Relay protection is the first line guarding the power systems. Defect rating, timely and accurate play an important role in improving the operation and maintenance efficiency of relay protection devices. However, the current defect rating is mainly artificial, lack of intelligent assistant decision-making, thus engages a risk of erroneous rating. This paper studies the defect rating method based on decision tree for line protection devices. Specifically, the defect rating requirements of relay protection and data characteristics of line protection defects in a certain power grid is analyzed firstly. Secondly, the decision tree method applied to defect rating with the ordinary defect attributes is introduced. Finally, the defect record data of different production models of line protection devices from the same manufacturer is used to model the decision tree and discusses the results. The results show that the proposed method has the preliminary capability of defect rating and can be severed as an assist in field device defect rating.
[1]
Zhe Chen,et al.
A Systematic Approach for Dynamic Security Assessment and the Corresponding Preventive Control Scheme Based on Decision Trees
,
2014,
IEEE Transactions on Power Systems.
[2]
Huang Shaofeng.
Time-varying Failure Rate Estimation of Relay Protection Devices and Their Regional Differences Analysis
,
2012
.
[3]
Li Zhi-jun.
Study on the reliability evaluation of protection devices based on defects analysis
,
2013
.
[4]
J. Ross Quinlan,et al.
Induction of Decision Trees
,
1986,
Machine Learning.
[5]
Xue Anchen,et al.
Research on Markov Model Based Risk Assessment of Protective Relaying for High Voltage Transmission Line
,
2014
.
[6]
Li Jian-qiang.
Electric load forecast based on decision tree and expert system
,
2005
.