Prediction of NOx emission of a power plant boiler based on adaptive simplified T-S model

zhao wenjie, Baohui Guo, Fuchang Chu, Yongjie Zhai


The combustion process of power plant boiler often has strong nonlinearity, uncertainty and time-varying nature. Offline models are often difficult to predict the emission of NOx accurately. In this paper, online identification method based on simplified T-S model for prediction of NOx emission is proposed. Firstly, the online subtractive clustering algorithm is used to determine the number of clusters and the clustering center adaptively. After obtaining the parameters, the recursive least squares algorithm is used to identify the parameters of each local model. Finally, the Mackey-Glass chaotic time series and field data of NOx emission of a power plant boiler are predicted by the above algorithm. The results show the effectiveness of the algorithm.

Full Text:



  • There are currently no refbacks.