同调机群的识别.doc

第32卷 电网技术 Vol. 32 No. 1
2008年1月 Power System Technology Jun. 2001
文章编号:1000-3673(2004)00-0000-00 中图分类号:TM 文献标识码:A 学科代码:470。0000
基于A-K网络模型的模糊聚类同调机群识别
刘绚1,文俊2,刘天琪1
(,四川成都 610065:
,重庆,400030)
A fuzzy clustering method based on A-works to recognize coherent generator groups
Liu Xuan,Wen Jun,Liu Tianqi
(School of Electrical Information, Sichuan University, Chengdu 610065, China)
ABSTRACT: A coherent groups recognition method using fuzzy clustering method based on A-works is proposed. Firstly, a fuzzy similarity matrix is formed by applying maxmum-minmum algorithm. Then train the A-works with each row of the fuzzy similarity matrix as inputs. The nerves of output layer which win ultimatly represent different dynamic styles. Finally, it is tested on the EPRI-36 bus model of PSASP. The results based on A-K fuzzy method are more similar to the results based on time pared to A-K method, which are not misajudgments. Moreover, A-K fuzzy method can identify coherent generator groups in greater time range.
KEY WORDS: power system; A-works; fuzzy clustering; coherent generator groups; coherency identification
摘要:给出了一种利用基于融合ART和Kohonen网络基本思想的自组织神经网络(简称A—K网络),即采用最大-最小法建立能够反映发电机组间同调程度的模糊相似矩阵;然后将其每行或每列输入A-K网络模型进行训
基金项目:国家自然科学基金(50595412)。
Project Supported by National Natural Science Foundation of China(50595412).
练