Abstract
Non-intrusive transmission cable monitoring is the latest advanced measurement technology for smart grids. It only samples the voltage on a certain part of the transmission cable, and uses intelligent algorithms to identify the quality, which has obvious advantages of low construction and maintenance costs. This paper established a model based on multi-channel data fusion and transfer learning to classify the quality of transmission cable. First, we used the ANSYS Maxwell simulation platform to obtain ten kinds of specific fault data, which solved the time cost of manual labeling. Then, we performed multi-channel data fusion on the original data, which strengthened the expression of important features and was more conducive to the training of the model. Next, we used Depthwise Separable Convolution (DSC) to speed up the learning of the model, and improve the accuracy of the classification. Finally, we transferred the model trained with simulation data into the real scene, realized the transfer from multi classes to two classes, the effectiveness was proved in experiments. The accuracy of the model built in the article to classify the quality of the transmission cables is 98.1%.
Highlights
With the continuous deepening construction of smart grid, the power industry has become a basic industry related to the national economy and people’s livelihood
The model obtained by training simulation data can be applied to the actual sampled data for fault judgment. This method mainly used the idea of transfer learning [15], which overcomed the problem of insufficient data in real scenarios and saved time on labelling [16]
This paper established a transmission cable quality classification model based on multi-channel fusion and transfer learning
Summary
With the continuous deepening construction of smart grid, the power industry has become a basic industry related to the national economy and people’s livelihood. Most of the quality detection methods for the transmission cable based on deep learning use labeled data to analysis, and the data used mainly come from real scenes. The model obtained by training simulation data can be applied to the actual sampled data for fault judgment This method mainly used the idea of transfer learning [15], which overcomed the problem of insufficient data in real scenarios and saved time on labelling [16]. A large amount of labeled and noiseless data was obtained through simulation We used these data to train the model to learn characteristics of fault types, and transfer the trained classifier to the data collected in the real scene to classify the quality of the transmission cable
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
