改进GWO-BP算法优化PID在配药系统中的应用  

Application of the improved GWO-BP algorithm to optimize the simulation application of PID simulation in pharmaceutical dispensing system

作　　者：孙宏昌[1,2] 李超[1,2] 何婉凌 郝远辉 焦宇泽 SUN Hongchang;LI Chao;HE Wanling;HAO Yuanhui;JIAO Yuze(Institute of Robotics and Intelligent Equipment,Tianjin University of Technology and Education,Tianjin 300222,China;Tianjin Key Laboratory of Intelligent Robot Technology and Application Enterprises,Tianjin University of Technology and Education,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学机器人及智能装备研究院,天津300222 [2]天津职业技术师范大学天津市智能机器人技术及应用企业重点实验室,天津300222

出　　处：《天津职业技术师范大学学报》2023年第2期42-47,共6页Journal of Tianjin University of Technology and Education

基　　金：全国职业教师教学创新团队建设体系化课题(TX20200104);天津市津南区“揭榜挂帅”科研计划项目(ZZJ0012210).

摘　　要：针对PID控制器对配药系统控制过程中常出现不稳定和跃进等现象导致配药浓度误差过大的问题,提出改进的GWO-BP算法优化PID控制器参数在配药系统控制中的仿真应用方案。对于灰狼优化算法在全局寻优能力不足、收敛精度不高和收敛速度不够快等问题,利用改进非线性收敛因子以及改进学习因子来改变位置更新公式,进而改进灰狼优化算法收敛速率,提高寻优能力;利用改进GWO-BP算法优化PID控制器参数解决在实际工程应用中存在鲁棒性低难以得到最优的PID控制器参数等问题。仿真结果显示:IGWO-BP-PID控制器超调量从原来的23.0%降低到10.6%,调节时间从0.76 s减少到0.17 s,峰值时间从0.22 s减少到0.06 s。IGWO-BP-PID控制器的控制效果更优、稳定性更好。The instability and leapfrogging in the control process of the PID controller for the dispensing system often lead to large errors in the dispensing concentration.To address the problem,a solution is proposed to improve the GWO-BP algorithm to optimize the application of PID in the control of the dispensing system.To address the problems of insufficient global optimization capability,low convergence accuracy and insufficient convergence speed in the gray wolf optimization algorithm,the improved nonlinear convergence factor and improved learning factor are applied to change the position update formula and thus improve the convergence rate of the gray wolf optimization algorithm and improve the optimization capability.The improved GWO-BP algorithm is used to optimize the PID controller parameters,which has problems such as low robustness and difficulty in obtaining the optimal PID controller parameters in the actual engineering application process,and the stable and optimal PID control parameters are obtained and applied to the pharmaceutical dispensing system.The simulation results show that IGWO-BP-PID controller optimizes the overregulation from the original 23.0%to 10.6%,the adjustment time from 0.76 s to 0.17 s,the peak time from 0.22 s to 0.06 s,the IGWO-BP-PID controller has better control effect and better stability.

关 键 词：灰狼优化算法 BP神经网络 PID参数优化 配药系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]