基于改进粒子群算法的电站锅炉多目标优化研究.doc


基于改进粒子群算法的电站锅炉多目标优
化研究#
回立川,任仁,李潇娟,王大朋,于洋洋*
5
10
(辽宁工程技术大学电控学院,辽宁葫芦岛 125105)
摘要:由于锅炉设备庞大,运行条件复杂,煤种多变等因素,很难建立锅炉 NOx 排放与效
率的函数模型。利用 rbf 神经网络建立了以锅炉 NOx 排放与热效率为输出的混合模型,并
对此模型进行了校验,结果表明,该模型具有调节参数少,运行速度快、结果稳定、预测精
度高等优点,可以根据燃煤特性以及各操作参数准确预报锅炉在不同工况下的 NOx 排放与
热效率。针对模型的多目标优化问题,在粒子群算法中通过加入随机数比较法获取最优个体,
增强了种群的多样性,并对惯性因子进行了历史影响调整,使其更具有普遍性,在此基础上
利用改进算法进行了优化仿真,可得到不同目标要求下的燃烧组合。
关键词:系统工程;粒子群算法;锅炉效率;NOx 排放;优化
中图分类号:
15
Optimizing of Multi-object in Boiler based on Particle
swarm algorithm
Hui Lichuan, Ren Ren, Li Xiaojuan, Wang Dapeng, Yu Yangyang
(Faculty of electrical and control Engineering Liaoning Technical University,
20
25
LiaoNing Huludao 125105)
Abstract: It is very difficult to develop the NOx emission and efficiency model because of the
huge boiler architecture, plex operating conditions, the large variation of the coal used and
so on. A mixed model for boiler NOx emission and its efficiency was established by the Radical
Basis Function (RBF) work . The model can predict the NOx emission and boiler
efficiency simultaneously with fast calculating speed and high accuracy under various operating
conditions. The multiple objective Particle Swarm Optimization was introduced to solve the
multiple objective problems. The simulation shows the proposed algorithm can increase boiler
efficiency and reduce its NOx emission in one single run.
Keywords: Sys