基于变量选择的深度置信神经网络锅炉烟气NOx排放预测  

Prediction ofNOx emission from boiler based on DBN with variable selection

作　　者：杨国田[1] 王英男 谢锐彪 刘凯 YANG Guotian;WANG Yingnan;XIE Ruibiao;LIU Kai(School of Control and Computer Engmeering,North China Electric Power University,Beijing 102206,China)

机构地区：[1]华北电力大学控制与计算机工程学院,北京102206

出　　处：《热力发电》2020年第4期34-40,共7页Thermal Power Generation

基　　金：中央高校基本科研业务费专项资金资助(2018QN052)。

摘　　要：准确预测NOx排放量有利于降低选择性催化还原(SCR)烟气脱硝成本,优化锅炉燃烧过程。本文利用偏最小二乘法(PLS)对燃煤锅炉实际数据进行变量重要性投影分析,得到变量重要性投影指标Vip,以Vip为依据对原始变量进行排序,将20项最优变量子集作为深度置信神经网络(DBN)的输入,得到NOx排放预测的PLS-DBN模型,并将PLS-DBN模型与最小二乘支持向量机(LSSVM)、DBN、误差反向传播神经网络(BPNN)模型用于某660 MW机组锅炉的3000组训练集及500组预测集进行测试对比。结果表明:PLS-DBN模型训练集和测试集的预测误差均较小,且在训练集和测试集上均方根误差不大于2%的预测准确率分别为0.940和0.714,预测准确率最高;表明PLS-DBN模型比其他3种NOx预测模型具有更高的预测精度和模型泛化能力。Accurately predicting NOx emission is conducive to reducing the cost of SCR flue gasdenitration and optimizing the coal combustion process. This paper uses partial least squares(PLS) method to carry out variable importance projection(Vip) analysis on the raw data of coal-fired boilers. Based on Vip, the raw variables are ranked, and the optimal 20 variable subsets are used as the input of deep belief networks(DBN), and finally the PLS-DBN model for NOx emission prediction is obtained. The PLS-DBN model and the least square supportive vector model(LSSVM), DBN and error back propagation neural network(BPNN) model are applied in 3 000 groups of training set and 500 groups of test sets of a 660 MW unit boiler. The results show that, the prediction error of training set and test set of the PLS-DBN model is both small, and the prediction accuracy of root-mean-square error of not more than 2% on the training set and test set is 0.940 and 0.714, respectively, which is the highest, indicating the PLSDBN model has higher prediction accuracy and stronger model generalization ability than other three conventional NOx prediction models.

关 键 词：燃煤锅炉 NOX排放 深度置信神经网络 受限玻尔兹曼机 偏最小二乘法 变量选择 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]