基于线性回归的SCR脱销系统入口NO_X预测模型  

Forecast Models of Inlet NO_X Based on Linear Regression Prediction in SCR

作　　者：王欣峰[1] 白建云[1] 王琦[1] 

机构地区：[1]山西大学自动化系,山西太原030013

出　　处：《工业控制计算机》2017年第4期128-129,131,共3页Industrial Control Computer

摘　　要：分析影响SCR入口NO_X生成量的因素,并采样某运行电厂DCS数据,利用主成分分析法和多元线性回归预测法得到预测模型方程。通过拟合优度检验法对模型的精确度进行检验,经过检验证明该模型具有较高的拟合度,对制定喷氨量控制系统中的理论喷氨量具有一定的参考价值。This paper analyzes the influence factors of inlet NOx concentration,and sample the DCS data of some power plant,carrying out the forecast formulation through making use of principal components analysis and multiple linear regression prediction method.The accuracy of the model is tested by goodness of fit.The model has better fitness and some reference value of setting theory amount of injecting ammonia in the injecting ammonia control system.

关 键 词：主成分分析法 多元线性回归理论 拟合优度检验 

分 类 号：O212.4[理学—概率论与数理统计]