A novel method for the prediction of three-dimensional (3D) spatial distribution of NOx in a furnace is proposed and evaluated. Computational fluid dynamics (CFD) simulations are conducted to generate the data sets of 3D NOx spatial distribution. The data sets are partitioned based on NOx generation mechanisms to improve the model accuracy. Combining the Pearson coefficient and mutual information (PMI), the model input variables are optimized by feature selection. The prediction model of 3D NOx spatial distribution in the furnace is established based on extreme learning machine (ELM). The experiments are conducted considering a 350 MW coal-fired boiler with a change in the burner tilt angles under a rated load. The experimental results show that the data-driven method based on PMI-ELM can realize the rapid prediction of the 3D spatial distribution of NOx in the furnace with 12.84% mean absolute percentage error.

The objective of this study was to obtain NOx emission prediction model at the inlet selective catalytic reduction (SCR) reactors, which was the basis of combustion optimization and denitrification treatment. A deep extreme learning machine (DELM) optimized by the sparrow optimization algorithm (SSA) was adopted to establish the NOx model based on data fusion of Computational Fluid Dynamics (CFD) simulation and Distributed Control System (DCD). The mechanism analysis and XGBoost algorithm was used to select input variables. The results show that the XGBoost-SSA-DELM-based prediction model has high prediction accuracy with mean absolute error of 2.54 mg/m3. The results of this study have important implications for research on improving combustion efficiency and reducing pollutant emissions.

No abstract

In this article, a data-driven model based on the incremental deep extreme learning machine (IDELM) algorithm is proposed to predict the temperature distribution in the furnace. To this end, computational fluid dynamics (CFD) simulations are carried out first to get temperature distributions under typical working conditions. Based on the air distribution mode, the simulation results are divided into six subclasses. Then the K-means clustering method is applied to find out the benchmark working condition of each subclass. Moreover, the random sampling method is used to extract samples to reduce computational complexity. Modeling inputs are selected according to the CFD boundary conditions and combustion mechanisms, and data sets are reconstructed based on the increments of each actual working condition from the benchmark working condition. Finally, an IDBN-based prediction model is built in each subclass. The experimental results show that the IDBN-based model has a promising predictive ability with less than 11% symmetric mean absolute percentage error.