基于人工神经网络的液压振动系统研究  

Study on hydraulic vibration system based on artificial neural network

作　　者：郭志刚[1] 李文选[1] 冯继刚[1] 

机构地区：[1]河北工程大学机电工程学院,河北邯郸056038

出　　处：《河北工程大学学报（自然科学版）》2012年第2期78-80,共3页Journal of Hebei University of Engineering:Natural Science Edition

摘　　要：以两自由度液压激振压路机的液压振动系统为研究对象,采用立体正交试验选取试验因素,在每个试验因素中选择3个水平子集合,获得训练神经网络的样本。通过人工神经网络理论建立数学模型,借助Mtalab仿真计算出试验因素水平子集合最优组合参数。研究结果表明:通过建立人工神经网络数学模型,得出立体正交表的最优组合仿真目标值为0.552 3,系统刚度为3.3 N/mm,与试验目标值的相对误差为10.46%,满足工程要求。The hydraulic vibration system of two freedom hydraulic vibration roller was the research object in this paper. Three horizontal subsets were selected in every experimental factor which was ob- tained from the three -dimensional orthogonal experiment to obtain the samples of the training neural network. The mathematic model was built by artificial neural network theory and the optimum com- bined parameters of horizontal subsets were established by means of Mtalab simulation. The results show that target value of the optimum combined is 0. 552 3 and the stiffness of the system is 3.3 N/ mm through the artificial neural network mathematics model. This meets the project requirement because of the relative error of 10.46% between experimental results and experimental target value.

关 键 词：正交试验 人工神经网络 数学模型 计算机仿真 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]