Flue gas NOx prediction method and system based on multi-delay characteristic multivariable correction

Abstract

The embodiment of the invention provides a flue gas NOx prediction method and system based on multi-delay characteristic multivariable correction. The flue gas NOx prediction method comprises the steps: obtaining and cleaning production operation data stored in a thermal power plant in real time, and reserving target characteristic data and other data; according to the production operation data of the variable parameters and the target characteristic data, respectively constructing a delay characteristic model of each variable parameter, a variable parameter corresponding to each delay characteristic model, and a corresponding boundary condition; extracting production operation data required for constructing the delay characteristic model to serve as a built prediction model; dividing the cleaned production operation data into different samples according to working conditions, establishing a regression model of all variable parameters and target characteristics according to the different production operation data samples, and training the regression model to obtain a NOx prediction model; and predicting the NOx concentration of the flue gas at the outlet of the denitration system through the NOx prediction model. High-precision modeling is achieved for multi-delay characteristic quantification, and the prediction efficiency of the NOx concentration of the flue gas at the outlet of the denitration system is improved.

Description

technical field [0001] The invention relates to a thermal power plant, in particular to a flue gas NOx prediction method and system based on multi-delay characteristics and multi-variable correction. Background technique [0002] Nitrogen oxides are one of the main pollutant emissions from thermal power plants, and one of the national total pollutant control objects. In recent years, in order to meet the emission requirements stipulated by the state, coal-fired units have generally undergone ultra-low emission transformation, and the selective catalytic reduction flue gas denitrification system has been widely used in thermal power plants. While suppressing the emission of nitrogen oxides, due to the excessive discharge of pollutants, it will face serious national assessments. Too low control of nitrogen oxides will not only cause more production costs (ammonia input, etc.), but also cause ammonium bisulfate blockage Air preheater risk. Therefore, since the transformation ...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the applicant found that there are at least the following problems in the prior art: the current PID control strategy design is too simple, only considers the static characteristics of the object, lacks an adaptive mechanism, and cannot meet the requirements of coal quality and coal mill operation mode. Adjustment requirements under the change of multiple parameters such as wind-to-coal ratio

Images