基于SVM与遗传算法的燃煤锅炉燃烧多目标优化系统  

Multi objective optimization system of coal-fired boiler combustion based on SVM and genetic algorithm

作　　者：费洪晓[1] 黄勤径[1] 戴弋[1] 肖新华[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410075

出　　处：《计算机应用研究》2008年第3期811-813,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(60673165);湖南省自然科学基金资助项目(05JJ30119)

摘　　要：电站燃煤锅炉燃烧优化要求在保证燃烧效率的基础上降低NOx的排放,针对锅炉燃烧系统多变量、强耦合、强干扰、大滞后的复杂特性,提出利用支持向量机(SVM)对锅炉燃烧特性建模,利用遗传算法实现运行工况寻优,从而获得锅炉燃烧优化调整方式。仿真实验和实践结果表明,该系统实现了锅炉高效低氮的燃烧优化,满足实时性的要求。Combustion optimization for the boilers in power station is required by reduce NOx emissions which based on ensure combustion efficiency. Aimed at the complex properties of the boiler combustion system, such as multi-variables, close coupling, strong disturbances and long-time delay etc. This paper employed genetic algorithm to solve the multiple and conflicting objectives and perform a search to determine the optimum solution of the SVM model which was used to set up a boiler combustion response property model, so as to obtain currently optimum combustion adjustment mode of boiler. Simulation studies and practice results show that this system is effective, which can achieve optimum searching of high efficiency and low NOx combustion in the boiler, and can satisfy the demand for real-time.

关 键 词：燃烧优化 支持向量机 遗传算法 锅炉效率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]