引用本文: | 聂晓音,谢刚,李洋,等.基于栈式相关性稀疏自编码的电力通信网故障诊断[J].电力系统保护与控制,2019,47(19):158-163.[点击复制] |
NIE Xiaoyin,XIE Gang,LI Yang,et al.Fault diagnosis of power communication network based on stacked relational sparse autoencoder[J].Power System Protection and Control,2019,47(19):158-163[点击复制] |
|
摘要: |
针对电力通信网故障的特征自学习提取与诊断问题,提出一种栈式相关性稀疏自编码(Stacked Relational Sparse Autoencoder, SRAE)深度神经网络的电力通信网故障诊断方法。将电力通信网中MIB(Management Information Base)变量状态数据编码为二进制序列作为训练数据,浅层单一的自编码网络对故障的自学习、特征提取能力不足。因此,首先将稀疏性限制和输入数据相关性限制融入自编码网络,构成相关性稀疏自编码神经网络(Relational Sparse Autoencoder, RAE)。然后将其层层堆栈,并在最后一层隐含层后添加分类器,构成SRAE。最后,以路由器之间的连接故障为例进行仿真实验。实验结果表明所提出的故障诊断方法准确率平均值达到99.625%,具有较高且稳定的诊断准确性。 |
关键词: 电力通信网 故障诊断 相关性 稀疏性 自编码 |
DOI:10.19783/j.cnki.pspc.181285 |
投稿时间:2018-10-16修订日期:2018-12-05 |
基金项目:山西省重点研发计划重点项目资助(201703D 111027);国网山西省电力公司科学技术项目资助 |
|
Fault diagnosis of power communication network based on stacked relational sparse autoencoder |
NIE Xiaoyin,XIE Gang,LI Yang,ZHANG Bo |
(School of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China;Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China;Department of Communications State Grid Information & Telecommunication Company of SEPC, Taiyuan 030001, China) |
Abstract: |
Aiming at the self-learning of fault feature and fault diagnosis in power communication network, a fault diagnosis method based on Stack Relational Sparse Autoencoder (SRAE) deep neural network is proposed. Considering that Management Information Base (MIB) data in power communication network is encoded into binary sequence as training data, the self-learning and feature extraction ability of shallow single autoencoder is insufficient. Therefore, the sparsity restriction and input data relational restriction are integrated into autoencoder to form a Relational Sparse Autoencoder (RAE); Then, it is stacked layer by layer, and the classifiers are added after the last hidden layer to form a SRAE; finally, a simulation experiment is carried out with the connection fault between routers. The experimental results show that the average accuracy of the proposed method is 99.625%, which has high and stable diagnostic accuracy. This work is supported by Key Project of Shanxi Province Key Research and Development Plan (No. 201703D111027) and Science and Technology Project of State Grid Shanxi Province Electric Power Company. |
Key words: power communication network fault diagnosis relational sparse autoencoder |