Distribution transformer data acquisition anomaly discrimination method based on multi-criterion fusion

Abstract

The invention discloses a distribution transformer data acquisition anomaly discrimination method based on multi-criterion fusion. The method comprises the following steps: carrying out statistical analysis on breakpoints and abnormal points of the acquired data and actual field operation data conditions; respectively using a prototype clustering method, a density clustering method, a probabilitydensity method, a deep learning method and the like to discriminate abnormal values, and two-out-of-four verification results are carried out on four models, that is, two models of the four models considering that a point to be judged is an abnormal point, and the point to be judged being an abnormal point. According to the method, the problems of high difficulty, low efficiency, low real-time performance and the like when a traditional machine learning method is used for processing mass data are solved.

Description

technical field [0001] The invention belongs to the technical field of power system distribution transformer data processing, and in particular relates to a method for discriminating abnormal data used in distribution transformers based on multi-criteria fusion. Background technique [0002] With the widespread application of computer, communication, and sensing technologies, the continuous advancement of distribution network operation monitoring services, and the deployment of a large number of monitoring and metering devices, the monitoring of the distribution and transformation station area has obtained massive operation data, user power consumption data and equipment status data. These data are analyzed, mined, extracted and processed to realize the safe and economical operation of the distribution and transformation station area, improve the service quality, and expand the electricity and electricity bill business, which have become the challenges faced by the distributi...

AI Technical Summary

Problems solved by technology

[0015] The purpose of the present invention is to provide a multi-criteria fusion-based data abnormality screening method for distribution transformers, using four methods of prototype clustering, density clustering, probability density, and deep learning to identify outliers. Screening, "out of 4" verification results for the four models, which solves the difficulties faced by traditional machine learning methods when processing massive data, low efficiency, and low real-time performance

Images