Prediction Method of NOx from Power Station Boilers Based on Neural Network

Abstract

In the coal-fired power generation system, it is necessary to predict the NOx emissions of power station boilers when it comes to the step to spray ammonia to ensure that NOx emissions do not exceed national standards. Using traditional machine learning algorithms in the modeling of power station boilers will require features selection and steady-state extraction, which is not suitable for practical applications. In order to reduce the NOx prediction error rate under variable operating conditions, a multi-model fusion algorithm S3LX combined with linear regression, XGBoost, and long-short-term memory recurrent neural network is proposed to model the NOx emission prediction of power station boilers. The preprocessing data scheme suitable for power station boiler data sets is proposed and implemented in this paper, which can perform numerical processing, data cleaning and data standardization for boiler’s data and features. A 7-day historical operating data set of a unit in Guangzhou Shajiao C Power Plant was used as the training set and test set and was used to build the NOx emission prediction model after data preprocessing. Results show that compared with traditional machine learning algorithms, S3LX has good prediction ability under varying conditions with an average error of 4.28%. Compared with the average prediction error of the multi-layer perceptron 9.16%, SVM 7.37%, S3LX makes the error significantly reduced and satisfies the actual engineering demand.