本文選題：礦用電連接器 + 串聯(lián)型故障電弧　； 參考：《電子測量與儀器學(xué)報(bào)》2017年08期

【摘要】：為提高煤礦井下供電系統(tǒng)的可靠性,在不同電壓、電流、功率因數(shù)、環(huán)境相對(duì)濕度條件下,開展了因機(jī)械振動(dòng)引發(fā)的串聯(lián)型故障電弧模擬實(shí)驗(yàn)。分析了不同實(shí)驗(yàn)參數(shù)對(duì)故障電弧的影響;提取串聯(lián)型故障電弧相鄰五周期電流信號(hào)中的過零點(diǎn)數(shù)、歸一化后的方差、協(xié)方差構(gòu)成特征向量;建立了基于隨機(jī)森林分類算法的串聯(lián)型故障電弧診斷模型,以正常運(yùn)行及故障電弧電流信號(hào)的特征向量構(gòu)成訓(xùn)練樣本和測試樣本作為隨機(jī)森林模型的輸入,對(duì)樣本進(jìn)行分類,進(jìn)而診斷是否發(fā)生串聯(lián)型故障電弧。結(jié)果表明,該方法能夠有效地實(shí)現(xiàn)礦用電連接器串聯(lián)型故障電弧的診斷。
[Abstract]:In order to improve the reliability of underground power supply system in coal mine, the series fault arc simulation experiment caused by mechanical vibration was carried out under different voltage, current, power factor and relative humidity. The influence of different experimental parameters on the fault arc is analyzed, and the number of zero-crossing points in the adjacent five-period current signal of the series fault arc is extracted, and the normalized variance and covariance constitute the eigenvector. A series fault arc diagnosis model based on stochastic forest classification algorithm is established. The training samples and test samples are used as input to the random forest model to classify the samples, which are composed of characteristic vectors of normal operation and fault arc current signals. Then diagnose whether the series fault arc occurs. The results show that the method can effectively diagnose the series fault arc of mine electrical connectors.
【作者單位】： 遼寧工程技術(shù)大學(xué)電氣與控制工程學(xué)院;遼寧工程技術(shù)大學(xué)安全學(xué)院;國網(wǎng)葫蘆島供電公司;
【基金】：國家自然科學(xué)基金(51674136) 遼寧工程技術(shù)大學(xué)市場調(diào)研基金(20160067T) 國家大學(xué)生創(chuàng)新創(chuàng)業(yè)計(jì)劃訓(xùn)練項(xiàng)目(201610147000028)資助
【分類號(hào)】：TD611.3
，

本文編號(hào)：1811481