摘要
采用人工神经网络构建了拖拉机后壁板拉延成形的目标函数模型,建立了拉延成形工艺参数和性能评价指标之间的映射关系,为各参数的研究和优化提供了重要参考。通过正交试验法对模型的训练,得到了高精度的神经网络模型。通过对拖拉机后壁板进行拉延成形建模,并对训练后的网络进行测试,网络误差小于5%,验证了所建网络模型的正确性和实用性,为工艺优化提供了行之有效的手段。
Using artificial neural network,the objective functional model of tractor back-wall blank forming in drawing process was established,a mapping between forming parameters and performance evaluation indexes was built,which provided important preferences for researching and optimizing these parameters. The neural network model of high precision was obtained by the training of orthogonal test method. At last a model of tractor back-wall blank was built. According to the test results,the error of the network was...
出处
《热加工工艺》
CSCD
北大核心
2009年第1期101-103,共3页
Hot Working Technology
基金
河南科技大学博士科研启动基金资助项目(20060616)
关键词
人工神经网络
正交实验
拖拉机后壁板
优化
artificial neural network
orthogonal test method
tractor back-wall blank
optimization
