摘要
超声波检测技术在电力设备带电检测中具有广泛的应用前景,针对电力变压器和GIS组合电器局部放电过程中产生的超声波信号进行了检测分类研究。提出了一种局部放电超声波信号多阶段多分类模型。在模型的第一阶段,采用支持向量机将局部放电超声波信号分类为不同设备的信号;在模型的第二阶段,采用极限学习机对不同设备的局部放电超声波信号进行详细的多分类,还采用了粒子群算法对支持向量机与极限学习机的参数进行了优化。实验结果表明,所提的模型取得了较好的分类结果,实现了多种局部放电超声波信号的精细分类。
Ultrasonic detection technology has a wide range of application prospects in the live detection of power equipment. In this paper, the detection and classification of ultrasonic signals generated in the partial discharge process of power transformers and GIS combined appliances is studied. This paper proposes a multi-stage multiclassification model for partial discharge ultrasonic signal classification. In the first stage of the model, the support vector machine was used to classify the partial discharge ultrasonic signals into signals of different devices. In the second stage of the model, the extreme learning machine was used to carry out detailed multi-classification of the partial discharge ultrasonic signals of different devices. In this paper, particle swarm algorithm is also used to optimize the parameters of support vector machine and extreme learning machine. The experimental results show that the model proposed in this paper achieves good classification results and realizes the fine classification of various partial discharge ultrasonic signals.
作者
陈泓岩
李浩然
杨宇豪
冯泰棋
应东
CHEN Hongyan;LI Haoran;YANG Yuhao;FENG Taiqi;YING Dong(State Grid Yinchuan Power Supply Company,Yinchuan 750001,China)
出处
《电气应用》
2022年第12期38-43,共6页
Electrotechnical Application
关键词
电力设备
带电检测
局部放电
超声波
机器学习
power equipment
live detection
partial discharge
ultrasound
machine learning
