%0 Journal Article
%T 负荷车电涡流缓速器加载控制系统研究<br>Study on the Eddy Current Retarder Loading Control System of Loading Vehicles
%A 李忠利
%A 闫祥海
%A 周志立
%J 西安交通大学学报
%D 2018
%R 10.7652/xjtuxb201803017
%X 为能更真实反映被试拖拉机牵引特性,对负荷车加载系统进行了改进,建立了负荷车加载系统传递函数模型。以牵引力载荷谱随机信号为输入,采用BP神经网络算法对加载系统进行动态加载控制,以输出不同类型的作业载荷。对系统响应特性进行了动态分析,在此基础上进行了道路试验验证,证明加载系统的有效性。在该控制模式下系统仿真载荷输出延迟0.12 s,最大超调量为3.1％;路试载荷输出延迟0.22 s,最大超调量为4.2％。试验结果表明,BP神经网络PID控制的系统输出载荷对输入载荷具有更好的跟随效果,比传统PID控制响应性好,开发的负荷车加载系统输出载荷能够较好再现拖拉机实际牵引载荷。<br>A loading control system of loading vehicle is improved to be able to effectively reflect the traction performance of a tractor in field work. A mathematical model of the loading vehicle’s loading system is established. The input signal of the loading system is the stochastic signal of a field load spectrum. The backpropagation neural network is applied to control the loading system. The output signal of the loading system can simulate different kinds of working loads. The loading system response is analyzed dynamically. On the basis of the above study, the road test of the tractor’s traction performance was conducted. In this control mode, the simulation results showed that the system delay time is 0.12 s and maximum overshoot is 3.1％. The road test results showed that the system delay time is 0.22 s and maximum overshoot is 4.2％. Experimental results showed that the system output traction has a good following effect in comparison with the input load. The BP neural net PID algorithm can improve the system’s dynamical performance and its control response is better than the traditional PID control. So the output load of the developed loading system can better reproduce the tractive performance for the tested tractor
%K 负荷车
%K 加载系统
%K 随机载荷
%K BP神经网络
%K PID控制&lt
%K br&gt
%K loading vehicle
%K loading system
%K random load
%K back propagation neural net
%K PID control
%U http://zkxb.xjtu.edu.cn/oa/DArticle.aspx?type=view&id=201803017