摘要
分析了常规有限元金属板料成形模拟的不足 ,提出了参数化有限元分析的概念 ,在对人工神经网络、遗传算法进行深入分析研究的基础上 ,采用参数化有限元分析方法进行分析 ,得到了训练样本。提出了采用人工神经网络技术建立冲压件成形多参数映射关系模型 ,采用遗传算法进行多参数组合优化 ,实现冲压件成形计算机模拟工艺参数优化的方法。实际应用结果表明 ,优化结果与试验结果基本吻合 ,该优化方案实用可行。
Based on analyzing the shortcomings of general FEA course,a conception of Parametric Finite Element Analysis (PFEA) was presented. According to the study of artificial neural networks (ANN) and genetic algorithm (GA), the training specimens were obtained by PFEA. A multi-parametric combination optimization model was found by PFEM and ANN for sheet metal forming. A new method that Parametric Finite Element Analysis, artificial neural networks and genetic algorithm were combined to research thoroughly on the problems of process parameter optimization of sheet metal forming process. Procedure was programmed for process parameter optimization of sheet metal forming and applied in a pressing analysis of square hole flanging. The optimum results obtained accord with the experimental results of published materials. The research shows that process parameter optimization of sheet metal forming are accurate and reliable. And a new efficient method is explored on process parameter optimization of numerical simulation of sheet metal forming.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2004年第7期648-651,654,共5页
China Mechanical Engineering
基金
江西省主要学科跨世纪学术和技术带头人培养计划资助项目(2 0 0 1-6)
华中科技大学塑性成形模拟及模具技术国家重点实验室开放基金资助项目 (2 0 0 3 -12)
关键词
金属冲压件成形
优化
参数化有限元分析
人工神经网络
遗传算法
sheet metal forming
optimization
parametric finite element analysis
artificial neural network
genetic algorithm
