基于PCA-RF直流炉中间点温度预测控制  

Based on PCA-RF DC Furnace Temperature Prediction Control

作　　者：梁伟平[1] 鲍鹏凯 Liang Weiping;Bao Pengkai(School of Control and Computer Engineering,North China Electric Power University,Hebei,Baoding,071003,China)

机构地区：[1]华北电力大学控制与计算机工程学院,河北保定071003

出　　处：《仪器仪表用户》2021年第7期86-89,79,共5页Instrumentation

摘　　要：针对直流炉中间点温度难预测的问题,提出了一种基于PCA(主成分分析)-RF(随机森林)的直流锅炉中间点温度预测的方法。基于某电厂的一段DCS系统运行数据,通过数据预处理采集到与之相关的8个因素,以预测的相对误差为评价指标,构建了PCA-RF预测模型,预测了直流锅炉中间点温度,同时与其它预测模型的仿真曲线对比,结果表明该模型的预测精度高一些,对于中间点温度的预测具有一定的有效性。Aimed at the forecast problem of the intermediate point temperature is difficult to dc furnace,this paper proposes a based on PCA(principal component analysis(PCA)-RF(random forests))dc boiler intermediate point temperature prediction method,based on a DCS system operation data of a certain power plant,through collecting data preprocessing to associated with eight factors,to predict the relative error as the evaluation index,The PCA-RF prediction model is built to predict the temperature of the intermediate point of the boiler.At the same time,compared with the simulation curves of other prediction models,the results show that the prediction accuracy of the model is higher and the prediction of the temperature of the intermediate point is effective to a certain degree.

关 键 词：直流锅炉 中间点温度 PCA(主成分分析) RF(随机森林) 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]