北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (4): 34-40.doi: 10.13190/j.jbupt.2020-271

• 论文 • 上一篇    下一篇

基于层次化类别嵌入的电力ICT系统故障分类

李建桂1, 梁越1, 高鹏飞1, 刘绍华2, 马应龙1   

  1. 1. 华北电力大学 控制与计算机工程学院, 北京 102206;
    2. 北京邮电大学 电子工程学院, 北京 100876
  • 收稿日期:2020-12-21 发布日期:2021-07-13
  • 通讯作者: 马应龙(1976-),男,教授,E-mail:yinglongma@ncepu.edu.cn. E-mail:yinglongma@ncepu.edu.cn
  • 作者简介:李建桂(1996-),女,硕士生.
  • 基金资助:
    国家重点研发计划项目(2018YFC0831404;2018YFC0830605)

A Hierarchical Category Embedding Based Approach for Fault Classification of Power ICT System

LI Jian-gui1, LIANG Yue1, GAO Peng-fei1, LIU Shao-hua2, MA Ying-long1   

  1. 1. School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;
    2. School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2020-12-21 Published:2021-07-13

摘要: 为解决电力信息通信客服系统在故障研判时存在故障分类准确率低甚至误分的问题,提出基于层次化类别嵌入的文本分类方法,进行电力信息通信系统故障识别.首先,基于电力信息通信系统故障的用户保修工单文本数据构建电力信息通信系统层次化电力故障标签;其次,提出了基于层次化深层金字塔卷积神经网络和基于层次化中断循环神经网络2种层次化文本分类方法,采用层次化类别嵌入方法逐层进行故障类型分类.实验结果表明,基于层次化深层金字塔卷积神经网络的方法效果最优,可以提供高效、准确的故障识别服务.

关键词: 电力信息通信客服系统, 电力文本分类, 层次化文本分类, 类别嵌入

Abstract: To solve the low classification accuracy oreven misclassification issue in fault diagnosis, a text classification method based on hierarchical category embedding is proposed in information and communication technology (ICT) customer service systems. First, a hierarchical label system is constructed for the failure data in power ICT systems based on the textual data of the work orders.Then, hierarchical deep pyramid convolutional neural networks (HDPCNN) and hierarchical disconnected recurrent neural networks are proposed, which adopt hierarchical category embedding technique for level-by-level fault type classification. The experimental results show that the hierarchical text classification algorithm HDPCNN has the best classification accuracy, which can provide efficient and accurate services for fault type recognition.

Key words: power information and communication technology customer service system, power text classification, hierarchical text classification, category embedding

中图分类号: