基于PLS-SVM的开关柜局部放电检测方法

发布时间：2018-08-20 10:06

【摘要】：超声波检测法是高压开关柜局部放电检测的一种有效方法,但目前基于超声波信号检测原理开发的局部放电检测产品主要有信号幅值检测、将信号降频至音频从而监听检测,具有检测结果不够准确、对检测人员要求较高等缺点。该研究提出了一种基于偏最小二乘(partial least squares,PLS)特征降维和支撑向量机(support vector machine,SVM)的开关柜局部放电检测方法,首先计算超声音频信号的声学特征,并采用PLS进行降维处理,然后采用SVM分类器来区分局放和非局放音频信号。实验结果表明,所提方法比传统阈值方法具有更高的识别准确率,并且降低了对检测人员的要求,具有更好的普适性。
[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.
【作者单位】： 深圳供电局有限公司;
【基金】：南方电网公司科技项目(K-SZ2014-006)“基于大数据的配电网设备全维度监测及智能巡检研究与应用”~~
【分类号】：TM591
，

本文编号：2193228