Work

Big data analysis and state perception of power grid based on deep learning

Year: 2026

Type: article

Abstract: This study proposes an intelligent state perception method for power equipment based on multi-modal data fusion. By integrating the ResNet50 network and Region Proposal Network, a hierarchical deep neural network model is constructed to achieve accurate classification of power equipment states and early warning of abnormalities. The experimental results show that the mean average precision (mAP) of this method for the primary and secondary labels of power equipment reaches 93.7% and 87.3% respectively, significantly outperforming traditional models.

Source: Discover Computing

DOI: 10.1007/s10791-026-10046-8

Authors: Xufei Liu, Shuling Wang, Wenchao Qin

Institution: Yunnan Power Grid Co., Ltd. (China)

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDGs: Industry, innovation and infrastructure, Affordable and clean energy

Open Access status: gold

Estimated APC paid: $1,520