工艺参数对W-MoS_2综合性能影响的人工神经网络预报  

Predicting Effects of Technical Parameters on General Properties of W-MoS_2 Based on Artificial Neural Network

作　　者：孙小华[1] 周元贵[1] 张黔[1] 

机构地区：[1]武汉大学动力机械工程学院,湖北武汉430072

出　　处：《机械工程材料》2003年第8期38-40,共3页Materials For Mechanical Engineering

摘　　要：在试验数据的基础上,用人工神经网络建立了工艺参数与W MoS2综合性能关系的预测模型,讨论了隐含层神经元数选取和不同BP优化算法对网络性能的影响,结果表明,网络的预测同试验基本一致,具有可靠的预报能力。BZA prediction model for the effects of technical parameters on general properties of WMoS2 is built based on experimental data with the aid of artificial neural network and effects of the number of neural cells in hidden layers and different BP optimization algorithm on the properties of neural network are discussed. Final results show that the value predicted by the network conforms to the experimental data and the neural network has reliable predictability.

关 键 词：固体润滑 神经网络 BP优化算法 

分 类 号：TB333[一般工业技术—材料科学与工程]