Transactions of Materials and Heat Treatment

Title：Prediction of steady state stress for aluminum alloy 6016 based on Sellars-Tegart equation and BP neural network

Authors： Zhang Jianping1 2 Li Bin1 Fang Fang1

Unit： 1. College of Energy and Mechanical Engineering Shanghai University of Electric Power Shanghai 200090 China 2. Shanghai Key Laboratory of Materials Protection and Advanced Materials in Electric Power Shanghai 200090 China

KeyWords： Sellars-Tegart equation BP neural network prediction model aluminum alloy 6016 steady state stress

ClassificationCode：

year,vol(issue):pagenumber：2016,41(1):116-120

Abstract：

In order to analyze the relationship between thermodynamic parameters and steady state stress for aluminum alloy 6016 and predict its steady state stress, the prediction models were established based on Sellars-Tegart equation and BP neural network. Then comparison and analysis between the predicted values and the experimental data of the two models were carried out. The results show that the predicted values of Sellars-Tegart constitutive equation and BP neural network constitutive model are both in good agreement with that of the experiment, and reflect the change law of steady state stress well. The average relative error and the standard residual error of the prediction values of steady state stress by BP neural network are 2.3212% and 1.3374 respectively, which are both less than that obtained by Sellars-Tegart constitutive equation. It is confirmed that the constitutive model of BP neural network has better prediction accuracy for the steady state stress of aluminum alloy 6016.

Funds：

国家自然科学基金资助项目（11572187）；上海市教育委员会科研创新项目（14ZZ154）；上海市科学技术委员会项目（14DZ2261000, 13160501000）

：张建平（1972-），男，博士，教授

Reference：

[1]谢丽军. 用于汽车工业的铸造铝合金评述 [J].轻金属, 2013, (11): 57-59.

Xie L J. Casting aluminum alloys for automobile [J]. Light Metals, 2013, (11): 57-59.

[2]Yuan W, Mishra R S, Webb S, et al. Effect of tool design and process parameters on properties of Al alloy 6016 friction stir spot welds [J]. Journal of Materials Processing Technology, 2011, 211(6): 972-977.

[3]Engler O, Hirsch J. Texture control by thermo mechanical processing of AA6xxx Al–Mg–Si sheet alloys for automotive applications—a review [J]. Material Science and Engineering, 2002, 336(1): 249-262.

[4]曹园园. 6181/6016H18高强铝合金同步冷却热成形工艺研究 [D]. 南京:南京航空航天大学, 2011.

Cao Y Y. Research on Dynchronized Cooling Hot Forming Process of 6181/6016 H18 High Strength Aluminum Alloys [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2011.

[5]张继祥, 冯伟, 文辉, 等. 6016铝合金高温流变应力行为研究 [J].材料热处理技术, 2012, 41(22): 1-5.

Zhang J X, Feng W, Wen H, et al. Mechanical behavior for 6016 aluminum alloy under hot-working conditions [J]. Material & Heat Treatment, 2012, 41(22): 1-5.

[6]Huang C Q, Diao J P, Deng H, et al. Microstructure evolution of 6016 aluminum alloy during compression at elevated temperatures by hot rolling emulation [J]. Transactions of Nonferrous Metals Society of China, 2013, 23(6): 1576-1582.

[7]葛丽丽, 李永兵, 陆兴, 等. 6016铝合金汽车板材预时效处理工艺研究 [J]. 锻压技术, 2014, 39(1): 113-117.

Guo L L, Li Y B, Lu X, et al. Research on pre-aging treatment of 6016 automotive aluminum sheet [J]. Forging & Stamping Technology, 2014, 39(1): 113-117.

[8]鲁世强, 周细林, 王克鲁, 等. 基于BP神经网络的2D70铝合金本构关系模型 [J]. 锻压技术, 2008, 33(1): 148-151.

Lu S Q, Zhou X L, Wang K L, et al. Building the constitutive relationship model of 2D70 aluminum alloy based on neural network [J]. Forging & Stamping Technology, 2008, 33(1): 148-151.

[9]文辉. 6016铝合金温挤压流变应力行为及有限元分析[D]. 重庆:重庆交通大学, 2011.

Wen H. The Warm Forming Flow Stress Characteristics of 6016 Aluminum Alloy and Finite Element Analysis [D]. Chongqing: Chongqing Jiaotong University, 2011.

[10]刁金鹏. 6016铝合金热变形行为及热轧过程数值模拟研究 [D]. 长沙：湖南大学, 2011.

Diao J P. Hot Deformation Behavior of Aluminum Alloy and Numerical Simulation of Hot Rolling Process [D]. Changsha: Hunan University, 2011.

[11]孙宇, 曾卫东, 赵永庆, 等. 基于BP神经网络Ti600合金本构关系模型的建立 [J]. 稀有金属材料与工程, 2011, 40(2): 220-224.

Sun Y, Zeng W D, Zhao Y Q, et al. Modeling of constitutive relationship of Ti600 alloy using BP artificial neural network [J]. Rare Metal Materials and Engineering, 2011, 40(2): 220-224.

Service：

【This site has not yet opened Download Service】【Add Favorite】