Technology, 2024, 67(12): 14–26. https://doi.org/10.16080/j.issn1671-833x.2024.12.014

[5] Kang Liang, Mi Xiaoxi, Wang Hailian, et al. Research Progress of Artificial Neural Networks in Materials Science [J]. Materials Reports, 2020, 34(21):21172-21179. https://doi.org/10.11896/cldb.19080073

[6] WANG P P, CHENG Z Z, LING Q, et al. Springback prediction of aluminum alloy profiles based on deep learning neural network [J]. Forging technology, 2024, 49 (07): 105-111. https://doi.org/10. 13330 / j. issn. 1000-3940. 2024. 07. 012

[7] ZHANG N N. Effect of combined deformation and heat treatment process on microstructure and properties of 6061 aluminum alloy [D]. Jiangsu University, 2017.

[8] XIANG S, ZHOU C R, GUO J L, et al. Effect of solution-aging on microstructure and properties of 6061 aluminum alloy extruded bar [J]. Light alloy processing technology, 2011, 39 (04): 31-35+60. https://doi.org/10.13979 / j.1007-7235.2011.04.006

[9] Ma Yanwei, Wang Baoyu, Jiao Wenchao, et al. Effect of solution and aging process on mechanical properties of 6016 aluminum alloy and multi-objective optimization [J]. Journal of Engineering Science, 2017, 39 (01): 75-80. https://cje.ustb.edu.cn/article/doi/10.13374/j.issn2095-9389.2017.01.010

[10] LI X L, WEI Z. Effect of solution temperature on microstructure and mechanical properties of 6061 aluminum alloy [J]. Hot working process, 2019, 48 (24): 144-146 + 152. https://doi.org/10.14158 / j.cnki.1001-3814.2019.24.034

[11] ZHANG H, WANG G W, ZENG F Y, et al. Prediction of grain size of 6082 aluminum alloy after solution and aging treatment based on BP neural network [J]. Forging technology, 2023, 48 (03): 227-235, https://doi.org/10.13330 / j.issn.1000-3940.2023.032

[12] YAO L F, ZHANG D T. Effect of extrusion temperature on grain size and mechanical properties of 6061 aluminum alloy [J]. Hot working process, 2020, 49 (07): 33-35 + 39. https://doi.org/10.14158 / j.cnki.1001-3814.20193405

[13] CHEN J H, LI M G, YU J R, et al. Effect of heat treatment process on microstructure and mechanical properties of 6061 aluminum alloy [J]. Journal of Lanzhou University of Technology, 2010, 36 (02): 15-17. https://qikan.cqvip.com/Qikan/Article/Detail?id=33657622

[14] ZHANG S H, CHE L Z, TIAN W H, et al. Modeling of Mechanical Properties of Hot Rolled Sheet Based on Convolutional Neural Network [J]. Journal of Netshape Forming Engineering, 2022, 14(3): 1-7. https://doi.org/10.3969/j.issn.1674-6457.2022.03.001

[15] WANG Y Y, Wu C, Peng Z W, et al. Prediction Method of Elastic Modulus of Titanium Alloy Based on Machine Learning [J]. Journal of Netscape Forming Engineering, 2024, 16(1):33-42. https://doi.org/10.3969/j.issn.1674-6457.2024.01.004