李绘超,王 杰,唐 鹏.基于神经网络和遗传算法的压力机调节螺杆优化设计[J].轻工机械,2011,29(5): |
基于神经网络和遗传算法的压力机调节螺杆优化设计 |
Optimization Design of a Press′s Adjustable Screw Based on Neural Network and Genetic Algorithm |
|
DOI: |
中文关键词: 机械设计 调节螺杆 有限元 神经网络 遗传算法 |
英文关键词:mechanical design adjustable screw finite element neural network genetic algorithm |
基金项目: |
李绘超 王 杰 唐 鹏 |
四川大学 制造科学与工程学院, 四川 成都 610065 |
摘要点击次数: 2122 |
全文下载次数: 1251 |
中文摘要: |
强度和质量是压力机调节螺杆主要性能指标。将神经网络和遗传算法结合起来,可以很好地对调节螺杆结构进行多目标优化设计。文章首先建立了调节螺杆有限元分析模型,然后应用正交试验方法对神经网络的训练样本进行试验安排,并建立出设计参数与最大应力、质量映射关系的神经网络模型。利用遗传算法对该神经网络模型进行全局寻优,得到调节螺杆的最优结构参数。 |
英文摘要: |
The strength and mass are the major performance parameters of the press's adjustable screw. The multi-objective optimization of the adjustable screw structure can be performed by a method based on the neural network in conjunction with the genetic algorithm. Firstly, the finite element model for adjustable screw was established. Then the trial sample data of the neural network were arranged with the orthogonal experimentation, and simulation models of the neural network which can reflect the mapping between design parameters and the maximum stress and mass were established. The neural network models were optimized with the generic algorithm, and the optimal structure parameters were obtained. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |