Corona pulses current method is a way which can be used to detect faulty insulators on ground 電暈脈沖電流法是一種地面檢測(cè)不良絕緣子的方法,但目前應(yīng)用中其檢測(cè)的準(zhǔn)確度較低。
But its accuracy of detecting is low in application . in this paper we try to find a method based on artificial neural network to improve the accuracy of detecting faulty insulators 本文力圖通過(guò)大量的實(shí)驗(yàn)室和現(xiàn)場(chǎng)數(shù)據(jù)的分析,發(fā)展一種基于人工神經(jīng)網(wǎng)絡(luò)的不良絕緣子診斷方法,提高脈沖電流法用于檢測(cè)不良絕緣子的準(zhǔn)確性。
We took a lot of data of corona pulses from the laboratory and field by using the detecting device . we got the corona finger prints for both the good insulators and the faulty insulators by statistic of the data 本文利用檢測(cè)裝置,在實(shí)驗(yàn)室和現(xiàn)場(chǎng)分別采集了大量電暈脈沖數(shù)據(jù),統(tǒng)計(jì)分析了有、無(wú)不良絕緣子時(shí)電暈信號(hào)的譜圖特征。
In order to verify the effectiveness of steep - front impulse voltage test in finding the internal faults of composite insulator , some insulators with faults , including conductive channel , semi - conductive channels , airy channel , partial little air bubble that occur separately at different place , are modeled . steep - front wave impulse voltage test is made for these faulty insulator and normal insulator 為了檢驗(yàn)陡波試驗(yàn)對(duì)于發(fā)現(xiàn)合成絕緣子內(nèi)部故障的有效性,分別模擬了絕緣子內(nèi)部不同部位有導(dǎo)電性、半導(dǎo)電性通道,小氣泡,金屬雜質(zhì),長(zhǎng)氣泡以及芯棒與護(hù)套間不粘連故障的絕緣子,并從三維靜電場(chǎng)計(jì)算和用不同陡度的陡波試驗(yàn)兩個(gè)方面進(jìn)行了驗(yàn)證。