

浏览全部资源
扫码关注微信
1.浙江工业大学信息工程学院,浙江省杭州市 310014
2.科润智能控制股份有限公司,浙江省衢州市 324100
Received:12 January 2022,
Revised:2022-05-27,
Published Online:10 April 2023,
Published:25 May 2023
移动端阅览
郭方洪,刘师硕,吴祥等.基于联邦学习的含不平衡样本数据电力变压器故障诊断[J].电力系统自动化,2023,47(10):145-152.
GUO Fanghong,LIU Shishuo,WU Xiang,et al.Federated Learning Based Fault Diagnosis of Power Transformer with Unbalanced Sample Data[J].Automation of Electric Power Systems,2023,47(10):145-152.
郭方洪,刘师硕,吴祥等.基于联邦学习的含不平衡样本数据电力变压器故障诊断[J].电力系统自动化,2023,47(10):145-152. DOI: 10.7500/AEPS20220112003.
GUO Fanghong,LIU Shishuo,WU Xiang,et al.Federated Learning Based Fault Diagnosis of Power Transformer with Unbalanced Sample Data[J].Automation of Electric Power Systems,2023,47(10):145-152. DOI: 10.7500/AEPS20220112003.
基于海量样本数据的深度神经网络可以显著提升电力变压器的故障诊断效果,但实际环境中各变压器本地数据被“数据孤岛”隔离,难以进行集中式深度训练。联邦学习可以实现多源数据的共同建模,但各变压器的非独立同分布不平衡数据会使算法性能严重下降。针对上述问题,提出一种基于联邦学习的含不平衡样本数据电力变压器故障诊断机制。与传统深度学习集中训练方式不同,文中采用多个参与者分布训练方式。每个参与者采用LeNet-5深度神经网络进行本地训练,中央服务器将本地模型进行聚合,同时引入改进的数据共享策略对云端共享数据进行选择性下发,以降低非独立同分布数据的不平衡性。实验结果证明,该机制实现了各变压器独立且不平衡数据的协同训练,对变压器故障类型的诊断精度可达到97%。
The deep neural network based on massive sample data can significantly improve the fault diagnosis effect of power transformers
but in the actual environment
the local data of each transformer are isolated by “data islands”
which makes it difficult to conduct the centralized in-depth training. Federated learning can realize the common modeling of multi-source data. However
the non-independent and identically distributed unbalanced data of each transformer will seriously degrade the performance of the algorithm. Aiming at the above problems
a power transformer fault diagnosis mechanism with unbalanced sample data based on federated learning is proposed. Different from the traditional intensive training method of deep learning
this paper adopts the distributed training method of multiple participants. Each participant uses the LeNet-5 deep neural network for local training
the central server aggregates local models
and introduces an improved data sharing strategy to selectively distribute the cloud shared data to reduce the imbalance of non-independently and identically distributed data. The experimental results show that the mechanism realizes the cooperative training of each transformer with independent and unbalanced data
and the diagnosis accuracy of transformer fault types can reach 97%.
张育杰 , 李典阳 , 冯健 , 等 . 基于多模型选择性融合的变压器在线故障诊断 [J]. 电力系统自动化 , 2021 , 45 ( 13 ): 95 - 101 .
ZHANG Yujie , LI Dianyang , FENG Jian , et al . On-line fault diagnosis for transformer based on selective fusion of multiple models [J]. Automation of Electric Power Systems , 2021 , 45 ( 13 ): 95 - 101 .
陈图南 , 马凤翔 , 王刘芳 , 等 . 高分子渗透膜在变压器油中溶解气体分析中的应用 [J]. 电工技术学报 , 2022 , 37 ( 3 ): 750 - 766 .
CHEN Tunan , MA Fengxiang , WANG Liufang , et al . Application of polymers membrane in dissolved gas analysis: a review [J]. Transactions of China Electrotechnical Society , 2022 , 37 ( 3 ): 750 - 766 .
梁小冰 , 王耀龙 , 黄萍 , 等 . 基于DGA的变压器故障诊断多专家融合策略 [J]. 电力系统自动化 , 2005 , 29 ( 18 ): 80 - 84 .
LIANG Xiaobing , WANG Yaolong , HUANG Ping , et al . Synthetic multi-expert in transformer fault diagnosis based on DGA [J]. Automation of Electric Power Systems , 2005 , 29 ( 18 ): 80 - 84 .
邹杰慧 . 基于新型编码隶属函数的变压器故障模糊诊断法 [J]. 电力自动化设备 , 2010 , 30 ( 7 ): 88 - 91 .
ZOU Jiehui . Fuzzy fault diagnosis of power transformer based on new coding membership function [J]. Electric Power Automation Equipment , 2010 , 30 ( 7 ): 88 - 91 .
马利洁 , 朱永利 , 郑艳艳 . 基于并行变量预测模型的变压器故障诊断及优化研究 [J]. 电力系统保护与控制 , 2019 , 47 ( 6 ): 82 - 89 .
MA Lijie , ZHU Yongli , ZHENG Yanyan . Research on transformer fault diagnosis and optimization based on parallel variable prediction model [J]. Power System Protection and Control , 2019 , 47 ( 6 ): 82 - 89 .
吴君 , 丁欢欢 , 马星河 , 等 . 改进自适应蜂群优化算法在变压器故障诊断中的应用 [J]. 电力系统保护与控制 , 2020 , 48 ( 9 ): 174 - 180 .
WU Jun , DING Huanhuan , MA Xinghe , et al . Application of improved adaptive bee colony optimization algorithm in transformer fault diagnosis [J]. Power System Protection and Control , 2020 , 48 ( 9 ): 174 - 180 .
吴杰康 , 覃炜梅 , 梁浩浩 , 等 . 基于自适应极限学习机的变压器故障识别方法 [J]. 电力自动化设备 , 2019 , 39 ( 10 ): 181 - 186 .
WU Jiekang , QIN Weimei , LIANG Haohao , et al . Transformer fault identification method based on self-adaptive extreme learning machine [J]. Electric Power Automation Equipment , 2019 , 39 ( 10 ): 181 - 186 .
方涛 , 钱晔 , 郭灿杰 , 等 . 基于天牛须搜索优化支持向量机的变压器故障诊断研究 [J]. 电力系统保护与控制 , 2020 , 48 ( 20 ): 90 - 96 .
FANG Tao , QIAN Ye , GUO Canjie , et al . Research on transformer fault diagnosis based on a beetle antennae search optimized support vector machine [J]. Power System Protection and Control , 2020 , 48 ( 20 ): 90 - 96 .
赵晋泉 , 夏雪 , 徐春雷 , 等 . 新一代人工智能技术在电力系统调度运行中的应用评述 [J]. 电力系统自动化 , 2020 , 44 ( 24 ): 1 - 10 .
ZHAO Jinquan , XIA Xue , XU Chunlei , et al . Review on application of new generation artificial intelligence technology in power system dispatching and operation [J]. Automation of Electric Power Systems , 2020 , 44 ( 24 ): 1 - 10 .
杨涛 , 黄军凯 , 许逵 , 等 . 基于深度学习的变压器故障诊断方法研究 [J]. 电力大数据 , 2018 , 21 ( 6 ): 23 - 30 .
YANG Tao , HUANG Junkai , XU Kui , et al . Diagnosis method of power transformer fault diagnosis method based on deep learning [J]. Power Systems and Big Data , 2018 , 21 ( 6 ): 23 - 30 .
赵丙镇 , 陈智雨 , 闫龙川 , 等 . 基于区块链架构的电力业务交易数据隐私保护 [J]. 电力系统自动化 , 2021 , 45 ( 17 ): 20 - 26 .
ZHAO Bingzhen , CHEN Zhiyu , YAN Longchuan , et al . Privacy protection of power business transaction data based on blockchain framework [J]. Automation of Electric Power Systems , 2021 , 45 ( 17 ): 20 - 26 .
BLANCO-JUSTICIA A , DOMINGO-FERRER J , MARTÍNEZ S , et al . Achieving security and privacy in federated learning systems: survey, research challenges and future directions [J]. Engineering Applications of Artificial Intelligence , 2021 , 106 : 104468 .
李鉴 , 邵云峰 , 卢燚 , 等 . 联邦学习及其在电信行业的应用 [J]. 信息通信技术与政策 , 2020 , 46 ( 9 ): 35 - 41 .
LI Jian , SHAO Yunfeng , LU Yi , et al . Overview of federal learning and its application in telecom industry [J]. Information and Communications Technology and Policy , 2020 , 46 ( 9 ): 35 - 41 .
LI X , HUANG K X , YANG W H , et al . On the convergence of FedAvg on non-IID data [EB/OL]. [ 2021-05-15 ]. https://arxiv.org/abs/1907.02189 https://arxiv.org/abs/1907.02189 .
许豪灿 , 李基拓 , 陆国栋 . 由LeNet-5从单张着装图像重建三维人体 [J]. 浙江大学学报(工学版) , 2021 , 55 ( 1 ): 153 - 161 .
XU Haocan , LI Jituo , LU Guodong . Reconstruction of three-dimensional human bodies from single image by LeNet-5 [J]. Journal of Zhejiang University (Engineering Science) , 2021 , 55 ( 1 ): 153 - 161 .
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .
SHASHIDHAR R , PATILKULKARNI S . Visual speech recognition for small scale dataset using VGG16 convolution neural network [J]. Multimedia Tools and Applications , 2021 , 80 ( 19 ): 28941 - 28952 .
PETROV D , MARSHALL N , VANCOILLIE L , et al . Anthropomorphic ResNet18 for multi-vendor DBT image quality evaluation [C]// Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment , February 15-20 , 2020 , Houston, USA : 248 - 252 .
WANG Z , OATES T . Encoding time series as images for visual inspection and classification using tiled convolutional neural networks [C]// Workshops at the 29th AAAI Conference on Artificial Intelligence , January 25-26 , 2015 , Austin, USA .
LEE J , SUN J M , WANG F , et al . Privacy-preserving patient similarity learning in a federated environment: development and analysis [J]. JMIR Medical Informatics , 2018 , 6 ( 2 ): e20 .
ZHAO Y , LI M , LAI L , et al . Federated learning with non-IID data [EB/OL]. [ 2021-05-15 ]. https://arxiv.org/abs/1806.00582 https://arxiv.org/abs/1806.00582 .
0
Views
0
下载量
8
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621