无润滑机构系统考虑摩擦和柔性影响的动态响应神经网络预测  

Prediction on Nonlinear Dynamic Responds of Non-lubrication Mechanism System Considered Friction and Flexibleness Based on Neural Network

作　　者：于霖冲[1] 白广忱[1] 焦俊婷[1] 李辉[1] 

机构地区：[1]北京航空航天大学能源与动力工程学院

出　　处：《润滑与密封》2006年第4期45-47,共3页Lubrication Engineering

基　　金：国家自然科学基金资助项目(50275006);教育部博士点基金资助项目(20020006036)

摘　　要：柔性机构的动态响应为高度非线性,摩擦和柔性的影响使机构运动的不确定性增大,机构实时控制的难度较大。应用改进的E lman动态神经网络技术,建立摩擦影响下的无润滑柔性机构非线性运动参数预测模型,对柔性机构的运动参数进行实时辨识和预测。通过对空间站展开机构动态响应的预测实例,证明该方法计算速度较快,精度较高,为实现复杂大系统的实时控制提供了一个有效可行的方法。The characters of flexible mechanism motion are highly nonlinear. The dynamic responds of mechanism become more uncertain because of friction and flexibleness. It is more difficult to control the mechanism at the real time. Via modified Elman dynamical artificial neural network, nonlinear parameters prediction model of non-lubrication mechanism considered influence of friction and flexibleness was established identification model to identify and forecast the motive parameters of flexible mechanism. Expand mechanism of space station was applied to test this method. The results prove that the calculation speed of the model is fast and the precision is high. The methods provide an available way on the control of complicated systems at the real time.

关 键 词：润滑机构 非线性动态响应 神经网络 预测 

分 类 号：TH164[机械工程—机械制造及自动化] TU311.3[建筑科学—结构工程]