王成亮;王宏华;徐钢;

• 1:江苏方天电力技术有限公司
• 2:河海大学能源与电气学院

摘要(Abstract)：

提出一种基于反向传播神经网络(back propagationneural network,BPNN)的发电机进相能力建模新方法。该BPNN含2个隐层和1个输出层,以发电机有功和无功功率为输入,以发电机功角、电网电压为输出。以典型工况下的发电机进相运行试验结果作为训练样本和测试样本,建立了某600 MW发电机进相能力BPNN模型,从收敛精度最优出发,优化设计了模型的隐层数、神经元数、传递函数。建模实例表明,提出的建模方法精度高、泛化能力强,能有效克服传统分析方法的局限性,有推广应用价值。

关键词(KeyWords)： 反向传播神经网络;发电机进相;泛化

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 王成亮;王宏华;徐钢;

Email:

DOI: 10.13335/j.1000-3673.pst.2011.11.027

参考文献(References)：

• [1]史家燕,史源素,赵肖敏,等.发电机工况参数模型及进相运行在线监测[J].中国电机工程学报,2006,26(11):139-143.Shi Jiayan,Shi Yuansu,Zhao Xiaomin,et al.The new method of determining the capability of leading phase of generator and realizing the on-line monitoring[J].Proceedings of the CSEE,2006,26(11):139-143(in Chinese).
• [2]张建忠,万栗,刘洪志,等.大型汽轮发电机进相运行及对电网调压试验研究[J].中国电力,2006,39(12):11-15.Zhang Jianzhong,Wan Li,Liu Hongzhi,et al.Study on leading phase operation and voltage regulation test of power network for large steam turbine-generator[J].Electric Power,2006,39(12):11-15(in Chinese).
• [3]李向荣,牟道槐.采用静止无功补偿器和异步发电机改善高压电力系统无功调节特性[J].电网技术,2002,26(10):58-61.Li Xiangrong,Mu Daohuai.Improvement of reactive power regulation performance of high voltage power system by use of asynchronous generator coupled with SVC[J].Power System Technology,2002,26(10):58-61(in Chinese).
• [4]SD325—1989电力系统电压和无功电力技术导则(试行)[S].
• [5]郭景斌,单周平.水轮发电机静态稳定应用分析方法[J].大电机技术,2000(4):23-25.Guo Jingbin,Shan Zhouping.Applicable analysis method for the static stability of hydro generator[J].Large Electric Machine and Hydraulic Turbine,2000(4):23-25(in Chinese).
• [6]郭景斌,单周平.凸极同步发电机静稳定边界的解析法和应用[J].中国电力,2000,33(10):39-41.Guo Jingbin,Shan Zhouping.Analytic method of the static stable boundary for hydro-generator and its application[J].Electric Power,2000,33(10):39-41(in Chinese).
• [7]董新胜,宁晓棠,石海珍.新疆主电网发电机进相试验与数据分析[J].华东电力,2007,35(4):67-70.Dong Xinsheng,Ning Xiaotang,Shi Haizhen.Generator phase advance tests and data analysis for Xin jiang main grids[J].East China Electric Power,2007,35(4):67-70(in Chinese).
• [8]范高锋,王伟胜,刘纯.基于人工神经网络的风电功率短期预测系统[J].电网技术,2008,32(22):72-76.Fan Gaofeng,Wang Weisheng,Liu Chun.Artificial neural network based wind power short term prediction system[J].Power System Technology,2008,32(22):72-76(in Chinese).
• [9]陈刚,周杰,张雪君,等.基于BP与RBF级联神经网络的日负荷预测[J].电网技术,2009,33(12):101-105.Chen Gang,Zhou Jie,Zhang Xuejun,et al.A daily load forecastingmethod based on cascaded back propagation and radial basis function neural network[J].Power System Technology,2009,33(12):101-105(in Chinese).
• [10]陈伟,吴耀武,娄素华,等.基于累积式自回归动平均法和反向传播神经网络的短期负荷预测模型[J].电网技术,2007,31(3):73-76.Chen Wei,Wu Yaowu,Lou Suhua,et al.A short-term load forecasting model based on ARIMA and BPNN[J].Power System Technology,2007,31(3):73-76(in Chinese).
• [11]王立德,李欣然,李培强,等.基于人工神经网络的综合负荷模型[J].电网技术,2008,32(16):59-65.Wang Lide,Li Xinran,Li Peiqiang,et al.Compositive load model based on artificial neural network[J].Power System Technology,2008,32(16):59-65(in Chinese).
• [12]陈林刚,韩凤琴,桂中华.基于神经网络的水电机组智能故障诊断系统[J].电网技术,2006,30(1):40-43.Chen Lingang,Han Fengqin,Gui Zhonghua.A neural network based intelligent fault diagnosis system for hydroelectric generating sets[J].Power System Technology,2006,30(1):40-43(in Chinese).
• [13]杨琦,张建华,王向峰,等.基于小波-神经网络的风速及风力发电量预测[J].电网技术,2009,33(17):44-48.Yang Qi,Zhang Jianhua,Wang Xiangfeng,et al.Wind speed and generated wind power forecast based on wavelet-neural network[J].Power System Technology,2009,33(17):44-48(in Chinese).
• [14]宋云亭,吴俊玲,彭冬,等.基于BP神经网络的城网供电可靠性预测方法[J].电网技术,2008,32(20):56-59.Song Yunting,Wu Junling,Peng Dong,et al.A BP neural networkbased method to predict power supply reliability of urban power network[J].Power System Technology,2008,32(20):56-59(in Chinese).
• [15]李膨源,顾雪平.基于神经网络的黑启动操作过电压快速预测[J].电网技术,2006,30(3):66-70.Li Pengyuan,Gu Xueping.Fast determination of switching overvoltage in black start process based on artificial neural networks[J].Power System Technology,2006,30(3):66-70(in Chinese).
• [16]乐波,谢恒堃.基于模糊输出BP神经网络的电机主绝缘老化状态评估方法[J].中国电机工程学报,2005,25(2):76-81.Yue Bo,Xie Hengkun.Evaluating the aging condition of main insulation in large generator based BP artificial neural network with fuzzy output[J].Proceedings of the CSEE,2005,25(2):76-81(in Chinese).
• [17]Martin T H,Howard B D,Mark H B.Neural network design[M].Boston:PWS Publishing Company,1996:207-221.