基于稀疏差异深度信念网络的绝缘子故障识别算法  

A faulted insulator identification algorithm of sparse difference-based deep belief network

作　　者：高强[1] 阳武[1] 李倩[1] 

机构地区：[1]华北电力大学电气与电子工程学院,河北保定071003

出　　处：《电测与仪表》2016年第1期19-25,共7页Electrical Measurement & Instrumentation

摘　　要：针对深度信念网络(DBN)的识别准确率比较低的问题,引入了基于模糊隶属函数的差异理论,提出了一种基于稀疏差异的深度信念网络图像分类新方法,简称D-DBN方法,并将其应用在了绝缘子故障识别中。差异理论有扩大低灰度区域,缩小高灰度区域的优点,更符合人眼的视觉特性。首先将图像的灰度特征矩阵转换成差异表示矩阵,并对其进行均值化、归一化和稀疏化,然后利用DBN网络对得到的差异特征进行训练,学习数据更本质的特征,从而达到提高识别性能的目的。在MNIST和SVHN库上对不同样本规模和不同网络结构进行实验,识别结果证明,与传统DBN和其它改进方法相比,本文算法取得了最好的识别效果。最后,将DDBN方法应用到绝缘子故障识别中。Aiming at the problem of the low recognition accuracy of deep belief network,the difference theory based on fuzzy membership function is introduced,a new image classification method,or D-DBN for short,of deep belief network based on the sparse difference is proposed in this paper,and its application on insulator fault identification is put forward. Because the difference theory has the advantage of widening the low gray areas,and reducing the high gray areas,it is more consistent with characteristics of human vision. At first,the images were changed from gray feature matrices to the difference feature matrices,and then,the difference matrices were made mean,normalization and sparse. Secondly,the difference features were trained by DBN to learn more intrinsic characteristics of data,so as to achieve the aim of improving recognition performance. The identification results on MNIST and SVHN database with different sample sizes and different network structures demonstrate that the proposed method achieves better recognition performance after comparing with the traditional DBN method and other improved methods. At last,a method of DDBN was applied in the fault identification of insulators.

关 键 词：深度信念网络 差异 图像分类 绝缘子 故障识别 

分 类 号：TM216[一般工业技术—材料科学与工程]