Suzhou Electric Appliance Research Institute
期刊号: CN32-1800/TM| ISSN1007-3175

Article retrieval

文章检索

首页 >> 文章检索 >> 往年索引

基于SDP和2DLNMF的变压器偏磁状态识别方法

来源:电工电气发布时间:2024-12-02 09:02 浏览次数:173

基于SDP和2DLNMF的变压器偏磁状态识别方法

叶帅,陈皖皖,王浩宇,赵义东
(国网安徽省电力有限公司淮南供电公司,安徽 淮南 232000)
 
    摘 要:为了有效检测变压器直流偏磁状态,从多通道振动信号融合的角度出发,提出了一种基于对称点模式(SDP)和二维局部非负矩阵分解(2DLNMF)的变压器偏磁状态识别方法。利用 SDP 算法将采集的多通道振动信号融合成 SDP 图像特征;然后应用 2DLNMF 算法对其进行了降维优化,据此构建了基于支持向量机(SVM)算法变压器偏磁状态识别模型。研究结果表明:基于 SDP-2DLNMF 的信息融合方法充分了展现不同信号间的特征差异,获取的低维特征可有效反映变压器直流偏磁程度,据此建立的 SVM 状态识别模型具有较高的识别精度,为变压器的状态监测提供了技术支撑。
    关键词: 变压器;直流偏磁;对称点模式;二维局部非负矩阵分解;支持向量机
    中图分类号:TM411     文献标识码:B     文章编号:1007-3175(2024)11-0042-07
 
Recognition Method of Transformer Magnetic Bias
State Based on SDP and 2DLNMF
 
YE Shuai, CHEN Wan-wan, WANG Hao-yu, ZHAO Yi-dong
(State Grid Anhui Electric Power Company Co., Ltd. Huainan Power Supply Company, Huainan 232000, China)
 
    Abstract: In order to effectively detect the transformer DC magnetic bias state, this paper starts from the perspective of multi-channel information fusion, and proposes a new method for identifying the bias state of a transformer based on symmetrized dot pattern (SDP) and 2-dimensionlal local nonngeative matrix factorzization(2DLNMF). Firstly, SDP algorithm is used to fuse the multi-channel vibration signals into SDP image features. Then, the 2DLNMF algorithm was used to optimize its dimensionality reduction, according to which the transformer magnetic bias state recognition model based on the support vector machine (SVM) algorithm was built. The research results show that information fusion method based on the SDP-2DLNMF fully shows the characteristics of the differences between different signal, the obtained low-dimensional characteristics can effectively reflect the degree of DC magnetic bias of the transformer, and the SVM state recognition model established on this basis has high recognition accuracy, which provides technical support for transformer state monitoring.
    Key words: transformer; DC magnetic bias; symmetrized dot pattern; 2-dimensionlal local nonngeative matrix factorzization; support vector machine
 
参考文献
[1] 舒印彪,张文亮. 特高压输电若干关键技术研究[J] .中国电机工程学报,2007,27(31) :1-6.
[2] 高沛,王丰华,苏磊,等. 直流偏磁下电力变压器的振动特性[J]. 电网技术,2014,38(6) :1536-1541.
[3] 谢志成,钱海,林湘宁,等. 直流偏磁下变压器运行状态量化评估方法[J] . 电力自动化设备,2019,39(2) :216-223.
[4] 张彬,徐建源,陈江波,等. 基于电力变压器振动信息的绕组形变诊断方法[J] . 高电压技术,2015,41(7) :2341-2349.
[5] 黄春梅,马宏忠,吴明明,等. 基于 CRP 和 RQA 的变压器绕组压紧状态检测[J] . 电力系统保护与控制,2018,46(7) :144-149.
[6] 郭洁,陈祥献,黄海. 交叉递归图在变压器铁芯压紧力变化检测中的应用[J] . 高电压技术,2010,36(11) :2731-2738.
[7] 杨毅,王丰华,段若晨,等. 基于自适应筛选 EMD 和 CFDC 的变压器绕组状态检测[J]. 振动与冲击,2017,36(19) :106-111.
[8] 解颖,王丰华,傅正财. 基于栈式自编码器的变压器机械故障诊断[J]. 高压电器,2020,56(9) :46-53.
[9] LI Yuchun, LIU Lianguang.The application of the wavelet packet to the study of vibration of transformer under DC magnetic bias[C]//2010 5th International Conference on Critical Infrastructure(CRIS), 2010 :1-4.
[10] 郭洁,黄海,唐昕,等.500 kV 电力变压器偏磁振动分析[J]. 电网技术,2012,36(3) :70-75.
[11] 吴晓文,周卫华,裴春明,等.500 kV 自耦变压器直流偏磁振动特征提取与模式识别方法研究[J]. 西安交通大学学报,2018,52(4) :24-30.
[12] LIU Xingmou, WU Jiaxin, LIN Haibo, et al.Research on DC bias analysis for transformer based on vibration Hilbert Huang transform and ground-state energy ratio method[J].International Journal of Electrical Power & Energy Systems,2019,109 :73-82.
[13] XU Xiaogang, LIU Haixiao, ZHU Hao, et al.Fan fault diagnosis based on symmetrized dot pattern analysis and image matching[J].Journal of Sound and Vibration,2016,374 :297-311.
[14] 王科俊,左春婷. 非负矩阵分解特征提取技术的研究进展[J]. 计算机应用研究,2014,31(4) :970-975.
[15] LI Stan Z, HOU Xinwen.Learming spatially localized, parts-based representation Computer Vision and Pattemn Recognition[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattemn Recognition,2001 :120-129.
[16] 许榕, 吴聪, 蒋士正, 等. 二维局部非负矩阵分解的路网态势算法[J] . 上海交通大学学报,2015,49(8) :1131-1136.
[17] 戴栋,黄筱婷,代洲,等. 基于支持向量机的输电线路覆冰回归模型[J] . 高电压技术,2013,39(11) :2822-2828.
[18] 刘方园,王水花,张煜东. 支持向量机模型与应用综述[J]. 计算机系统应用,2018,27(4) :1-9.
[19] 陈仕龙,曹蕊蕊,毕贵红,等. 利用多分辨奇异谱熵和支持向量机的特高压直流输电线路区内外故障识别方法[J]. 电网技术,2015,39(4) :989-994.
[20] 付旻,王炜,王昊,等. 多分类支持向量机在公交换乘识别中的应用[J] . 哈尔滨工业大学学报,2018,50(3) :26-32.
[21] 杨毅,刘石,张楚,等. 基于振动分布特征的电力变压器绕组故障诊断[J]. 振动与冲击,2020,39(1) :199-208.
[22] 张雪冰,饶柱石,塔娜,等. 变压器油箱振动功率流研究[J]. 振动与冲击,2009,28(5) :188-191.
[23] 张凡, 汲胜昌, 师愉航, 等. 电力变压器绕组振动及传播特性研究[J] . 中国电机工程学报,2018,38(9) :2790-2798.