Research on Unstructured Text Data Mining and Fault Classification Based on RNN-LSTM with Malfunction Inspection Report
Research on Unstructured Text Data Mining and Fault Classification Based on RNN-LSTM with Malfunction Inspection Report
复制标题
基于RNN-LSTM的带故障检查报告的非结构化文本数据挖掘与故障分类研究
DOI：
10.3390/en10030406
复制
发表时间：
2017-03
期刊：
影响因子：
3.2
通讯作者：
Liu Yilu
中科院分区：
文献类型：
--
作者：
Wei Daqian;Wang Bo;Lin Gang;Liu Dichen;Dong Zhaoyang;Liu Hesen;Liu Yilu
本文记录了电力变压器的状态维护（CBM），其分析依赖于两个基本数据组：结构化（例如，数字和分类）和非结构化（例如，自然语言文本叙述），这两个数据组占所需数据的80%。然而，由电网运行和维护记录的故障检查报告组成的非结构化数据构成了大量未开发的电力洞察来源。提出了一种基于深度学习的故障检测报告处理方法，该方法将面向文本数据挖掘的递归神经网络（RNN）与长短期记忆（LSTM）相结合。在本文中，通过在每个序列步骤复制目标的简单训练策略，建立了RNN-LSTM网络对检测数据建模的有效性。然后，在数据集中给出相应的故障标签，通过与原始数据标签和输出样本的比较，计算故障分类的准确率。实验结果可以反映在关键变量配置中如何选择关键参数以达到最优结果。故障识别的准确性表明，本文提出的方法可以为网格检测人员处理非结构化数据提供一种更有效的方法。
This paper documents the condition-based maintenance (CBM) of power transformers, the analysis of which relies on two basic data groups: structured (e.g., numeric and categorical) and unstructured (e.g., natural language text narratives) which accounts for 80% of data required. However, unstructured data comprised of malfunction inspection reports, as recorded by operation and maintenance of the power grid, constitutes an abundant untapped source of power insights. This paper proposes a method for malfunction inspection report processing by deep learning, which combines the text data mining–oriented recurrent neural networks (RNN) with long short-term memory (LSTM). In this paper, the effectiveness of the RNN-LSTM network for modeling inspection data is established with a straightforward training strategy in which we replicate targets at each sequence step. Then, the corresponding fault labels are given in datasets, in order to calculate the accuracy of fault classification by comparison with the original data labels and output samples. Experimental results can reflect how key parameters may be selected in the configuration of the key variables to achieve optimal results. The accuracy of the fault recognition demonstrates that the method we proposed can provide a more effective way for grid inspection personnel to deal with unstructured data.
登录
查看更多内容
DOI：
10.1109/icicic.2006.200
发表时间：
2006-08
期刊：
First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06)
影响因子：
--
作者：
H. Su;Qunzhan Li
通讯作者：
H. Su;Qunzhan Li
DOI：
10.1109/iccpct.2015.7159492
发表时间：
2015-03
期刊：
2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]
影响因子：
--
作者：
A. K. Reshmy;D. Paulraj
通讯作者：
A. K. Reshmy;D. Paulraj
DOI：
10.1109/mper.2002.4312484
发表时间：
2002-08
期刊：
IEEE Power Engineering Review
影响因子：
--
作者：
Mang-Hui Wang
通讯作者：
Mang-Hui Wang
DOI：
10.1109/tdei.2012.6396956
发表时间：
2012-12
影响因子：
3.1
作者：
Hui Ma;C. Ekanayake;T. K. Saha
通讯作者：
Hui Ma;C. Ekanayake;T. K. Saha
DOI：
10.1109/tsmcc.2008.2007253
发表时间：
2009
期刊：
IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)
影响因子：
--
作者：
A. Shintemirov;Wenhu Tang;Q. Wu
通讯作者：
A. Shintemirov;Wenhu Tang;Q. Wu