基于可闻声波信号分析的配电变压器内部绝缘缺陷识别方法

Recognition Method of Insulation Defects in Distribution Transformers Based on Audible Sound Signal Analysis

本文提出了一种基于可闻声波信号分析的配电变压器内部绝缘缺陷识别方法。首先对配电变压器内部绝缘缺陷放电产生的可闻声波信号采用谐波小波变换进行多尺度分解,再提取各尺度信号的高阶累积量组合成轨迹矩阵进行奇异值分解,选择奇异值序列矩阵的最大值和奇异熵作为特征参数,最后将特征参数组合成特征向量输入到支撑向量机分类器中进行缺陷类型识别。通过实验室内模拟配电变压器内部绝缘缺陷放电故障验证了本文提出方法的有效性,且识别准确率不会在高斯白噪声干扰的情况下降低。

This paper proposes a recognition method of insulation defects in distribution transformers based on audible sound signal analysis.At first,audible sound signals produced by insulation defects in distribution transformers are analyzed by multiple scale decomposition with harmonic wavelet transform.The higher-order cumulants extracted from each scale signal are composed as a trajectory matrix,and singular value sequence matrix of this trajectory matrix is obtained by singular value decomposition.The maximum value and singular entropy of singular value sequence matrix are selected as the feature parameters.These feature parameters are extracted from audible sound signals and inputted to the support vector machine classifier for defect type recognition.The effectiveness of the proposed method is verified by simulating the discharge faults of the insulation defects of the distribution transformer in the laboratory.In addition,the recognition accuracy is not reduced under the interference of the Gaussian white noise.