Transformer cluster management method and system

Abstract

The invention discloses a transformer cluster management method and system, and the method comprises the following steps of S1, obtaining a running log of a transformer, and constructing a first cluster management model sample set representing the basic features of cluster management based on the running log; and S2, optimizing the cluster management basic features in the first cluster management model sample set by using feature fusion to construct a second cluster management model sample set representing the optimal features of cluster management, and constructing a cluster management model for attributing a transformer to an optimal management cluster based on the second cluster management model sample set. According to the method, the transformers with similar machine account parameters and working condition data are divided into the same transformer cluster by adopting a hierarchical clustering algorithm, the difference of devices in the cluster is known through the mutual comparison of the transformer state monitoring data in the same cluster, which transformer is in an abnormal state can be quickly judged, and the anomaly detection accuracy is high.

Description

technical field [0001] The invention relates to the technical field of transformer management, in particular to a transformer cluster management method and system. Background technique [0002] The power transformer is one of the most important power transmission and transformation equipment in the power system. Its operating status is directly related to the safety and stability of the entire power system. The power transformer here is usually a transformer of 10KV or above, for example: a 10KV distribution transformer, 35KV and above transmission transformers, etc., so it is very important to ensure the reliable operation of transformers. With the rapid development of sensor technology and computer technology, real-time status monitoring and evaluation of transformers has gradually become possible. [0003] At present, the mainstream method of identifying whether the state of the transformer is abnormal is to monitor the core state quantities of the transformer online, an...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a transformer cluster management method and system to solve the problem that in the prior art, data is analyzed only based on manual experience such as thresholds, so that the utilization rate of the data is very low, and the due value of the data is buried, which eventually leads to Technical problems with low discrimination accuracy

Images