Method and system for diagnosing transformer fault by using sound feature codes

Abstract

The invention discloses a method and a system for diagnosing a transformer fault by using sound feature coding. The method comprises the following steps: acquiring a transformer sound sample; extracting a plurality of sound features of the transformer sound sample; for each sound feature, obtaining a corresponding feature code according to a preset transformer sound feature coding rule table, and combining the feature codes of all the sound features to form a feature code combination; and querying a preset transformer fault table according to the feature code combination to obtain a transformer fault diagnosis result. The method and the system for diagnosing the transformer fault by using sound feature coding have the advantages of simple diagnosis method, easy programming realization, multiple diagnosis fault types and high diagnosis accuracy.

Description

technical field [0001] The invention relates to the technical field of power safety monitoring, in particular to a method and system for diagnosing transformer faults by using sound feature coding. Background technique [0002] Transformer is one of the most critical equipment in the power system, and its safe operation is of great significance to ensure the reliability of power supply of the power system. The sound is produced with the operation of the transformer, and the amplitude, time-domain waveform, and spectral characteristics of the sound are closely related to its operating voltage, current, mechanical state, excitation state, and insulation state, which can reflect the changes in the operating state of the equipment in time. According to DL / T 573-2010 "Maintenance Guidelines for Power Transformers", transformer overload, unbalanced load, harmonic load, severe overheating, DC bias, partial discharge, loose winding core, loose accessories and other defects are relat...

AI Technical Summary

Problems solved by technology

The manual inspection method is time-consuming and laborious, and it is prone to misjudgments. The diagnosis results are closely related to the experience of technicians; the method and algorithm based on artificial intelligence are difficult to implement, and it is difficult to combine with embedded development. Diagnosing different types of faults requires a large number of corresponding faults sample

Due to the complexity of the algorithm, there are many factors affecting the diagnosis effect of the algorithm, which may easily lead to problems such as low reliability of fault diagnosis and low diagnosis accuracy.

Images