Desulfurization system multi-working-condition prediction method based on extreme learning machine

Abstract

The invention provides a desulfurization system multi-working-condition prediction method based on an extreme learning machine, and the method comprises the steps: obtaining the historical data of the operation parameters of a thermal power plant boiler and a desulfurization system, carrying out the working condition classification according to the feature parameters of six flag bits, and determining a corresponding working condition training data set; for the training data set, based on a Bayesian algorithm, establishing classification models of different working conditions, and selecting a proper modeling sample set; estimating the delay time of a variable by using a Pearson coefficient, and recombining modeling data through the delay time; establishing SO2 prediction models under different marking conditions based on an extreme learning machine algorithm by using the recombined data set; and inputting the real-time data of the system into the classification model, judging the real-time working condition category of the system, and predicting the SO2 emission concentration by adopting a corresponding prediction model. According to the method, on the premise that the delay time influence is reduced, the current working condition of the system is judged based on the boiler operation data, different working condition prediction models are switched, and the prediction efficiency and precision of outlet SO2 are improved.

Description

technical field [0001] The invention relates to the technical field of computer modeling and prediction, in particular but not limited to a method for predicting multiple operating conditions of a desulfurization system based on an extreme learning machine. Background technique [0002] With the increasingly prominent environmental problems, under China's strict environmental protection policy of sulfur dioxide emission control, Flue Gas Desulfurization (FGD) has been widely used in thermal power plants, which has greatly reduced the emissions of air pollutants from power plants in my country. , improving the environment. [0003] Since the desulfurization process presents the characteristics of multiple working conditions and large hysteresis, the parameter values ​​recorded by the distributed control system (DCS) at the current moment cannot accurately predict the concentration of SO2 in the net flue gas, so the delay of key parameters in the system The time and the workin...

AI Technical Summary

Problems solved by technology

[0005] Aiming at one or more problems in the prior art, the present invention proposes a multi-working condition prediction method for desulfurization system based on extreme learning machine to solve the situation of variable working conditions and large hysteresis in the wet desulfurization system of thermal power plants , it is impossible to accurately predict the export SO 2 concentration problem

Images