论文部分内容阅读
采用神经网络技术预测拉深件毛坯外形的方法中，网络的结构对预测结果的优劣有很大的影响。提出了ＢＰ网络的网络参数，并结合训练样本的数目给出了网络参数和样本数目之间的关系。应用本文提出的方法设计了毛坯外形预测的ＢＰ神经网络结构。
In the method of using neural network technology to predict the contour of a blank, the structure of the network has a great influence on the prediction results. The network parameters of BP network are proposed, and the relationship between the network parameters and the number of samples is given according to the number of training samples. The method proposed in this paper is used to design the rough structure of BP neural network.