IGSA-LSSVM Soft Sensing Model for Predicting NOx Emission of Coal-fired Boiler
DING Zhi-ping1,LIU Chao2,NIU Pei-feng3
1. Institute of Information Technology and Creative Design, Qingyuan Polytechnic, Qingyuan, Guangdong 511510, China
2. Guizhou Aerospace Electronics Co. Ltd., Guiyang, Guizhou 550009, China
3. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, Hebei 066004, China
Abstract：Based on least squares support vector machine optimized by improved gravitational search algorithm (IGSA-LSSVM), an intelligent soft sensing method to accurately measure the NOx emission of the coal-fired boiler is presented. Firstly, the GSA have the drawbacks of easy to fall into local minimum and poor global search ability, so an improved version of GSA is proposed to improve global optimal performance, using the grid algorithm that is employed to initialize the population and using the adaptive decreasing inertia weight based on fitness value of optimization problems that is introduced into position update. Secondly, IGSA is developed to find the optimal parameters of LSSVM to improve the regression accuracy and generalization ability for predicting NOx emission. Finally, a soft computing method based on IGSA-LSSVM is established to forecast NOx emission of a 330 MW coal-fired boiler.The simulation results show that the IGSA-LSSVM model demonstrates better regression precision and generalization capability, it can accurately measure NOx emission.
［1］Tan P, Xia J. Modeling and optimization of NOx emission in a coal-fired power plant using advanced machine learning methods ［J］. Energy Procedia,2014,61:377-380.
［2］牛培峰, 马云鹏, 张京.基于相关向量机的电站锅炉NOx燃烧优化［J］.计量学报, 2016, 37(2): 191-196.
Niu P F, Ma Y P, Zhang J. Utility boilers NOx combustion optimization based on relevance vector machine［J］. Acta Metrologica Sinica, 2016, 37(2): 191-196.
［3］牛培峰, 麻红波, 李国强.基于GSA-SVM的循环流化床锅炉NOx排放特性模型［J］.计量学报, 2013, 34(6): 602-606.
Niu P F, Ma H B, Li G Q. NOx emission characteristic model for circulating fluidized bed boilers based on GSA-SVM［J］. Acta Metrologica Sinica, 2013, 34(6): 602-606.
［3］牛培峰,王丘亚,马云鹏,等. 基于量子自适应鸟群算法的锅炉NOx排放特性研究［J］. 计量学报, 2017, 38(6): 770-775.
Niu P F, Wang Q Y, Ma Y P, et al. Study on NOx emission from boiler based on quantum adaptation bird swarm algorithm［J］. Acta Metrologica Sinica, 2017, 38(6): 770-775.
［4］张维平, 赵文蕾, 牛培峰.基于粗糙集与最小二乘支持向量回归的汽轮机主蒸汽流量预测［J］.计量学报, 2015, 36(1): 43-47.
Zhang W P, Zhao W L, Niu P F. Forecasting of turbine main steam flow based on rough sets and least squars support vector machine regression ［J］. Acta Metrologica Sinica, 2015, 36(1): 43-47.
［5］Liu C, Niu P F. A hybrid heat rate forecasting model using optimized LSSVM based on improved GSA［J］. Neural Processing Letters,2017,45:299-318.
［6］Li Q, Niu P F, Zhang W P. Model NOx emissions by least squares support vector machine with tuning based on ameliorated teaching-learning-based optimization ［J］. Chemometrics and Intelligent Laboratory Systems,2013,126:11-20.
［7］牛培峰, 王培坤, 李国强.基于自由搜索算法和支持向量机的燃煤锅炉NOx建模与优化［J］.计量学报, 2014, 35(6): 626-630.
Niu P F, Wang P K, Li G Q. Modeling and optimization of NOx for coal-fired boilers by free search algorithm and support vector machine ［J］. Acta Metrologica Sinica, 2014, 35(6): 626-630.
［8］Esmat Rashedi, Hossein Nezanudmdi-pour, Saryazdi Saryazdi. GSA: A Gravitational Search Algorithm［J］. Information Sciences,2009,179(13):2232-2248.
［9］Gouthamkumar N, Sharma Veena, Naresh R. Disruption based gravitational search algorithm for short term hydrothermal scheduling［J］. Expert Systems with Applications,2015,42(20):7000-7011.
［10］Sajjad Yazdani, Hossein Nezamabadi-pour, Shima Kamyab. A gravitational search algorithm for multimodal optimization［J］. Swarm and Evolutionary Computation,2014,14:1-14.
［11］Li G Q, Niu P F, Xiao X J. Development and investigation of efficient artificial bee colony algorithm for numerical function optimization［J］. Applied Soft Computing, 2012, 12(1): 320-332.
［12］牛培峰, 刘超, 李国强.汽轮机热耗率多模型建模方法研究［J］.计量学报, 2015, 36(3): 251-255.
Niu P F, Liu C, Li G Q. Investigation on multi-model modeling method of steam turbine heat rate［J］. Acta Metrologica Sinica, 2015, 36(3): 251-255.
2018, Vol. 39 
