CLC number: TM76; TP181
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2019-11-12
Cited: 0
Clicked: 7306
Hui-fang Wang, Zi-quan Liu. An error recognition method for power equipment defect records based on knowledge graph technology[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(11): 1564-1577.
@article{title="An error recognition method for power equipment defect records based on knowledge graph technology",
author="Hui-fang Wang, Zi-quan Liu",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="20",
number="11",
pages="1564-1577",
year="2019",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1800260"
}
%0 Journal Article
%T An error recognition method for power equipment defect records based on knowledge graph technology
%A Hui-fang Wang
%A Zi-quan Liu
%J Frontiers of Information Technology & Electronic Engineering
%V 20
%N 11
%P 1564-1577
%@ 2095-9184
%D 2019
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1800260
TY - JOUR
T1 - An error recognition method for power equipment defect records based on knowledge graph technology
A1 - Hui-fang Wang
A1 - Zi-quan Liu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 20
IS - 11
SP - 1564
EP - 1577
%@ 2095-9184
Y1 - 2019
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1800260
Abstract: To recognize errors in the power equipment defect records in real time, we propose an error recognition method based on knowledge graph technology. According to the characteristics of power equipment defect records, a method for constructing a knowledge graph of power equipment defects is presented. Then, a graph search algorithm is employed to recognize different kinds of errors in defect records, based on the knowledge graph of power equipment defects. Finally, an error recognition example in terms of transformer defect records is given, by comparing the precision, recall, F1-score, accuracy, and efficiency of the proposed method with those of machine learning methods, and the factors influencing the error recognition effects of various methods are analyzed. Results show that the proposed method performs better in error recognition of defect records than machine learning methods, and can satisfy real-time requirements.
[1]Amit S, 2012. Introducing the Knowledge Graph: Things, not Strings. https://googleblog.blogspot.com/2012/05/ introducing-knowledge-graph-things-not.html
[2]Baum LE, Petrie T, 1966. Statistical inference for probabilistic functions of finite state Markov chains. Ann Math Stat, 37(6):1554-1563.
[3]Bizer C, Lehmann J, Kobilarov G, et al., 2009. DBpedia—a crystallization point for the Web of data. J Web Semant, 7(3):154-165.
[4]Bollacker K, Cook R, Tufts P, 2007. Freebase: a shared database of structured general human knowledge. Proc 22nd National Conf on Artificial Intelligence, p.1962-1963.
[5]Cao J, Chen LS, Qiu J, et al., 2017. Semantic frame work- based defect text mining technique and application in power grid. Power Grid Tech, 41(2):637-643 (in Chinese).
[6]Chen LW, Feng YS, Zhao DY, 2013. Extracting relations from the Web via weakly supervised learning. J Comput Res Dev, 50(9):1825-1835 (in Chinese).
[7]Devaney M, Ram A, Qiu H, et al., 2005. Preventing failures by mining maintenance logs with case-based reasoning. Proc 59th Meeting of the Society for Machinery Failure Prevention Technology, p.1-10.
[8]Dhillon BS, Liu Y, 2006. Human error in maintenance: a review. J Qual Mainten Eng, 12(1):21-36.
[9]Goodwin T, Harabagiu SM, 2013. Automatic generation of a qualified medical knowledge graph and its usage for retrieving patient cohorts from electronic medical records. Proc IEEE 7th Int Conf on Semantic Computing, p.363- 370.
[10]Grover A, Leskovec J, 2016. node2vec: scalable feature learning for networks. Proc 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.855-864.
[11]Hu XB, Tang XH, Tang FL, 2017. Analysis of investment relationships between companies and organizations based on knowledge graph. Proc 11th Int Conf on Innovative Mobile and Internet Services in Ubiquitous Computing, p.208-218.
[12]Huang YH, Zhou XX, 2015. Knowledge model for electric power big data based on ontology and semantic web. CSEE J Power Energy Syst, 1(1):19-27.
[13]IEC, 2014. International Electrotechnical Vocabulary (IEV): Generation, Transmission and Distribution of Electricity—Substations. International Electrotechnical Commission, Geneva.
[14]Lampert TA, Gançarski P, 2014. The bane of skew. Mach Learn, 97(1-2):5-32.
[15]Li WJ, Zhang P, Wei FR, et al., 2008. A novel feature-based approach to Chinese entity relation extraction. Proc 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies, p.89-92.
[16]Liddy DE, Symonenko S, Rowe S, 2013. Sublanguage analysis applied to trouble tickets. Proc 19th Int Florida Artificial Intelligence Research Society Conf, p.752-757.
[17]Liu Q, Li Y, Duan H, et al., 2016. Knowledge graph construction techniques. J Comput Res Dev, 53(3):582-600 (in Chinese).
[18]Liu ZQ, Wang HF, Cao J, et al., 2018. A classification model of power equipment defect texts based on convolutional neural network. Power Syst Technol, 42(2):644-650 (in Chinese).
[19]Lv SH, 2015. The Key Technology Research and Implementation of the Pinyin-to-Character Conversion System. MS Thesis, University of Electronic Science and Technology of China, Chengdu, China (in Chinese).
[20]Mikolov T, Chen K, Corrado G, et al., 2013. Efficient estimation of word representations in vector space. https://arxiv.org/abs/1301.3781
[21]Pujara J, 2017. Extracting knowledge graphs from financial filings: extended abstract. Proc 3rd Int Workshop on Data Science for Macro—Modeling with Financial and Economic Datasets, p.1-2.
[22]Q/GDW, 2013. Defects Description Specification of Power Transmission and Substation Equipment, Part 1: Power Substation Equipments, Q/GDW 1904.1-2013. State Grid Corporation of China (in Chinese).
[23]Qiu J, Wang HF, Lin DY, et al., 2015. Nonparametric regression-based failure rate model for electric power equipment using lifecycle data. IEEE Trans Smart Grid, 6(2):955-964.
[24]Qiu J, Wang HF, Ying GL, et al., 2016. Text mining technique and application of lifecycle condition assessment for circuit breaker. Autom Electron Power Syst, 40(6): 107-112 (in Chinese).
[25]Radeva A, Rudin C, Passonneau R, et al., 2009. Report cards for manholes: eliciting expert feedback for a learning task. Proc Int Conf on Machine Learning and Applications, p.719-724.
[26]Rotmensch M, Halpern Y, Tlimat A, et al., 2017. Learning a health knowledge graph from electronic medical records. Sci Rep, 7(1):1-11.
[27]Rudin C, Waltz D, Anderson RN, et al., 2012. Machine learning for the New York City power grid. IEEE Trans Patt Anal Mach Intell, 34(2):328-345.
[28]Rudin C, Ertekin Ş, Passonneau R, et al., 2014. Analytics for power grid distribution reliability in New York City. Interfaces, 44(4):351-439.
[29]Shi LX, Li SJ, Yang XR, et al., 2017. Semantic health knowledge graph: semantic integration of heterogeneous medical knowledge and services. Biomed Res Int, 2017:1- 12.
[30]Suchanek FM, Kasneci G, Weikum G, 2008. YAGO: a large ontology from Wikipedia and WordNet. J Web Semant, 6(3):203-217.
[31]Wei DQ, Wang B, Lin G, et al., 2017. Research on unstructured text data mining and fault classification based on RNN-LSTM with malfunction inspection report. Energies, 10(3):1-22.
[32]Xie C, Zou GP, Wang HF, et al., 2016. A new condition assessment method for distribution transformers based on operation data and record text mining technique. Proc China Int Conf on Electricity Distribution, p.1-7.
[33]Zheng J, Dagnino A, 2014. An initial study of predictive machine learning analytics on large volumes of historical data for power system applications. Proc IEEE Int Conf on Big Data, p.952-959.
Open peer comments: Debate/Discuss/Question/Opinion
<1>