摘要
结合海防电厂300MW机组100%负荷下的快速甩负荷试验,采用粒子群优化算法(PSO)对支持向量机(SVM)的参数进行优化,并建立PSO-SVM过热蒸汽温度预测模型。在分析试验时机组燃料量、高旁阀位开度及温度等主要参数变化过程的基础上,对过热蒸汽温度预测模型进行仿真分析。结果表明:建立的PSO-SVM过热蒸汽温度模型具有较高的预测精度,能够实现快速甩负荷工况下过热蒸汽温度的预测,维持机组安全稳定运行。
Combining with the FCB tests under a 300 MW unit's 100% load conditions in Haifang Power Plant,making use of PSO algorithm to optimize SVM parameters and to establish a PSO-SVM-based prediction model of the superheated steam was implemented. Having the changing process of main parameters like the unit's fuel amount,valve opening and the temperature analyzed and the prediction model of the superheated steam temperature simulated shows that this PSO-SVM-based prediction model has higher accuracy in quickly predicting the superheated steam temperature under FCB conditions and it can maintain the unit's safe and stable operation.
引文
[1]王建国,孙灵芳,张利辉.电厂热工过程自动控制[M].北京:中国电力出版社,2009.
[2]张明.煤制天然气项目甲烷化废热锅炉系统的技术探讨[J].化工机械,2012,39(2):121~123,161.
[3]宣进,刘晓宇.循环流化床锅炉吊挂管短期爆管原因分析[J].化工机械,2012,39(1):91~95.
[4]黄宝海,韩璞,葛忠真,等.基于现场数据的电站过热器神经网络建模[J].华北电力大学学报,2008,35(2):66~69.
[5]于红霞.基于神经网络过热汽温模型辨识[J].锅炉制造,2008,(4):66~68.
[6]Sun Z H,Sun Y X.Fuzzy Support Vector Machine for Regression Estimation[C].IEEE International Conference on Systems,Man and Cybernetics.Washington:IEEE,2003:3336~3341.
[7]Chen R,Liang C Y,Hong W C,et al.Forecasting Holiday Daily Tourist Flow Based on Seasonal Support Vector Regression with Adaptive Genetic Algorithm[J].Applied Soft Computing,2015,26:435~443.
[8]宋志宇,李俊杰.基于微粒群算法的大坝材料参数反分析研究[J].岩土力学,2007,28(5):991~994.
[9]刘瑞兰,牟盛静,苏宏业,等.基于支持向量机和粒子群算法的软测量建模[J].控制理论与应用,2006,23(6):895~899.
[10]邓乃扬,田英杰.支持向量机——理论、算法与拓展[M].北京:科学出版社,2009.
[11]Kennedy J,Eberhart R.Particle Swarm Optimization[J].IEEE International Conference on Neural Networks,1995,4(8):1942~1948.
[12]孙灵芳,邵萌萌,刘旭颖.基于改进的BP算法的过热汽温建模[J].自动化技术与应用,2010,29(4):1~3.