首页|基于深度学习的一二次融合装备全场景故障研究

基于深度学习的一二次融合装备全场景故障研究

扫码查看
提出了基于深度学习的一二次融合装备全场景故障分析方法.针对低压配电网故障场景的类型和方式进行了说明,分析了影响配电网故障仿真的影响因素.针对低压配电网单相接地故障模型进行了说明,建立了小电阻接地系统模型、消弧线圈接地系统模型,分析二者在模拟故障时的影响因素.基于深度学习技术提出了卷积神经网络的故障场景诊断方式,结合一二次设备融合装置的功能特点进行了流程分析.针对仿真分析验证了所提出故障场景模拟在数据准确率以及训练数据结果方面的有效性.
Research on Security Check of Interconnected Grid Dispatching Considering Electricity Spot Market
A method for full-scenario fault analysis of primary and secondary integrated equipment based on deep learning is proposed.Types and methods of fault scenarios in low-voltage distribution networks are explained,and factors affecting the simulation of distribu-tion network faults are analyzed.The single-phase-to-ground fault model for low-voltage distribution networks is detailed,and models for both a small resistance grounding system and an arc suppression coil grounding system are established,with an analysis of the influen-cing factors during fault simulation for both systems.A fault scenario diagnosis approach using convolutional neural networks is proposed based on deep learning technology,and a process analysis is carried out,integrating the functional characteristics of primary and second-ary equipment integration devices.The effectiveness of the proposed fault scenario simulation in terms of data accuracy and training data results is validated through simulation analysis.

deep learningprimary and secondary integrationfault scenario simulationground fault

徐启源、林心昊、徐全、喻磊、马楠、刘胤良、雷金勇

展开 >

深圳供电局有限公司,广东 深圳 518022

南方电网科学研究院有限责任公司,广东 广州 510663

深度学习 一二次融合 故障场景模拟 接地故障

南方电网公司科技项目

090000KK52200128

2024

电子器件
东南大学

电子器件

CSTPCD
影响因子:0.569
ISSN:1005-9490
年,卷(期):2024.47(1)
  • 10