Transformer fault diagnosis method based on multi-feature fusion common vectors

Abstract

The invention discloses a transformer fault diagnosis method based on multi-feature fusion common vectors, and designs a reliable, high-accuracy, easy-to-implement and model parameter-free transformerfault diagnosis method by utilizing dissolved gas concentration data in transformer oil. Specifically, the method comprises the following steps: firstly, carrying out dual construction of statisticalcharacteristics and ratio characteristics on dissolved gas concentration data; secondly, establishing a classification model based on a common feature vector for multi-feature fusion data of originaldissolved gas concentration data, statistical feature data and ratio feature data; and finally, identifying the fault type of the transformer according to the dissolved gas analysis data in the faultstate of the transformer. The method basically does not involve complex transformation or mathematical calculation, and is simple to operate and very easy to implement. In addition, in the implementation process of the method, certain model parameters do not need to be determined subjectively, so that the problem of parameter selection is greatly solved.

Description

technical field [0001] The invention relates to a transformer fault diagnosis method, in particular to a transformer fault diagnosis method based on multi-feature fusion common vector. Background technique [0002] The technical level and complexity of modern equipment are constantly increasing, and the impact of equipment failure on production has also increased significantly. Therefore, to ensure the reliable and effective operation of the equipment, the status of the equipment must be monitored in real time. From this point of view, fault diagnosis technology is essential. As the key equipment of the power supply and distribution system, the transformer has important research significance for its healthy and normal operation to ensure stable power transmission. Therefore, it is an indispensable technology to monitor the operation status of the transformer, diagnose the fault type and repair the equipment in time. The common way to solve the problem of transformer fault...

AI Technical Summary

Problems solved by technology

From the perspective of this task requirement, the neural network model is greatly affected by parameters, so it is not suitable to study and solve such problems.

Images