基于改进分布式极限学习机的电站锅炉NO_x排放预测算法  

NO_x Emission Prediction Algorithm of Power Station Boiler Based on Improved Distributed Extreme Learning Machine

作　　者：徐晨晨[1] 续欣莹[1] 阎高伟[1] 韩晓霞[1] 

机构地区：[1]太原理工大学信息工程学院,山西晋中030600

出　　处：《太原理工大学学报》2017年第6期946-952,共7页Journal of Taiyuan University of Technology

基　　金：山西省自然科学基金资助项目(2014011018-2);山西省回国留学人员科研资助项目(2015-045);神经网络协同遗传算法高效筛选镍基甲烷化催化剂研究(21606159)

摘　　要：提出了一种改进的分布式极限学习机的电站锅炉NO_x排放特性建模方法。引入分布式和岭回归理论,提升了极限学习机预测算法的泛化性能和预测准确率。采用改进的MapReduce编程框架对提出的算法模型进行并行化改进,提高其处理大数据的能力。选用某660 MW电站锅炉提供的真实运行数据进行分析,并在Hadoop集群上进行实验,结果表明该模型对NO_x排放有着较好的拟合和预测能力,且提出的算法具有优异的并行性能。An improved distributed extreme learning machine was proposed to model the NO_x emission characteristics of power station boiler.The introduction of distributed type and ridge regression theory improved the generalization performance and prediction accuracy of the limit learning algorithm.An improved MapReduce programming framework was adopted to carry out the parallelization of the the proposed algorithm so as to enhance its ability of dealing with massive data.The real operation data provided by a 660 MW power station boiler was analyzed and tested on Hadoop cluster.Results show that the proposed model has a better fitting and predictive ability for NO_x emission,and the proposed algorithm has excellent parallel performance.

关 键 词：NOX排放 海量数据 MAPREDUCE 分布式极限学习机 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]