Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash

Abstract

The invention provides a soft measuring method based on an improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash. The soft measuring method is based on particle swarm optimization and carries out parameter optimization on support vector regression, two parameters affecting the validity of a regression model are selected, firstly, values of related auxiliary variables are collected by sensors and are subjected to data preprocessing, two main parameters of the support vector regression model are identified according to the history data in the past 6 hours in order to determine a soft measurement model for the unburned carbon content in fly ash, the soft measurement model is updated every hour according to the updated history data, and the real-time measured values of the auxiliary variables are inputted to the built soft measurement model, so that the output value of the unburned carbon content in fly ash is obtained. The soft measuring method can be used for measuring the unburned carbon content in fly ash generated in the combustion process of a boiler of a fire power plant in real time, the real-time measurement on the unburned carbon content in fly ash is realized, and meanwhile, the soft measuring method has the advantages of high precision, low calculation time consumption, wide application range and the like.

Description

technical field [0001] The invention relates to a method for measuring the carbon content of boiler fly ash, in particular to a soft measurement method for the carbon content of fly ash based on an improved support vector machine. Background technique [0002] The boiler is the combustion equipment of the thermal power plant. The safety and economy of boiler operation determine the safety and economy of the entire thermal power plant operation to a large extent. The carbon content in boiler flue gas is the basis for judging the quality of boiler operation and an important indicator for reducing coal consumption, as well as the basis for judging the quality of boiler combustion. The real-time monitoring of the carbon content of boiler fly ash is beneficial to adjust the combustion conditions in time, improve the control level of boiler combustion, thereby reducing the cost of power generation and improving the economy of the unit. If the online measurement of the carbon cont...

AI Technical Summary

Problems solved by technology

In order to solve the problem that the support vector machine is seriously affected by the learning parameters, someone proposed the support vector modeling combined with the optimization algorithm, and used the large-scale traversal search algorithm to optimize the parameters. This method consumes a lot of time and is not suitable for online modeling; Someone proposed support vector modeling based on least squares, which converts the optimization problem into the solution of linear equations, and its convergence speed is fast, but there is no clear method for determining the regularization parameter set and kernel parameter set, which is greatly affected by human factors

These existing improved support vector machine modeling methods have not clearly proposed the determination method of penalty coefficient and kernel parameter, which is seriously affected by human factors, and it is difficult to guarantee the measurement accuracy of the model

Images