BP神经网络在复杂曲线曲面反求中的应用研究  

Study on application of BP neural network to the reverse design of complex curve and surface

作　　者：李建伟[1] 梁爱琴[1] 丁俊成[1] 

机构地区：[1]河南农业大学机电工程学院,郑州450002

出　　处：《现代制造工程》2007年第1期38-40,43,共4页Modern Manufacturing Engineering

摘　　要：介绍BP神经网络的结构与学习算法,建立用于复杂曲线、曲面反求的BP神经网络模型,论述模型建立的步骤与原则方法,阐述利用所建立的模型对曲线、曲面进行反求的实施过程。实验研究表明,该方法能够较好地实现复杂曲线、曲面的反求,并具有一定的容错能力。最后简要介绍该方法的不足之处。The architecture and the arithmetic of BP neural network were introduced. Furthermore, the BP neural network model was established. At the same time, the process and principle of the modeling also were expounded. Then, it was explained that how to use the BP neural network model in the reverse design of complex curve and surface. The result of experiment shows that the method takes effect very well in the reverse design of complex curve and surface, and also has the ability to resist errors. At last, the disadvantage of the method was discussed briefly.

关 键 词：BP神经网络 复杂曲线 曲面 反求设计 

分 类 号：TH122[机械工程—机械设计及理论] TP391[自动化与计算机技术—计算机应用技术]