摘要
研究了汽轮发电机组轴承转子系统摩擦学设计知识获取的神经网络方法,通过分析BP网络权重,得到网络输入与输出的函数关系,并定义了关系系数C.由关系系数C的大小和正负可以确定输入与输出的关系。
A neural network based on knowledge acqulsition-method of tribology design for rotor-bearing system of turbine-generator sets is discussed.The retationships between input and output neurons are acquired by analysing weights of BP networks.And the relationship co-efficient which translated implicit knowledge contained in the neural network into the ex-plicit representation is proposed.
出处
《机械科学与技术》
CSCD
北大核心
1995年第6期136-140,共5页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金
关键词
摩擦学
设计
神经网络
知识获取
Tribology design Neural network Knowledge acquisition.