|
摘要：
|
|
结合人工神经网络所表现出来的良好特性,利用正交试验获得的数据作为神经网络的训练样本,建立输入为工艺参数、输出为回弹量ΔZ的神经网络模型。通过样本检验了ANN模型的准确性,从而缩短设定工艺参数的时间,在工艺参数取值范围内,采用ANN模型代替CAE软件模拟试验,结合正交试验法,对工艺参数进一步优化。结果表明,将神经网络与正交试验、数值模拟三者结合用于板料成形参数优化,可以缩短优化工艺参数的时间,提高工艺设计效率。
|
|
The data got from an orthogonal experiment was used as the training sample to establish a neural network model in which the input was the technological parameters and the output was the springback quantity.The accuracy of the ANN model was proved by the sample.In this way,the time to set the technological parameters was shortened.The ANN model was used to substitute CAE numerical simulation test,and combined with orthogonal experiment method,the technological parameters was further optimized.The result shows that the integration of ANN,orthogonal experiment and numerical simulation method used in optimization of sheet metal forming has shorten the time of technological parameter optimizing and has greatly increased the technological design efficiency.
|
|
基金项目：
|
|
河南省教育厅自然科学科技攻关项目(2006460011);;
河南科技大学博士科研启动基金资助(20060616)
|
|
作者简介：
|
|
|
|
参考文献：
|
[1]李玉强,崔振山,张冬娟,等.板料成形优化技术进展与质量工程研究[J].塑性工程学报,2005,12(2):11-16.
[2]潘江峰,钟约先,袁朝龙,等.板料拉深成形工艺参数的多目标遗传算法优化[J].清华大学学报:自然科学版,2007,47(8):1267-1269.
[3]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.
[4]潘江峰,钟约先,袁朝龙,等.基于遗传算法和神经网络技术的板料拉深成形参数优化[J].锻压技术,2006,31(6):44-46.
[5]张超.正交试验法在汽车翼子板成形技术中的应用[J].模具工业,2007,33(5):26-29.
[6]高军,张承瑞,季廷炜,等.基于正交设计的神经网络训练样本的选择方法[J].塑性工程学报,2006,13(5):32-35.
|
|
服务与反馈：
|
|
【本网站尚未开通全文下载服务】【加入收藏】
|
|
|
|
