An operation health status monitoring algorithm of special transformers based on BIRCH and Gaussian cloud methods

Abstract

The health status monitoring of special transformers is of great significance to ensure the secure operation of the distribution network and the power quality of special transformer users. Given this background, an operation health status monitoring algorithm of special transformers is proposed in this paper based on balanced iterative reducing and clustering using hierarchies (BIRCH) and Gaussian Cloud methods (GCM). The algorithm is composed of two parts, i.e., the offline and online parts. For the offline part, the operating indexes of special transformers are extracted based on historical operating data, and Gaussian clouds of normal operating conditions of the special transformers are determined by BIRCH clustering and Gaussian cloud methods. For the online part, Gaussian clouds of real-time operating conditions of special transformers are determined by BIRCH clustering and Gaussian cloud methods based on real-time operation data. Then, the monitoring results of operating health status are determined by the distance between the standard Gaussian clouds and the real-time Gaussian clouds of special transformers. Finally, case studies for actual special transformers are performed to verify the proposed method, and the results show that the proposed model can effectively identify the abnormal operation of the special transformer.