基于改进灰色预测单神经元PID的URV伺服控制系统研究  

Research on URV Servo Control System Based on Improved Grey Prediction Single Neuron PID

作　　者：王永涛 肖俊辰 WANG Yongtao;XIAO Junchen(Chongqing Vocational Institute of Safety and Technology,Chongqing 404000,China;School of Computer Science and Technology,Wuhan University of Technology,Wuhan 421000,China)

机构地区：[1]重庆安全技术职业学院,重庆404020 [2]武汉理工大学计算机科学与技术学院,武汉421000

出　　处：《兵器装备工程学报》2021年第8期251-257,共7页Journal of Ordnance Equipment Engineering

基　　金：教育部科技发展中心教学改革基金项目(2018B02003)。

摘　　要：无人侦察车伺服控制系统模型很难准确建立,且传统的PID控制误差大、精度低,难以满足实际要求,提出一种序列-残差联合灰色预测单神经元PID控制器的设计方案。单神经元PID控制具有较强的自学习和自适应能力,能够提高系统的鲁棒性;变论域模糊控制则实现其模糊规则的自适应调整,动态调整控制器参数,实现算法增益;建立序列-残差联合灰色预测模型,通过对预测残差的二次预测修正,取代测量结果进行控制运算,实现对控制系统的快速、精准控制。仿真结果表明:改进灰色预测单神经元PID的无人侦察车伺服控制系统较传统的PID控制具有优良的动、静态性能指标和抗扰动能力。In view of the nonlinearity of the servo control system of unmanned reconnaissance vehicle,it is difficult to establish its model accurately,and the traditional PID control error is large and the precision is low,which is difficult to meet the actual performance requirements.In order to improve the performance of the system,an improved Grey prediction single neuron PID controller was proposed,which is the sequence residual joint Grey prediction single neuron PID controller.Single neuron PID control has strong self-learning and self-adaptive ability,which can improve the robustness of the system;fuzzy control can realize the self-regulation of algorithm gain;the sequence residual joint Grey prediction model was established to modify the prediction results by the second prediction of the predicted residual error,and it replaced the measurement results for control operation,so as to realize the fast and accurate control of the control system.The simulation results show that the improved Grey prediction single neuron PID control system has better dynamic and static performance indexes and anti disturbance ability than the traditional PID control.

关 键 词：无人侦察车 灰色预测 序列-残差 单神经元PID控制 变论域 模糊控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]