Assessment of interconnected power grid operation security based on grey correlation analysis

Liu, Xiaofei; Wang, Qi; Wang, Tianzheng; Zhang, Laifu

doi:10.1109/cecnet.2013.6703300

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…k-nearest neighbor (KNN) is an effective non-parametric classification algorithm based on statistics, which has the advantages of small sample size, short time consumption, accuracy, etc., and can quickly realize the warning of coal mine ventilation disasters [8][9][10]. In addition, combined with the grey correlation analysis (GCA), the dominant factors affecting disaster warning can be obtained on the basis of disaster warning, and a more comprehensive understanding of disaster warning can be obtained [11][12].…”

Section: Introductionmentioning

confidence: 99%

Warning Model of Coal Mine Ventilation Disaster Based on the Combination of K-Neighborhood-Gray Correlation Method and Its Application

Wang¹,

Chen²,

Gao³

2022

IJHT

View full text Add to dashboard Cite

The abnormalities in the mine ventilation system can reflect the risks and hidden dangers during the mine production. By combining the basic information of the mine and the ventilation monitoring data with the production status, the gas concentration and wind speed are used as the calculation indicators, and the k-nearest neighbor (KNN) is used to study the abnormal change characteristics of calculation indicators of mine ventilation system in different ventilation periods, and a ventilation hazard warning model was constructed and the model results were compared and validated. In addition, the dominant factors of the warning level were obtained by combining the grey correlation analysis (GCA). The results show that under different ventilation periods (easy ventilation period and difficult ventilation period), the correct rates of calculation and verification in easy ventilation period and difficult ventilation period are 95.65% and 97.82% respectively. It can be seen that the accuracy of the warning model is over 95%, which has good application and promotion value. Furthermore, the correlation coefficient of the wind speed in two periods is relatively high, which is indicating that the speed is the main indicator that affects the warning level. The research of this paper can provide theoretical support for realizing the intelligent management of mine risk in advance and short-term early warning.

show abstract

Section: Introductionmentioning

confidence: 99%