基于PID神经网络控制器的汽车起动电机测试系统  

Automobile Staring Motor Test System Based of PID Neural Network Controller

作　　者：张墩利[1] 周国栋[1,2] 

机构地区：[1]湖南广播电视大学机电工程系,湖南长沙410004 [2]中南大学机电工程学院,湖南长沙410083

出　　处：《电机与控制应用》2016年第9期70-73,78,共5页Electric machines & control application

基　　金：湖南省教育厅资助项目(15C0930);湖南省科技厅工业支撑项目(2014GK3054)

摘　　要：汽车起动电机测试系统具有复杂的非线性和强干扰等特点,测试精度高、测试速度快,对控制器要求很高。传统的PID算法对非线性系统效果不佳,容易出现较大的电流和力矩冲击;复杂的智能算法过程繁琐,参数整定困难,在工程实际中实现困难。设计了PID神经网络控制器,结合PID算法和智能算法两者的优点,既利用PID简单的结构,又借助神经网络的非线性映射特点和自学习能力来优化PID参数。仿真表明系统具有较高的测试精度和测试效率。该方法使用简单,很适合在工程实际中推广应用。Starter performance tester requires high precision and fast speed with a complex nonlinear structure and strong interference. The traditional PID controller always brings the bad effect with larger current and torque shocks. The complex intelligent algorithm was difficult to be realized in practical engineering for its trouble of parameter tuning. A new PID neural network（PIDNN） controller was designed which integrated the advantages of PID and intelligent controller. PIDNN had simple structure as PID and self learning ability as NN to optimize parameters. The simulation results verified the precision and efficiency of the test system.

关 键 词：直流电机 起动电机测试系统 PID神经网络 

分 类 号：TM306[电气工程—电机]