基于多层卷积神经网络 的变电站异常场景识别算法

针对卷积神经网络对小样本识别率较低的问题,引入置信度的概念,提出了一种基于多层卷积神经网络的图像分类方法,简称M_CNN,并将其应用在变电站异常场景识别中。依据网络对小样本的识别情况,设置置信度判决函数,对在已训练好的单层网络结构中难以识别的样本,重新进行特征的提取并训练下一层的网络,形成多层卷积神经网络结构,达到提高识别率的目的。在MNIST手写体数据库上对不同规模样本数进行实验,结果表明M_CNN模型在针对小样本识别时具有一定优越性,最后,将M_CNN模型应用在变电站异常场景识别中,取得了良好的效果。

A substation abnormal scene recognition algorithm based on multilayer convolution neural network

Aiming at the problem of low recognition rate of small samples by convolution neural network,the concept of confidence is introduced,and a new image classification method based on multi-layer convolution neural network is proposed,which is called M_CNN,and its application in substation abnormal scene recognition is put forward.the confidence decision function is set according to the network identification of the small sample,and the samples are picked out for which are difficult to identify in the trained single-layer network,re-extracted features and trained the next layer of the network,forming the multilayer convolution neural network structure,so as to achieve the aim of improving recognition performance.The identification results on MNIST database with different sample sizes demonstrate that M_CNN model has some superiority in identifying small samples.At last,the M_CNN model is applied in substation abnormal scene recognition and achieves pretty results.