【摘要】：超聲波檢測法是高壓開關柜局部放電檢測的一種有效方法,但目前基于超聲波信號檢測原理開發(fā)的局部放電檢測產品主要有信號幅值檢測、將信號降頻至音頻從而監(jiān)聽檢測,具有檢測結果不夠準確、對檢測人員要求較高等缺點。該研究提出了一種基于偏最小二乘(partial least squares,PLS)特征降維和支撐向量機(support vector machine,SVM)的開關柜局部放電檢測方法,首先計算超聲音頻信號的聲學特征,并采用PLS進行降維處理,然后采用SVM分類器來區(qū)分局放和非局放音頻信號。實驗結果表明,所提方法比傳統(tǒng)閾值方法具有更高的識別準確率,并且降低了對檢測人員的要求,具有更好的普適性。
[Abstract]:Ultrasonic detection is an effective method for detecting partial discharge of high voltage switchgear. However, at present, based on the principle of ultrasonic signal detection, partial discharge detection products mainly include signal amplitude detection, signal frequency reduction to audio frequency and monitoring detection. The test results are not accurate enough and the inspection personnel are required to be high. In this paper, a partial discharge detection method for switchgear based on partial least squares (partial least squares pls) feature reduction and support vector machine (support vector machine) is proposed. Firstly, the acoustic features of ultrasonic audio signal are calculated, and the dimension reduction is processed by PLS. Then the SVM classifier is used to divide the audio signal between local and non-PD. The experimental results show that the proposed method has higher recognition accuracy than the traditional threshold method, and reduces the requirements of the detection personnel, and has better universality.
【作者單位】： 深圳供電局有限公司;
【基金】：南方電網(wǎng)公司科技項目(K-SZ2014-006)“基于大數(shù)據(jù)的配電網(wǎng)設備全維度監(jiān)測及智能巡檢研究與應用”~~
【分類號】：TM591
，

本文編號：2193228