基于数据驱动的燃煤锅炉NO_(x)排放浓度动态修正预测模型

Data Driven based Dynamic Correction Prediction Model for NO_(x) Emission of Coal Fired Boiler

NO_(x)浓度实时预测对于燃煤电厂污染物排放控制和机组运行具有重要意义。为了克服燃烧过程大时延及强非线性特性,提出一种考虑时间延迟的动态修正预测模型。利用最大信息系数(maximum information coefficient MIC)计算相关参数与NO_(x)浓度的延迟时间,重构建模数据集;然后,构建基于Lasso和ReliefF的自适应特征选择算法,筛选与NO_(x)浓度相关程度高的参数;最后,建立结合误差校正的极限学习机(extreme learning machine,ELM)模型,达到动态预测氮氧化物浓度的目的。基于实际数据的实验结果表明:相同变量在升、降、平稳等负荷工况下的延迟时间不同;且不同负荷工况下模型特征变量存在差异;动态误差校正策略有效提升建模精度;所提出算法在不同工况下的预测误差均小于2%,能够准确预测燃烧出口的NO_(x)浓度,为NO_(x)排放监测和燃烧过程优化提供指导。

The real-time prediction of NO_(x) emissions is of great significance for pollutant emission control and unit operation of coal-fired power plants.Aiming at dealing with the large time delay and strong nonlinear characteristics of the combustion process,a dynamic correction prediction model considering the time delay was proposed.First,the maximum information coefficient(MIC) was used to calculate the delay time between related parameters and NO_(x) emissions,and the modeling data set was reconstructed.Then,an adaptive feature selection algorithm based on Lasso and ReliefF was constructed to filter out the high correlation with NO_(x) emissions.Finally,an extreme learning machine(ELM) model combined with error correction was established to achieve the purpose of dynamically predicting the concentration of nitrogen oxides.ExpNO_(x) erimental results based on actual data show that the same variable has different delay time under load conditions such as rising,falling,and steady;and there are differences in model characteristic variables under different load conditions.The dynamic error correction strategies effectively improve modeling accuracy.The prediction error of the algorithm under different working conditions is less than 2%,which can accurately predict the NO_(x) concentration at the combustion outlet,and provide guidance for NO_(x) emission monitoring and combustion process optimization.