基于PSO-LSSVM的双压凝汽器真空建模  

Vacuum Modeling for Dual-Pressure Condensers Based on PSO-LSSVM Model

作　　者：吴伟 冯林魁 王平 赵凯 WU Wei;FENG Lin-kui;WANG Ping;ZHAO Kai(State Grid Gansu Electric Power Research Institute,Lanzhou Gansu 730000,China)

机构地区：[1]国网甘肃省电力公司电力科学研究院,甘肃兰州730000

出　　处：《机械研究与应用》2021年第4期128-130,共3页Mechanical Research & Application

摘　　要：凝汽器真空状态反映了凝汽器的工作运行状态,是保证火力发电机组安全运行的重要参数。文中结合凝汽器的工作原理,建立了基于PSO-LSSVM的凝汽器真空预测模型,并对某1000MW超临界机组的双压凝汽器真空进行预测,同时将预测结果与PSO-BP模型和PSO-Elman模型进行了对比。结果表明,使用的PSO-LSSVM模型具有更高的精度和更快的收敛速度,为机组的性能诊断、参数寻优提供了依据理论,具有一定的工程应用价值。The condenser vacuum,which reflects the operating condition of unit condenser,is a significant parameter for security assurance of thermal power generating unit.In this paper,a vacuum prediction model based on PSO-LSSVM for dual-pressure condenser is established and applied to predict in dual-pressure condenser in a 600 MW unit;the predictions are also compared with the PSO-BP and PSO-Elman models.The experimental results show that the PSO-LSSVM model has a higher accuracy and faster convergence rate;it provides basis theory for performance diagnosis and parameter optimization of the unit,and has certain engineering application value.

关 键 词：最小二乘支持向量机 粒子群优化算法 双压凝汽器 凝汽器真空 

分 类 号：TK264[动力工程及工程热物理—动力机械及工程]