摘要
在原有水利发电优化控制系统中引入BP神经网络方法,通过对系统的最优化建模和控制达到提高工作效率和电能质量的效果。同时,通过对水利发电过程中甩负荷故障实验对该方法的有效性进行了验证。
BP neural network was recruited into hydroelectric power optimization control system in order to promote working efficiency as well as to improve power quality by modeling of the system. Meanwhile,the effectiveness of new system was verified by load rejection failure experiments in the process of hydroelectric power.
引文
[1]何常胜,董鸿魁,翟鹏,等.水电机组一次调频与AGC典型控制策略的工程分析及优化[J].电力系统自动化,2015,39(3):146-151.
[2]李超顺,周建中,肖汉,等.基于引力搜索模糊模型辨识的水电机组预测控制[J].水力发电学报,2013,32(6):272-277.
[3]谢国财,李朝晖.基于Community Intelligence的水电机组融合监测方法[J].电力自动化设备,2013,33(1):153-159.
[4]安学利,潘罗平,张飞,等.水电机组劣化趋势混合预测模型[J].水力发电学报,2014,33(3):286-291,310.
[5]Miskovic M,Mirosevic M.Making the model of synchronous generator using the date from monitoring system[C]//Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference.Croatia:2004:1 129-1 132.
[6]冯惠妍,陈争光,王淑云.BP神经网络的土壤肥力评价研究[J].黑龙江八一农垦大学学报,2014,26(1):92-95.
[7]王磊,李桂香,王元麒.基于PSO算法优化的BPNN天然气脱CO2膜分离过程软测量模型[J].海南大学学报(自然科学版),2015,33(1):28-33.
[8]Arce A,Ohishi T,Soares S.Optimal dispatch of generating units of the Itaipu hydroelectric plant[J].IEEE Transactions on Power Systems,2002,17(1):154-158.
[9]田仲富,马国勇,黎粤华.智能木材干燥控制系统的研究与设计[J].安徽农业科学,2014,42(10):2 973-2 974.
[10]王利辉.轴承动态测量仪神经网络控制系统设计[J].内蒙古民族大学学报(自然科学版),2014,29(4):402-404.