【摘要】：準(zhǔn)確識(shí)別故障類型是配電網(wǎng)故障處理的首要任務(wù)。提出了一種基于時(shí)頻矩陣奇異值分解(SVD)和多級(jí)支持向量機(jī)(SVM)的配電網(wǎng)故障識(shí)別方法。利用局部特征尺度分解法(LCD)、Hilbert變換以及帶通濾波算法,構(gòu)造配電網(wǎng)母線電壓、主變低壓側(cè)進(jìn)線電流等波形的時(shí)頻矩陣,對其進(jìn)行奇異值分解以獲取波形奇異譜,提取相應(yīng)奇異譜的分布參數(shù)(如反映奇異值大小的奇異譜均值、反映信號(hào)復(fù)雜程度的奇異熵等)作為特征向量。將特征向量輸入基于多級(jí)SVM的分類器以實(shí)現(xiàn)故障識(shí)別。各類典型工況下的仿真和實(shí)驗(yàn)結(jié)果表明該識(shí)別方法的正確率均90%,可實(shí)現(xiàn)對各類不同故障的有效辨識(shí),且具有很強(qiáng)的適應(yīng)性和實(shí)用性。
[Abstract]:Accurate identification of fault types is the primary task of distribution network fault processing. A fault identification method for distribution network based on time-frequency matrix singular value decomposition (SVD) and multistage support vector machine (SVM) is proposed. Based on the local characteristic scale decomposition (LCD), Hilbert) transformation and bandpass filtering algorithm, the time-frequency matrix of the waveform such as bus voltage and low voltage input current of main transformer is constructed, and the singular value decomposition is carried out to obtain the singular spectrum of the waveform. The distribution parameters of the corresponding singular spectrum (such as the singular spectral mean which reflects the size of the singular value, the singular entropy reflecting the complexity of the signal, etc.) are extracted as the eigenvector. The feature vector is input into the classifier based on multilevel SVM to realize fault identification. The simulation and experimental results under various typical working conditions show that the accuracy of the method is 90%, which can effectively identify different kinds of faults, and has strong adaptability and practicability.
【作者單位】： 福州大學(xué)電氣工程與自動(dòng)化學(xué)院;國網(wǎng)福建省電力有限公司技能培訓(xùn)中心;
【基金】：國家自然科學(xué)基金(51677030) 福建省自然科學(xué)基金(2016J01218)~~
【分類號(hào)】：TM711

【相似文獻(xiàn)】

相關(guān)期刊論文 前6條

1 趙聞飆,施頌椒,夏偉;固定階數(shù)的結(jié)構(gòu)奇異值反饋控制器的設(shè)計(jì)[J];自動(dòng)化學(xué)報(bào);1999年03期

2 趙瑞峰;;最小奇異值靈敏度分析法的研究[J];湖南工業(yè)大學(xué)學(xué)報(bào);2010年03期

3 王昆;彭昱;周瑋;孫輝;;基于預(yù)估/校正技術(shù)的改進(jìn)奇異值指標(biāo)[J];繼電器;2006年17期

4 徐志友,欒兆文,樊濤,駱濟(jì)壽;衡量節(jié)點(diǎn)電壓穩(wěn)定的奇異值法和穩(wěn)定指標(biāo)[J];電力系統(tǒng)自動(dòng)化;1997年08期

5 胡三高;安宏文;馬志勇;柳亦兵;滕偉;;基于小波奇異值分析的汽輪機(jī)碰磨特征提取[J];動(dòng)力工程學(xué)報(bào);2013年03期

6 ;[J];;年期

，

本文編號(hào)：2275128