Coal ash sintering temperature prediction method based on principal component regression

Abstract

The invention discloses a coal ash sintering temperature prediction method based on principal component regression. The method comprises the following steps: 1) collecting historical data of a coal ash sintering test; (2) variables are selected by adopting a useless information variable elimination method, variables of useless information on the coal ash sintering temperature are removed, the influence of irrelevant information on a prediction model is reduced, the prediction precision of the model is improved, and in addition, the operation efficiency is improved while the number of the variables is reduced; 3) establishing a principal component regression model, taking the coal quality test data as an input variable of the model, taking the coal ash sintering temperature as an output variable of the model, establishing a one-to-one correspondence mapping relationship between the two variables, and establishing the principal component regression model by utilizing the obtained optimal principal component number, and 4) substituting coal quality test data into the model to obtain a predicted value. According to the method, the prediction model is established according to coal type total analysis data and coal ash component analysis data, and the initial sintering temperature of other coal ashes is predicted.

Description

technical field [0001] The invention belongs to a method for predicting coal ash sintering temperature of power coal slagging and contamination characteristic index, specifically a method for predicting coal ash sintering temperature based on principal component regression. Background technique [0002] Boiler slagging and contamination affect the economy, environmental protection and safety of boiler operation, seriously affect the normal operation of the boiler, and even cause safety production accidents. The current indicators for judging boiler slagging and fouling include ash melting point, slagging index, alkali metal content, fouling index, coal ash sintering temperature, etc. efficient. [0003] The initial sintering temperature of coal ash is used to characterize the strength and weakness of coal ash contamination on the convective heating surface of the boiler, and the initial sintering temperature ts value of coal ash is used to judge the contamination characteri...

AI Technical Summary

Problems solved by technology

[0005] Scholars have conducted a lot of research on the application of multivariate statistical methods in the actual production process. At present, the commonly used methods include BP neural network in building models and multivariate statistical regression. BP neural network is widely used, but the historical data of this prediction model test The amount is small, and the prediction accuracy is poor when using the BP neural network isotype for prediction

Images