Boiler combustion efficiency predicting method based on support vector machine incremental algorithm

Abstract

The invention discloses a boiler combustion efficiency predicting method based on a support vector machine incremental algorithm. The boiler combustion efficiency predicting method based on the support vector machine incremental algorithm is characterized by including the following steps: (1) a kernel function is selected; (2) an initial data set is formed; (3) the initial data is pre-treated; (4) a training sample is taken out and tested; (5) a sensitivity coefficient Epsilon is 0.0001, a training precision is 0.00001 and the default values of a penalty coefficient C and a width coefficient sigmate Sigma are respectively 10 and 0.0001; (6) generalization is determined; (7) the optimum coefficient pair is selected; (8) an initial classifier Omega 0, a support vector set and a non-support vector set are obtained through training; (9) sample points which are not in line with a generalized karush-kuhn-tucker (KKT) condition, namely yif (xi)>1 are found out in a newly added sample set X1; (10) a new set is formed; (11) in terms of X, a classifier Omega and a support vector SV are determined; (12) a support vector machine predicting model on boiler combustion efficiency is established. Less input coefficients are input so as to facilitate measuring, a complicated calculation process is removed, training time of working conditions of boiler combustion is shortened, a requirement for online calculation of a distributed control system (DCS) is met and prediction precision is high.

Description

technical field [0001] The invention relates to a method for predicting boiler combustion efficiency, in particular to a method for predicting boiler combustion efficiency based on a support vector machine incremental algorithm. Background technique [0002] Improving boiler operating efficiency is the main goal of thermal power plants to achieve energy saving and emission reduction. The combustion mechanism of boilers is complex, with strong nonlinearity and diversity, and it is difficult to directly measure the combustion efficiency. At present, the main measurement methods used are numerical simulation measurement and artificial intelligence algorithm measurement. Different numerical simulations may have different emphases, but numerical simulation methods have common characteristics: large amount of calculation, long time-consuming, and it is difficult to establish an accurate and perfect combustion efficiency measurement method when the mechanism is not very clear, so t...

AI Technical Summary

Problems solved by technology

However, there are still the following problems to be solved by using neural network measurement: ① Neural network measurement requires a large number of samples, while the number of real furnace test conditions is often limited; ② The training time of neural network is long, and it is difficult to realize online training. The online linearity of the combustion efficiency measurement is limited; ③ the neural network is sensitive to the incompleteness and error of the data sample; ④ the neural network also has the problem of overfitting (overnt), and the generalization ability is poor

Images