|
|
|
| Modeling and Optimization of NOx for Coal-fired Boilers by Free Search Algorithm and Support Vector Machine |
| NIU Pei-feng1,2,WANG Pei-kun1,LI Guo-qiang1 ,MA Yun-fei1,CHEN Gui-lin1,2,ZHANG Xian-chen1,2 |
1. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University,Qinhuangdao, Hebei 066004, China;
2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Qinhuangdao, Hebei 066004, China |
|
|
|
|
Abstract A model of the boilers NOx emissions is developed by support vector machine (SVM). The free search (FS) algorithm is used to optimize the parameters of the SVM model and the input parameters of the boilers. The modeling results show that, FS-SVM model can predict NOx emissions very well, the forecast accuracy is very high.NOx emissions are significantly reduced by optimizing the input parameters, and the change of the optimized parameters are consistent with the experimental results of the related reference.
|
|
|
|
|
|
［1］许昌,吕剑虹. 基于生成机理的燃煤电站锅炉NOx排放量神经网络模型［J］. 中国电机工程学报, 2004, 24(10):233-237.
［2］周昊,茅建波,池作和,等. 燃煤锅炉氮氧化物燃烧特性的神经网络预报［J］.环境科学,2002,23(2):18-22.
［3］王培红,李磊磊,陈强,等. 电站锅炉NOx排放与效率的响应特性模型［J］.动力工程,2004,24(2):254-259.
［4］Vapnik V N. The nature of statistical learning theory［M］. New York:Springer-Verlag,1995.
［5］Penev K,Littlefair G.Free Search-a comparative analysis［J］.Information Sciences, 2005, 172(1-2): 173-193.
［6］Cherkassky V,Ma Y.Practical selection of SVM parameters and noise estimation for SVM regression ［J］. Neural Networks, 2004, 17(1):113-126.
［7］Mao Y, Xia Z , Yin Z, et al. Fault diagnosis based on fuzzy support vector machine with parameter tuning and feature selection［J］.Chinese Journal of Chemical Engineering,2007,15(2):233-239.
［8］许昌,吕剑虹,郑源. 基于效率与NOx排放的锅炉燃烧优化试验及分析［J］. 锅炉技术,2006,37(5):69-74.
［9］周晖,李丹美,邵世煌,等. 一种新的集群智能算法—自由搜索［J］. 东华大学学报,2007,33(5) :579-583.
［10］何宏舟. 一次风率及循环废气率变对燃油锅炉运行中氮氧化物生成的影响［J］. 锅炉技术,2004, 35(1): 65-68. |
|
|
|
2014, Vol. 35 
