基于GA-BP神经网络控制的电热型流量调节阀  

Control for Electro-thermal Flow Control Valve Based on GA-BP Neural Network

作　　者：郭林嘉 杨彪[1,2] 王世礼[1] GUO Lin-jia;YANG Biao;WANG Shi-li(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Key Laboratory of Unconventional Metallurgy,Ministry of Education,Kunming University of Science and Technology,Kunming 650093,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500 [2]昆明理工大学教育部非常规冶金重点实验室,云南昆明650093

出　　处：《软件导刊》2018年第6期150-152,156,共4页Software Guide

基　　金：云南省应用基础研究计划项目(2014FD009);昆明理工大学引进人才科研启动基金项目(KKSY201503006)

摘　　要：针对供暖系统在实际运用中为一个滞后过程,难以保证其供暖介质流量控制精度的问题,利用感温石蜡的热胀冷缩效应作为电热型流量调节阀执行结构的动力源,获取石蜡温度与流量之间的关系,提出基于遗传算法的BP神经网络(GA-BP)方法。首先获取供暖系统温度,通过电热器加热石蜡得到其温度变化量与流量,然后应用GA-BP神经网络方法,对流量进行预测。通过与3次B样条函数递推最小二乘法、BP神经网络法对流量的预测结果对比试验验证,预测值和真实值的最大绝对误差分别为0.19、0.35、0.87,且均能满足实际应用的控制周期。结果表明,GA-BP神经网络对流量的控制更为精确。Aiming at the problem that it is difficult to ensure control precision of the heating medium flow because the heating system is a big lag processin practice,we utilize the thermal expansion and contraction effect of temperature sensing paraffin as the executive power for electro-thermal flow control valve structure to verify the relationship between parafin temperature and the flow rate.The GA-BP neural network method is proposed.Firstly the temperature of the heating system is obtained,and then paraffin is heated by the electro-thermal heater to obtain paraffin temperature change and flow rate;secondly the flow rate is predicted by GA-BP neural network.By comparison with the cubic B-spline function recursive least squares method and BP neural network method,the maximum absolute error between the predicted value and the true value is 0.19,0.35,and 0.87 respectively,which can meet the control period of practical application,the experimental results show that the flow controlled by the GA-BP neural network has better accuracy in flow control.to predict the flow by adopting the temperature variation.

关 键 词：电热型流量调节阀 智能控制 GA-BP神经网络法 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]