基于BP神经网络自整定PID恒温控制系统研究  

Study of Constant Temperature Control System Based on BP Neural Network Self-Turning PID

作　　者：刘冰艳 朱武 张佳民 LIU Bing-yan;ZHU Wu;ZHANG Jia-min(Academy of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Academy of Electronics and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力学院自动化工程学院,上海200090 [2]上海电力学院电子与信息工程学院,上海200090

出　　处：《仪表技术与传感器》2018年第8期52-55,共4页Instrument Technique and Sensor

基　　金：上海市教委科研创新重点项目(11ZZ173);上海市地方能力建设项目(15110500900)

摘　　要：针对传统PID热导传感器(TCD)系统控制参数不能在线实时调整的问题,设计了一种基于BP神经网络自整定PID的热导传感器恒温控制系统。该系统硬件上以C8051F060微控制器为主控制器,辅以热导信号的采集、放大、滤波以及温度闭环控制等外部电路,软件上以BP神经网络PID控制算法为核心,搭建了一个完整的热导传感器恒温控制系统。另外,该系统以热导传感器温度为直接控制对象对系统进行仿真分析与实验。实验结果表明,该系统提高了热导传感器温度控制精度,最终温度控制误差在±0.1℃的范围内,增强了系统稳定性及可靠性。In terms of the traditional PID thermal conductivity sensor(TCD)system,the real?time parameters cannot be ad?justed online.To solve this problem,a self?tuning PID thermal conductivity sensor constant temperature system based on BP neu?ral network was designed.The system took the C8051F060 micro controller as the main controller,supplemented by external cir?cuit,such as the collection,amplification,filtration and temperature closed?loop control of the thermal conductivity signal.Addi?tionally,the BP neural network and PID control algorithm was used as the core of software to build a thermal conductivity sensor temperature control system.In this paper,the temperature of the TCD was taken as the direct control target for the simulation a?nalysis and experiment.The result shows that the system can improve the temperature control accuracy of the TCD.The final tem?perature deviation is controlled in the range of±0.1℃,which enhances stability and reliability of the system.

关 键 词：热导传感器 恒温系统 PID控制 BP神经网络 温度 控制精度 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]