Transformer substation remote intelligent inspection method and system based on neural network

Abstract

The invention discloses a transformer substation remote intelligent inspection method and system based on a neural network. The method comprises the steps of obtaining a cloud transformer substation inspection data analysis model which is updated in real time from a cloud end, updating the analysis model based on the monitoring data in a database which is updated in real time, and obtaining an edge transformer substation inspection data analysis model, analyzing the newly received monitoring data based on an edge end transformer substation inspection data analysis model, and when it is determined that the difference between the model parameters of the edge end transformer substation inspection data analysis model and the cloud end transformer substation inspection data analysis model meets a preset condition, uploading data to the cloud end, so that the cloud end updates the cloud end transformer substation inspection data analysis model in real time. Based on a cloud edge collaboration mechanism, the automatic uploading of the inspection data training sample and the regular updating of the transformer substation inspection data analysis model are realized, and the efficiency and accuracy of intelligent identification and discrimination can be continuously improved.

Description

technical field [0001] The invention relates to the technical field of substation inspection, in particular to a neural network-based remote intelligent inspection method and system for substations. Background technique [0002] Routine inspection of substation equipment is a routine means to ensure the safe and stable operation of power equipment. With the continuous expansion of the scale of the power grid, the number and types of equipment are increasing. Under the existing power system, the inspection of the status of the equipment is mainly carried out by the operation and maintenance personnel, which leads to a large workload on site. The efficiency of inspection is low, and the comprehensiveness, completeness and accuracy of inspection will be low during the inspection process. Contents of the invention [0003] In view of the problems existing in the above-mentioned prior art, the present invention provides a method and system for remote intelligent inspection of ...

AI Technical Summary

Problems solved by technology

With the continuous expansion of the scale of the power grid, the number and types of equipment are increasing. Under the existing power system, the inspection of the status of the equipment is mainly carried out by the operation and maintenance personnel, which leads to a large workload on site. The inspection efficiency is low, and the comprehensiveness, completeness and accuracy of the inspection will be low during the inspection process

Images