摘要
在已有的滑动轴承非线性油膜力数据库基础上 ,将轴承的位置和速度参数加以综合 ,利用变量状态空间变换将分段的油膜力数据转换成连续的数据空间 ,建立非线性油膜力连续型数据库和相应的网络模型 .以圆轴承 -转子系统为例 ,分别采用有限差分法、数据库法和 BP网络模型计算了轴承系统的非线性油膜力和轴心轨迹 .结果表明 ,网络模型计算结果与基于数值方法的结果较为吻合 。
The database method to compute nonlinear oil-film force of the finite width hydrodynamic journal bearings can solve the contradiction between accuracy and efficiency, but the database and formulae of oil-film force are subsections. Positions and velocities of bearings are synthesized into three basic parameters and the state space transformation is used to change discontinuous oil-film force databases to consecutive oil-film force databases. So the integrative formula and the BP network model based on consecutive oil-film force databases are established to obtain the oil-film force under any movement state of axes with high accuracy. By means of the computation example of cylinder journal hydrodynamic bearings, the finite differential method, the database method and the BP neural network model are employed to calculate the oil-film force and the orbit of shaft center in the transient analysis of the rotor-bearing system. Results show that the result achieved with the BP network model is more approximate to that achieved with the numerical computation method and the BP network model can raise remarkably the computation efficiency of bearings.
出处
《摩擦学学报》
EI
CAS
CSCD
北大核心
2002年第3期226-231,共6页
Tribology
基金
国家自然科学基金重大项目资助 ( 1 9990 5 1 0
关键词
神经网络模型
非线性油膜力
BP网络
滑动轴承
Database systems
Films
Finite element method
Hydrodynamics
Neural networks
Rotors
