Research on transformer state recognition based on elastic vibration and deep leaning
In order to overcome the shortcomings of traditional transformer state recognition algorithms that require human intervention,this paper proposes a new state recognition method,which uses the One-Di-mensional Convolutional Neural Network(the 1D-CNN algorithm)to automatically extract the features and classify.The algorithm could automatically extract the signal features through three convolutional and poo-ling layer,expands the extracted features into a 1D vector through a fully connected layer,and finally clas-sifies the signals through a Softmax layer.Since the strong anti-interference capability of the elastic vibra-tion,a dataset of elastic vibration signals of a 500kV transformer is used to verify the proposed algorithm,and shows that the accuracy of the 1D-CNN algorithm is higher than BP,SVM and SAE in transformer state recognition.
NETL
NSTL
万方数据
