A novel switchgear state assessment framework based on improved fuzzy C-means clustering method with deep belief network

Abstract

Due to the problems such as fuzzy state assessment grading boundaries, the recognition accuracy is low when using traditional fuzzy techniques to grade the switchgear state. To address this problem, this paper proposes a switchgear state assessment and grading method based on deep belief network (DBN) and improved fuzzy C-means clustering (IFCM). Firstly, the switchgear state information data are processed by normalization method; then the feature parameters are extracted from the switchgear state information data by using DBN, and finally the extracted feature parameters are categorised according to the condition of switchgear equipment through clustering using IFCM. The experimental results show that the accuracy of the method in assessing the switchgear state under small sample conditions reaches 94, which exceeds the accuracy of other switchgear state assessment grading methods currently in use.

Analysis of the Operational Reliability of Different Types of Switching Substations Using the Monte Carlo Method

“…Assessing the health of switchgears is critical, as degraded equipment poses threats to grid security and reliability [6]. Numerous studies, including [7][8][9][10], explore various aspects of switchgear health assessment, using methods from contact resistance measurement to vibration signal analysis and partial discharge measurement.…”

“…[7][8][9][10][11][12][13][14][15][16] illustrate the diverse topologies characteristic of double-busbar systems.…”