摘要
基于MATLAB平台,将BP人工神经网络、遗传算法和数值模拟技术应用于铝型材挤压模具的导流孔形状优化设计。由正交实验法安排模拟实验组合,采用SuperForge软件对进行型材挤压过程进行数值模拟,并以挤压时金属流出模口平面的z向质点流速的均方差作为模型目标值;将模拟结果作为人工神经网络的输入样本对进行网络训练并建立网络知识源;通过遗传算法求得模型的全局优化解;最后通过有限体积法数值模拟技术验证并比较优化所得导流孔形状与经验法确定的导流孔形状对金属流动均匀性的影响。分析结果表明,通过调整导流孔形状能使金属流出模口的速度分布更均匀,表明对挤压模具导流孔形状的优化是有效的。
BP artificial neural network, genetic algorithm and finite element method （FEM） simulation were applied to optimization of the deflector hole design of profile extrusion die on MATLAB foundation. Orthogonal test was arranged for numerical simulation to get z-velocity at the die land exit which was used as the target value of the model. The BP artificial neural network was trained by the above z-velocity values to form knowledge source; and the general optimized solution was attained through genetic algorithm. At last, the optimized guide extrusion die was analyzed by SuperForge FEM software and compared to the design in the experiential way. The results of the computer aided engineering analysis shows that the optimization process is effective and the optimized deflector hole makes the velocity distribution in the die land more uniform.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2007年第2期225-231,共7页
Journal of Central South University:Science and Technology
基金
云南省省院省校科技合作计划项目(2003UABAB05A050)
关键词
BP人工神经网络
遗传算法
挤压模具
导流孔
有限体积法
BP artificial neural network
genetic algorithm
extrusion die
deflector hole
finite volume method
