A power station boiler no x Emission Dynamic Soft Sensing Method

Abstract

The invention discloses a NOx emission dynamic soft-sensing method for a power station boiler. The method comprises the steps of acquisition and preprocessing of data, initialization of a self-adaptive particle swarm algorithm and the like. According to the method, related operating and state parameters of a boiler combustion system serve as the input of a model, the nitrogen oxide emission concentration serves as the output of the model, historical operating data are selected as training samples, a support vector regression machine serves as a soft-sensing modeling tool, the idea of a non-linear auto-regression moving average model is combined, the orders of input variables and output variables of the model are considered, and therefore the soft-sensing model has the capability of describing the dynamic change process. By means of the method, the change of NOx emission in the boiler combustion dynamic operating process can be effectively traced and predicted, and the method has important significance on safe and optimized operation of the power station boiler.

Description

technical field [0001] The present invention relates to thermal technology and artificial intelligence interdisciplinary technical field, in particular to a power plant boiler NO x Soft-sensing method for emission dynamics. Background technique [0002] With the rapid development of my country's economy and power industry, the nitrogen oxides produced by coal-fired boilers in thermal power plants have become the main source of atmospheric nitrogen oxide pollution. In order to meet the increasingly stringent environmental protection requirements, the NOx of coal-fired units x Emission control puts forward higher requirements. Realize the power plant boiler NO x The premise of optimal emission control is to establish an effective NO x Emissions soft-sensing model. [0003] due to NO x The combustion products of coal are complex, and the boiler combustion system is also an extremely complex part of the power plant system, involving many input variables with strong nonlinea...

AI Technical Summary

Problems solved by technology

[0005] First: usually only consider the time series matching data of each measuring point as the input and output of the steady-state soft sensor model. However, most of the actual power plant boiler operation process is in a dynamic change. A certain state of the system output at the current moment is determined by It is determined by the input state of the previous period of time, not by the input state at a certain time point alone, that is, the delay characteristics of the combustion process are ignored;

[0006] Second: Since the steady-state soft-sensing model requires the system to remain in the steady-state working condition for a certain period of time to ensure the accuracy of the steady-state data, its applicability is limited to the steady-state working condition, and it lacks the knowledge of process dynamics. The description of the change characteristics, once the operating point changes or disturbance occurs in the boiler operation, the tracking ability of the steady-state soft sensor model will be greatly reduced;

[0007] Third: The steady-state operating conditions of power plant boilers are often difficult to meet, which also limits the application of the steady-state model

Images