掺烧煤泥循环流化床机组经济性优化运行研究  

Economic Optimization Study of Mix-burning Coal Slime Circulating Fluidized Bed Boiler

作　　者：张维[1] 高明明[1] ZHANG Wei;GAO Mingming(State Key Lab of Alternate Electric Power System With Renewable Energy Sources（North China Electric Power University）,Changping District,Beijing 102206,China)

机构地区：[1]新能源电力系统国家重点实验室(华北电力大学)

出　　处：《中国电机工程学报》2018年第16期4807-4814,共8页Proceedings of the CSEE

基　　金：国家重点研发计划项目(2016YFB0600205);中央高校基本科研业务费专项资金项目(2016MS28,2017XS072)~~

摘　　要：目前,循环流化床煤泥掺烧技术是低热值燃料高效清洁规模化利用的有效途径。以某300MW掺烧煤泥循环流化床机组历史稳态数据为样本,利用最小二乘支持向量机建立掺烧煤泥循环流化床经济性模型;在稳态下各控制变量安全阈值范围内,利用遗传算法对典型负荷指令下CFB各参数设定值离线寻优以建立专家知识库;将经济实用度引入关联规则衡量标准,得到改进模糊关联规则挖掘（IFARM）算法,利用IFARM在离线EKB中挖掘CFB最优运行状态与机组负荷的关联关系,实现负荷指令下快速指导掺烧煤泥循环流化床机组在线优化控制。At present, mix-burning coal slime in circulating fluidized bed （CFB） boiler is an effective way to cleanly use low heat value fuels in a large scale. On the basis of the 300MW CFB steady-state operating data, least squares support vector machine （LS-SVM） was used to build the energy cost model, which described the relationship between the operating parameters and the energy cost; Within the safety threshold range of each control variable, the genetic algorithm （GA） was used to optimize the typical CFB parameter settings to establish an expert knowledge base （EKB） offiine; The economic utility was introduced into association rule measurement standards, and the improved fuzzy association rule mining （IFARM） algorithm was used to extract the associations between optimal control variables and unit load from the off-line EKB, so as to achieve fast guidance on online optimization and adjustment of mix-burning coal slime CFB under load command.

关 键 词：循环流化床(CFB) 最小二乘支持向量机 遗传算法 改进模糊关联规则挖掘 

分 类 号：TK39[动力工程及工程热物理—热能工程]