Power distribution room equipment fault analysis and pre-judgment method and device based on edge computing

Abstract

The invention discloses a power distribution room equipment fault analysis and pre-judgment method and device based on edge computing, and the method comprises the steps: collecting the state quantitydata of a power distribution room sensing terminal, carrying out the normalization processing, and forming a sample data set; constructing a deep learning model based on a deep convolutional network,inputting the sample data set for identification training, and stopping training until an output identification result is consistent with a training sample label; performing fusion analysis on the state quantity by using the trained deep learning model; identifying and positioning abnormal sounds of multiple partial discharge sources and equipment for the plurality of sensing terminals in combination with a collaborative edge strategy; and judging the fault state of the power distribution room equipment based on the fusion analysis result and the identification positioning result. According to the invention, the manual inspection cost is effectively reduced, and information and data are acquired in real time; in addition, based on integrated judgment of a fusion analysis result and an identification positioning result, the accuracy of equipment fault judgment is improved.

Description

technical field [0001] The invention relates to the field of distribution network and Internet of Things information technology, and in particular to a method and device for analyzing and predicting equipment faults in a power distribution room based on edge computing. Background technique [0002] The operating status of equipment is very important to ensure the safe operation of the power grid. At present, the main methods of power grid companies are manual inspection and live detection. However, there are two problems: 1. Manual inspection has a large workload, low efficiency, and high cost, resulting in a heavy workload for inspection personnel , the inspection pressure is high, and the contradiction between the rapid growth of the grid scale and the allocation of equipment operation and maintenance personnel is becoming increasingly prominent; 2. There are inspection blind spots in manual inspections, and operation and maintenance personnel cannot perform all-weather, fu...

AI Technical Summary

Problems solved by technology

[0002] The operating status of equipment is very important to ensure the safe operation of the power grid. At present, the main methods of power grid companies are manual inspection and live detection. However, there are two problems: 1. Manual inspection has a large workload, low efficiency, and high cost, resulting in a heavy workload for inspection personnel , the inspection pressure is high, and the contradiction between the rapid growth of the power grid scale and the allocation of equipment operation and maintenance personnel is becoming increasingly prominent; 2. There are inspection blind spots in manual inspection, and the operation and maintenance personnel cannot realize all-weather, full-time, all-round inspection

At present, there are mainly problems in live detection and diagnosis of power distribution room equipment, such as heavy workload of inspection personnel, low cost performance of detection methods, and low detection accuracy of old and fault-prone equipment.

Images