Power equipment sound diagnosis method and system

Abstract

The invention provides a power equipment sound diagnosis method and system. The method comprises the steps of acquiring sound of power equipment; performing digital signal processing on the acquired sound of the power equipment, and extracting spectrum features of the sound of the power equipment; performing sound type labeling on the acquired sound of the power equipment to obtain labeling information; training to obtain a sound classification model by utilizing the frequency spectrum characteristics of the sound of the power equipment and the labeling information; acquiring field sound of the power equipment, performing digital signal processing on the field sound, and extracting spectrum characteristics of the field sound; and inputting the spectrum characteristics of the field sound into the sound classification model, obtaining the type of the field sound, and further judging the operation state of the power equipment. According to the invention, the monitoring cost is reduced in an automatic manner, the monitoring efficiency is improved, and a new solution is provided for long-time monitoring of the operation state of the power equipment.

Description

technical field [0001] The invention relates to the technical field of power equipment monitoring, in particular to a sound diagnosis method and system for power equipment with edge computing capability. Background technique [0002] For the power industry, equipment management is a very important task, which is directly related to the stability of equipment operation. In recent years, the scale of my country's power grid has continued to expand, which has increased the difficulty of equipment management to a certain extent. Because most of the power equipment needs to run for a long time without interruption, it is inevitable that there will be failures. When the power equipment fails, it will affect the operation of the power system and the power grid. Therefore, it is necessary to regularly detect the faults of the power equipment. [0003] In the electric power industry, the traditional detection method of electric power equipment usually adopts the method of monitoring...

AI Technical Summary

Problems solved by technology

[0003] In the electric power industry, the traditional detection method of electric power equipment usually adopts the method of monitoring the voltage, current, oil chromatography and other physical quantities of electric equipment to predict equipment failure. This method is expensive, bulky, complicated to install, and has a negative Influence and intelligence are low, and the monitoring and diagnosis of electrical equipment often requires complex and expensive equipment to monitor electrical quantities, or a large amount of manpower is required for regular patrol inspections, so there are difficulties in fault analysis and detection process. It is impossible to monitor the power equipment for a long time due to problems such as affecting the work of the equipment and low work efficiency

[0004] At present, there is no description or report of the similar technology of the present invention, and no similar data at home and abroad have been collected yet.

Images