神经网络技术在油气悬挂缸输出力特性预测中的应用  

Non-parametric modeling of hydro-pneumatic cylinder based on neural network

作　　者：周德成[1] 王国强[1] 国香恩[1] 刘玉臣[1] 

机构地区：[1]吉林大学机械学院,吉林长春130025

出　　处：《煤矿机械》2004年第3期113-115,共3页Coal Mine Machinery

摘　　要：以某重型自卸车油气悬挂缸为研究对象进行了台架实验 ,得到了不同激励振幅和激励频率时输出力的变化规律。利用所得实验数据 ,应用BP网络建立了该型油气悬挂缸的非参数化模型 ,并应用该模型对油气悬挂缸的输出力特性进行了预测。结果表明 :该网络具有良好的泛化能力 ,可以准确地预测该型油气悬挂缸的输出力特性。This paper takes the hydro-pneumatic cylinder of certain type of heavy dumper trucker as studying object,conducts an experiment,and gets the rule of the output force under different excitation amplitude and frequency.At the same time,based on the experimental results,the paper applies back-propagation network to build the non-parametric model,and uses the model to forecast the characteristics of the output force.The simulation results show that the network has good generalization performance and that can forecast the nonlinear characteristics perfectly.

关 键 词：油气悬挂缸 神经网络 非参数化模型 台架实验 

分 类 号：U469.4[机械工程—车辆工程]