基于强化学习的化学发光免疫分析仪温度控制策略研究  

作　　者：李中伟 乔美英[1] 王聪 

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454003 [2]安图实验仪器(郑州)有限公司,郑州450016

出　　处：《科技创新与应用》2024年第13期39-43,共5页Technology Innovation and Application

摘　　要：传统PID控制作为最常用的控制算法,在全自动化学发光免疫分析仪的温度控制单元上有着广泛的应用,但存在PID控制参数整定困难,调节时间长和超调量较大等问题,如何在保证温度控制精度的情况下,缩短温度调节时间,减小超调量,进一步提升仪器的检验效率,成为需要解决的问题。针对此问题,应用基于深度确定性策略梯度(Deep Deterministic Policy Gradient,DDPG)的温度控制策略,可以避免依靠人工经验进行PID参数整定,并缩短温度调节时间,大幅度减小超调量,通过仿真实验分析温度控制的参数指标。结果表明,该算法相较于传统的PID控制和模糊PID控制策略,在调节时间上分别提升14.9%和6.3%,在超调量上分别提升99.8%和99.2%,对于提升仪器的性能有较大意义。Traditional PID control,as the most commonly used control algorithm,has a wide range of applications in the temperature control unit of fully automatic chemiluminescence immunoassay analyzer.However,there are problems such as difficulty in tuning PID control parameters,long adjustment time,and large overshoot.How to shorten temperature adjustment time,reduce overshoot,and further improve instrument inspection efficiency while ensuring temperature control accuracy has become a problem that needs to be solved,To address this issue,a temperature control algorithm based on Deep Deterministic Policy Gradient(DDPG)is applied,which can avoid relying on manual experience for PID parameter tuning,shorten temperature adjustment time,and significantly reduce overshoot.By analyzing the parameter indicators of temperature control through simulation experiments,the results show that this algorithm is superior to traditional PID control and fuzzy PID control algorithms,In terms of adjustment time,it has increased by 14.9%and 6.3%respectively,and in terms of overshoot,it has increased by 99.8%and 99.2%respectively,which is of great significance for improving the performance of the instrument.

关 键 词：发光免疫分析仪 温度控制 PID DDPG 强化学习 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]