Thermal power plant boiler NOx emission modeling variable selection method

Abstract

The invention discloses a thermal power plant boiler NOx emission modeling variable selection method. Whether the accuracy and the generalization ability of a model are affected or not is judged through variable selection. Aiming at the problem of variable selection, the maximum information coefficient variable selection method is provided by combining with the maximum information coefficient on the basis of the mutual information variable selection method, the maximum information coefficient is introduced to improve the original variable selection method, and the effectiveness of the method is verified by using the experimental data set of the nominal model.

Description

technical field [0001] The invention relates to the technical field of NOx emissions of thermal power plant boilers, in particular to a variable selection method for modeling NOx emissions of thermal power plant boilers. Background technique [0002] The hysteresis of NOx measuring instruments in power plants leads to inaccurate SCR denitrification control, and it is necessary to model and predict boiler NOx emissions; the mathematical model of boiler NOx emissions is the basis for NOx emission optimization. [0003] In the power industry, due to the complex on-site environment and many related variables, the noise is relatively obvious. If there is no effective method for variable selection, data modeling errors will occur, and the system cannot be accurately described and predicted. Whether the variable selection is accurate affects the accuracy and generalization ability of the model. Missing variables will cause the model to be unable to accurately describe the character...

AI Technical Summary

Problems solved by technology

[0002] The hysteresis of NOx measuring instruments in power plants leads to inaccurate SCR denitrification control, and it is necessary to model and estimate boiler NOx emissions; the mathematical model of boiler NOx emissions is the basis for NOx emission optimization

[0003] In the power industry, due to the complex on-site environment and many related variables, the noise is relatively obvious. If there is no effective method for variable selection, data modeling errors will occur, and the system cannot be accurately described and predicted.

Whether the variable selection is accurate affects the accuracy and generalization ability of the model. Missing variables will cause the model to be unable to accurately describe the characteristics of the modeling object, and too many variables will increase the complexity of the model and affect the generalization ability of the model.

Images