Prediction of NOX Emission from Coal - fired Boiler Based on RF - GBDT
- DOI
- 10.2991/iceep-17.2017.61How to use a DOI?
- Keywords
- NOx prediction; random forest (RF); gradient lift decision tree (GBDT); coal fired boiler
- Abstract
A NOX emission forecasting model was established for a supercritical 660MW unit boiler combined with random forest (RF) and gradient lift decision tree (GBDT) algorithm. The steady-state working point of the historical data is screened from the SIS system of the power plant. The feature feature of the RF model is used to filter the data characteristics, and the GBDT model for predicting NOX emission is established with the selected feature as the input variable. The comparison with support vector machine (SVM), RF and other models shows that RF-based feature selection can improve model performance. Compared with other models, RF-GBDT has the highest prediction accuracy of NOX emission.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Liangming Gui AU - Yongjun Xia AU - Haishan Li AU - Peng Tan AU - Shangzhi Zhang AU - Cheng Zhang PY - 2017/06 DA - 2017/06 TI - Prediction of NOX Emission from Coal - fired Boiler Based on RF - GBDT BT - Proceedings of the 2017 6th International Conference on Energy and Environmental Protection (ICEEP 2017) PB - Atlantis Press SP - 344 EP - 350 SN - 2352-5401 UR - https://doi.org/10.2991/iceep-17.2017.61 DO - 10.2991/iceep-17.2017.61 ID - Gui2017/06 ER -