基于IGWO的台车轮注油系统注油量控制方法研究  

Research on the Control Method of Sintering Machine Table Wheel Oiling Quantity Based on IGWO

作　　者：李洪涛 库涛[2,3,4] 王二林 刘金鑫[2,3,4] 林乐新[2,3,4] LI Hongtao;KU Tao;WANG Erlin;LIU Jinxin;LIN Lexin(School of Mechanical Engineering,Shenyang University of Technology,Shenyang Liaoning 110870,China;Key Laboratory of Networked Control Systems,Chinese Academy of Sciences,Shenyang Liaoning 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang Liaoning 110169,China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang Liaoning 110016,China;Beijing Shougang Co.,Ltd.,Qianan Hebei 064404,China)

机构地区：[1]沈阳工业大学机械工程学院,辽宁沈阳110870 [2]中国科学院网络化控制系统重点实验室,辽宁沈阳110016 [3]中国科学院机器人与智能制造创新研究院,辽宁沈阳110069 [4]中国科学院沈阳自动化研究所,辽宁沈阳110016 [5]北京首钢股份有限公司,河北迁安064404

出　　处：《机床与液压》2023年第22期67-71,共5页Machine Tool & Hydraulics

基　　金：国家重点研发计划(2020YFB1708503)。

摘　　要：传统烧结机台车轮自动注油系统注油量控制存在控制精度低和鲁棒性差等问题,已经无法满足精确注油的需求。为改善注油性能,提出一种基于改进灰狼(IGWO)算法的烧结机台车轮注油量智能控制方法。利用MATLAB软件辨识注油量控制系统数学模型;搭建BP神经网络PID注油量控制系统;为了提高灰狼算法的收敛速度,引入非线性收敛因子和动态权重,设计IGWO算法实现对BP神经网络的最优初始值及阈值的寻优,输出最优PID控制参数;最后,在仿真环境下,将用IGWO算法优化前后的控制效果进行对比。结果表明:所设计的PID控制器超调小、控制精度高,能够实现注油量的智能控制,满足精确注油的需求。Oiling quantity control of the traditional sintering machine table wheels oiling system has problems such as low control accuracy and poor robustness,which can no longer meet the demand for accurate oiling.In order to improve the oiling performance,an intelligent control method of sintering machine table wheels oiling quantity based on the improved grey wolf algorithm(IGWO)was pro⁃posed.MATLAB software was used to identify the mathematical model of the oiling quantity control system;then,a BP neural network PID oiling quantity control system was built.In order to improve the convergence speed of the grey wolf algorithm,a non-linear con⁃vergence factor and dynamic weights were introduced,and the IGWO algorithm was designed to realize the optimal initial values and thresholds of the BP neural network,and the optimal PID control parameters were output.Finally,the control effects before and after optimization with the IGWO algorithm were compared in simulation environment.The research results show that the designed PID con⁃troller has low overshoot and high control accuracy,which can realize the intelligent control of oiling quantity and meet the demand of precise oiling.

关 键 词：烧结机台车轮 BP神经网络 改进灰狼算法 PID控制 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]