|本期目录/Table of Contents|

[1]刘石红,党超亮,王能才.基于PID神经元网络的智能车舵机控制系统研究[J].工业仪表与自动化装置,2014,(06):97-101.
　LIU Shihong,DANG Chaoliang,WANG Nengcai.Study of intelligent vehicle servo control system based on PID neuron network[J].Industrial Instrumentation & Automation,2014,(06):97-101.
点击复制

基于PID神经元网络的智能车舵机控制系统研究(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2014年06期
页码:
97-101
栏目:
出版日期:
2014-12-15

文章信息/Info

Title:
Study of intelligent vehicle servo control system based on PID neuron network
作者:
刘石红1; 党超亮2; 王能才2
（1. 兰州石化职业技术学院 电子电气工程系，兰州 7300501；2. 兰州理工大学 电气工程与信息工程学院，兰州 730050）
Author(s):
LIU Shihong1;  DANG Chaoliang2;  WANG Nengcai2
(1. Lanzhou Petrochemical College of Vocationat Technology, Lanzhou 730060,China；2. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China)
关键词:
电磁导航智能车; 舵机控制; PID神经元网
Keywords:
electromagnetic navigation intelligent vehicle;  servo control; PID neural network
分类号:
TP249
DOI:
-
文献标志码:
A
摘要:
针对传统PID控制算法在电磁导航智能车舵机偏差处理中存在比例、积分、微分参数一经确定，不能在线调整、不具有自适应能力的缺点，提出了将PID神经元网络（PIDNN）控制器及其算法应用到智能车的舵机控制系统中来对传统PID控制进行改进。PIDNN控制系统不依赖智能车舵机的数学模型，能够根据控制效果在线训练和学习，调整网络连接权重值，最终使系统的目标函数达到最小来实现智能车的舵机控制。仿真测试表明，PIDNN控制系统的响应快，无超调、无静差，与传统PID控制算法相比，大大提高了智能车舵机控制系统的性能。
Abstract:
In the intelligent vehicle steering deviation, the traditional PID control parameters of proportional, integral, differential algorithm is confirmed, can’t adjust online, do not have adaptive ability, put forward the PID neural network (PIDNN) controller and its algorithm should be used in the servo control system of intelligent vehicle to improve the traditional PID control. PIDNN does not dependents on the mathematical model of the control system of the smart car servo, according to the control effect of online training and learning, adjusts the network connection weights, and makes the objective function of control system reached the minimum value to realize the intelligent vehicle servo control. Matlab simulation tests show that the PIDNN control system has merits of fast response, no overshoot, and no steady-state error. compared with the traditional PID control algorithm, greatly improves the performance of the intelligent vehicle servo control system

参考文献/References:

[1] 刘源,张文斌,刘雪扬,等.电磁导航智能车检测和控制系统研究[J].传感器与微系统,2012,31(4):63-66.[2] 韩启勇,王蕊.模糊PID控制器MATLAB仿真探讨[J].中国仪器仪表,2009,12:78-81.[3] Bo XIONG, Shiru QU. Intelligent Vehicle’s Path Tracking Based on Fuzzy Control[J].IEEE Transportation Systems Engineering and Information Technology, 2010,10(2): 70-75.[4] 袁朝辉,张慧.多温区电加热炉的PID神经网络控制[J]. 计算机仿真,2010,27(12):176-185.[5] 袁佑新,卢立殊,王萍,等.基于PID神经元的温度控制系统研究[J].武汉理工大学学报,2002,24(3):21-23.[6] 钱宇达,朱凌云,赵玮娜,等.基于PID神经网络的恒压供水控制系统设计[J].仪表技术,2008(10):15-17.[7] 汤积仁,雷玉勇,聂光伟,等.神经网络PID控制在柴油机调速系统中的应用[J].煤矿机械2010,31(01):201-204.[8] 卢萍,金朝永.基于PID神经元网络的研究和改进[J].自动化仪表,2012,33(8):51-54.

相似文献/References:

备注/Memo

备注/Memo:
-
更新日期/Last Update: 1900-01-01