Boiler NOx prediction method based on MI-LSTM

Abstract

The invention discloses a boiler NOx prediction method based on MI-LSTM. The method comprises: ranking the importance of auxiliary variables and selecting variables by using mutual information (MI) "minimum redundancy maximum correlation" as a criterion; using a selected auxiliary variable set as an input of a long short term memory (LSTM) model; establishing an MI-LSTM model for NOx emission prediction, and searching for an optimal parameter for the LSTM model by using multilayer grids. In the process of variable selection, a sequence forward selection method is used to determine the optimalinput feature set and the optimal model parameter with the model prediction accuracy as a goal, thereby effectively reducing the information redundancy between the input variables, reducing the modelcomplexity, and improving the prediction accuracy and generalization capability of the model.

Description

technical field [0001] The invention belongs to the technical field of combustion control, and in particular relates to a MI-LSTM-based boiler NO x method of prediction. Background technique [0002] NO produced during coal combustion x It is an important source of air pollutants and seriously affects human health and air quality. In 2011, the Ministry of Environmental Protection promulgated new pollutant emission standards, requiring coal-fired boilers to x Emission does not exceed 100mg / m 3 . Restrictions on nitrogen oxide emissions will become more and more stringent. In order to meet emission standards, thermal power plants need to control NOx x Emissions are monitored and controlled in real time. However, the existing measurement equipment cannot achieve real-time measurement of NO x requirements, and monitoring is difficult. To this end, establish an effective NO x Emission prediction model, for NO x Efficient and rapid monitoring of concentration is necessar...

AI Technical Summary

Problems solved by technology

However, in the actual modeling process, NO x The generation mechanism is complex and affected by multiple variables, the selection of auxiliary variables will directly affect the prediction accuracy of the model

Multiple selection of auxiliary variables will take more time for feature analysis and model training, and may also lead to the "curse of dimensionality", making the model overly complex and reducing its generalization ability; while few or missing variables will make the model inaccurate

Images