Prediction of line failure fault based on weighted fuzzy dynamic clustering and improved relational analysis

2018 Asia Conference on Energy and Environment Engineering

能源学;生态环境科学

Meng, Xiaocheng^1,2 ; Che, Renfei^1,2 ; Gao, Shi^1,2,3 ; He, Juntao^1,2

Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education, Jinan

250061, China^1

School of Electrical Engineering, Shandong University, Jinan

250061, China^2

State Grid Hebei Maintenance Branch, Shijiazhuang

050070, China^3

关键词: Coefficient of variation;    Corresponding weights;    Dynamic clustering;    Early warning analysis;    Gray relational degrees;    Historical information;    Relational analysis;    Weighted fuzzy clustering;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/133/1/012001/pdf
DOI  :  10.1088/1755-1315/133/1/012001

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

With the advent of large data age, power system research has entered a new stage. At present, the main application of large data in the power system is the early warning analysis of the power equipment, that is, by collecting the relevant historical fault data information, the system security is improved by predicting the early warning and failure rate of different kinds of equipment under certain relational factors. In this paper, a method of line failure rate warning is proposed. Firstly, fuzzy dynamic clustering is carried out based on the collected historical information. Considering the imbalance between the attributes, the coefficient of variation is given to the corresponding weights. And then use the weighted fuzzy clustering to deal with the data more effectively. Then, by analyzing the basic idea and basic properties of the relational analysis model theory, the gray relational model is improved by combining the slope and the Deng model. And the incremental composition and composition of the two sequences are also considered to the gray relational model to obtain the gray relational degree between the various samples. The failure rate is predicted according to the principle of weighting. Finally, the concrete process is expounded by an example, and the validity and superiority of the proposed method are verified.