Transactions of Materials and Heat Treatment

Title：Optimization on forming capacity for transition area of heavy forging based on BP-GA

Authors： Xiao Hong Dai Jiahong Liu Ge

Unit： Yangtze Normal University

KeyWords： aluminum alloy heavy forging local loading filing capacity artificial neural network genetic algorithm

ClassificationCode：TG316

year,vol(issue):pagenumber：2017,42(3):180-184

Abstract：

For the problems of under filling for aluminum alloy heavy forging, the forming parameters under the local loading were studied by combining back propagation neural network and genetic algorithm with FEM. Then, the filling capacity of transition zone was regarded as evaluation objectives, a relationship model between billet temperature, press velocity, amount of depression, feed rate and quality index was established, and the reasonable parameters were obtained with billet temperature 435 ℃, press velocity 5 mm·s-1, amount of depression 18 mm and feed rate 1165 mm. The forming process was simulated again with the above obtained parameters, and the practical manufacture was carried out. Therefore, the capacity of filling was good. It can be concluded that the filling problem can be effectively managed by the strategy proposed.

Funds：

肖红（1989-），男，硕士，助教

Reference：

［1］Yang H, Li L X, Wang Q D. Research on the development of advanced forming for lightweight alloy materials area [J]. Journal of Mechanical Engineering, 2010, 46 (12): 31-42.
［2］Clarka D A, Johnson W S. Temperatures effects on fatigue perform of cold expanded holes in 7050-T7451 aluminum alloy [J]. International Journal of Fatigue, 2003, 25 (2): 159-165.
［3］Deng L, Wang X Y, Xia J C, et al. Microstructural modeling and simulation of Al2.8Cu1.4Li alloy during elevated temperature deformation [J]. Metallurgical and Materials Transactions A, 2011, 42A (8): 2509-2515.
［4］Liu G, Wang Q, Ao Y. Convenient formulas for modeling three-dimensional thermo mechanical asperity contacts [J]. Tribology International, 2002, 35 (7): 411-423.
［5］Zhang D W, Yang H, Sun Z C. Analysis of local loading forming for titanium alloy Tshaped components using slab method [J]. Journal of Materials Processing Technology, 2010, 210 (2): 258-266.
［6］Zhang D W, Yang H. Metal flow characteristics of local loading forming process for ribweb component with unequalthickness billet [J]. International Journal of Advanced Manufacturing Technology, 2013, 68(9-12): 1949-1965.
［7］孙志超, 杨合, 李志燕. TA15合金H型构件等温局部加载成形工艺研究[J]. 稀有金属材料与工程, 2009, 38(11): 1904-1909.Sun Z C, Yang H, Li Z Y, et al. Research of isothermal local loading on Hshaped component of TA15 alloy[J]. Rare Metal Materials and Engineering, 2009, 38(11): 1904-1909.
［8］李志燕, 杨合, 孙志超,等. TA15合金大型复杂构件等温局部加载过渡区宏微观变形研究[J]. 稀有金属材料与工程，2008, 37(9):1516-1521.Li Z Y, Yang H, Sun Z C, et al. Macro and micro deformation research on translation area of isothermal local loading of heavy component of TA15 alloy[J]. Rare Metal Materials and Engineering, 2008, 37(9):1516-1521.
［9］Sadeghi B H M. A BPneural predictor model for plastic injection molding process [J]. Journal of Materials Processing Technology, 2000, 103 (3): 411-416.
［10］Fei Y, Hua J M, Lin H, et al. Back propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding[J]. Materials and Design, 2011, 32(4): 1844-1850.
［11］Chow T T, Zhang G Q, Lin Z, et al. Global optimization of absorption chiller system by genetic algorithm and neural network [J]. Energy Build, 2002, 34 (1): 103-109.

Service：

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