摘要
针对变压器与中压开关柜传统绝缘状态检测方法依赖人工的问题,本文基于可听声声音识别方法,通过将电力设备放电故障声音与正常工况声音、环境噪声进行混叠制作样本集,以模拟真实电力设备运行环境;对故障声音进行预处理后,使用声谱图提取声音的短时频率、能量分布等特征,构建声谱图数据集,结合改进的卷积神经网络实现对放电故障的检测;通过加入注意力机制,调节指数衰减学习率、数据集样本数量、音频采样率等方式进一步提升网络的精度,最终设计的网络模型识别准确率最高可达99.2%,相比其他检测方法优势明显,可实现对放电故障的在线检测。
In view of the problem that the traditional insulation state detection methods of transformers and mediumvoltage switchgear rely on manual labor,this paper based on the audible sound recognition method,by mixing the discharge fault sound of power equipment with the sound of normal conditions and environmental noise to make a sample set,in order to simulate the real operating environment of power equipment.After the fault sound is preprocessed,the spectrogram is used to extract the short-time frequency and energy distribution features of the sound,and the spectrogram data set is constructed.Combined with the improved convolutional neural network,the discharge fault detection is realized.By adding the attention mechanism,adjusting the exponential decay learning rate,the number of data set samples,the audio sampling rate and other ways to further improve the accuracy of the network model,the final design of the network model identification accuracy up to 99.2%,compared with other detection methods have obvious advantages,can realize the online detection of discharge faults.
作者
汪志成
王泽旺
朱梦帆
纪荣焕
张斌
Wang Zhicheng;Wang Zewang;Zhu Mengfan;Ji Ronghuan;Zhang Bin(East China University of Technology,Nanchang 330013,China;Quanzhou Weidun Electric Co.,Ltd.,Quanzhou 362012,China)
出处
《电子测量技术》
北大核心
2023年第20期148-155,共8页
Electronic Measurement Technology
基金
江西省科技合作专项重点项目(20212BDH80008)
科技部常规性科技援外项目(KY201702002)
江西省重点研发计划项目(20181BBE58006)
国家自然科学基金(12165001)项目资助
关键词
电力设备
局部放电
声谱图
声音识别
卷积神经网络
electric power equipment
partial discharge
spectrogram of sound
voice recognition
convolutional neural network
