【摘要】 基于滑动轴承油膜力数据库的连续性分析,建立了椭圆轴承非线性油膜力的神经网络计算模型.该模型采用混沌扰动的BP算法训练网络,其计算结果吻合于数值解,和数据库计算方法相比,提高了计算效率.将油膜力的网络模型用于椭圆轴承-转子系统的运动方程中,可快速准确地获得系统的运动状态.在不同转速下,系统表现出同步周期运动、倍周期运动、拟周期运动或混沌等典型的非线性运动特性.应用实例表明,该模型可有效地用于旋转机械非线性动力学问题的研究.更多还原

【Abstract】 Based on continuity analysis of oilfilm force databases of hydrodynamic bearings, neural network model of nonlinear oilfilm forces of elliptical bearings is developed. The neural network is trained by chaotic BP algorithm. The solutions of network model are almost identical to numerical computation, and the running efficiency is increased compared with database computation method. The motion of elliptical bearingrotor system is simulated by means of network model of oilfilm forces and fourthorder RungeKutta method. Nonlinear motion states of bearingrotor system are obtained with high efficiency and accuracy. There exist multitypes of motion behaviors at various rotating speeds, such as synchronous, subsynchronous, quasiperiodic or chaotic motion. It is shown that the neural network models of oilfilm forces are useful to study nonlinear dynamic problems of rotation machinery.更多还原