Switch cabinet state evaluation method and device
A state assessment, switch cabinet technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of artificial setting of initial parameters, difficulty in dealing with non-spherical clusters, and the influence of clustering effects, and achieve reasonable improvement. good effect of gender and clustering
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] figure 1 It is a flow chart of a method for assessing the state of a switchgear provided in Embodiment 1 of the present invention. This embodiment is applicable to evaluating the health state of a switchgear. The method can be performed by a device for evaluating the state of a switchgear, and specifically includes the following steps:
[0046] S110. Obtain live detection data of the switch cabinet.
[0047] Specifically, the faults of the switchgear are mainly insulation faults. Therefore, when evaluating the health status of the switchgear, the insulation state of the switchgear can be mainly evaluated. At this time, the live detection data of the switchgear mainly includes the Insulation state data. For example, the live detection data of the switchgear may include TEV detection data and ultrasonic detection data, which are used to reflect the insulation status of the switchgear. In addition, the TEV test data and ultrasonic test data may include the data of measur...
Embodiment 2
[0055] figure 2 It is a flow chart of a method for evaluating the state of a switchgear provided in Embodiment 2 of the present invention. On the basis of the above embodiments, the method includes:
[0056] S210. Obtain live detection data of the switch cabinet.
[0057] S220. Perform preprocessing on the electrification detection data.
[0058] Specifically, the electrification detection data may include various types of data, and a multi-dimensional feature data set is first constructed for the electrification detection data. For example, live detection data includes TEV detection data, ultrasonic detection data, environmental state temperature data, environmental state humidity data, and historical operation time data. A new data set is established for the above five state feature quantities, and the five sets of feature quantities The data sets are respectively represented by k*1 order column vectors. Exemplarily, the data set of TEV detection data is U=[U (1) u (2)...
Embodiment 3
[0094] image 3 It is a flow chart of a switchgear state evaluation method provided by Embodiment 3 of the present invention. On the basis of the above-mentioned embodiments, the method includes:
[0095] S310. Obtain live detection data of the switch cabinet.
[0096] S320. Using the DBSCAN clustering algorithm to classify the states of the live detection data, so as to determine the states of the switchgear.
[0097] S330. Calculate the silhouette coefficient of the DBSCAN clustering algorithm according to the clusters of the data samples.
[0098] Specifically, calculate the silhouette coefficient of the DBSCAN clustering algorithm according to the clusters of data samples, including:
[0099] Calculate the average distance between the sample points in the cluster and other sample points in the same cluster, which is the intra-cluster dissimilarity of the sample points in the cluster.
[0100] Specifically, the sample point X in the cluster j The average distance to oth...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


