利用小波能量特征的增长型自组织神经网络同调机组分群方法
提出了一种利用小波变换多尺度空间能量分布特征的自组织神经网络同调机组分群方法。首先改进了同调机群识别判据,然后利用小波变换的多尺度空间能量分布特征提取方法,对机组功角摇摆曲线提取特征,将时域特征、频域特征及小波能量特征构成的综合向量,作为增长型自组织神经网络的输入,通过调节阈值λ,得出不同精度的分群结果。最后在IEEE-39节点系统上对只考虑时频域特征和同时考虑小波能量特征、时频域特征的同调机组识别结果进行了对比分析,最终表明同时考虑小波能量特征、时频域特征的分群结果具有更高准确性。...
Saved in:
| Published in | 电测与仪表 Vol. 54; no. 14; pp. 7 - 13 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
华北电力大学 新能源电力系统国家重点实验室,河北 保定,071003%国网福建省电力有限公司电力科学研究院,福州,350007%中国电力科学研究院,北京,100192
2017
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-1390 |
Cover
| Summary: | 提出了一种利用小波变换多尺度空间能量分布特征的自组织神经网络同调机组分群方法。首先改进了同调机群识别判据,然后利用小波变换的多尺度空间能量分布特征提取方法,对机组功角摇摆曲线提取特征,将时域特征、频域特征及小波能量特征构成的综合向量,作为增长型自组织神经网络的输入,通过调节阈值λ,得出不同精度的分群结果。最后在IEEE-39节点系统上对只考虑时频域特征和同时考虑小波能量特征、时频域特征的同调机组识别结果进行了对比分析,最终表明同时考虑小波能量特征、时频域特征的分群结果具有更高准确性。 |
|---|---|
| Bibliography: | This paper proposes a novel method to identify coherent generator groups using wavelet transform multi- scale space energy distribution feature and improved self-organizing neural networks. Firstly, the identification criteria of coherent generator groups are defined, and then, the features of the unit power angle rocking curve are extracted u- sing multi-scale spatial energy wavelet distribution method. Furthermore, the time domain, frequency domain and wavelet energy feature vectors are used as inputs of growth-oriented self-organizing neural networks to obtain grouping of different precisions by adjusting the threshold k. Finally, the recognition results on the IEEE-39 bus system, con- sidering the features of only time-frequency domain and both the wavelet energy and time-frequency domain, are com- pared. The results show that the proposed method taking into account the feathers of both the wavelet energy and time- frequency domain can obtain higher accuracy. 23-1202/TH wavelet analysis, multi-scale spatial |
| ISSN: | 1001-1390 |