Series type fault arc test platform based on deep learning and test method thereof

Abstract

The invention relates to a series type fault arc test platform based on deep learning and a test method thereof, and belongs to the field of electrical fire-protection application. The test platform comprises a series type fault arc generator, a grid simulator, an RLC programmable load, a programmable program controller, a data collection processor and a deep learning computer; the series type fault arc generator is serially connected between the grid simulator and the RLC programmable load via a cable to form a test power supply and load regulation loop; the grid simulator, the RLC programmable load, the programmable program controller and the data collection processor are respectively connected with the deep learning computer; the data collection processor is connected with an arc pressure sensor, a current transformer and an arc light sensor inside the series type fault arc generator; and the programmable controller is connected with a step motor and a rotary encoder inside the series type fault arc generator. According to the series type fault arc test platform based on the deep learning and the test method thereof provided by the invention, the accuracy for series type fault arc detection and identification is improved, and the market blank for such a type of product is remedied.

Description

technical field [0001] The invention belongs to the application field of electric fire protection. In particular, it relates to a deep learning-based series fault arc test platform and a test method thereof. Background technique [0002] In recent years, fire accidents caused by electrical reasons have remained high, causing huge losses to the country and people's lives and property. According to statistics from the Fire and Rescue Bureau of the Ministry of Emergency Management, a total of 281,000 fires occurred across the country in 2017. Among all fires, fires caused by electrical reasons accounted for 35.7% of the total, and electrical circuit problems accounted for 62.2% of the total number of electrical fires. Equipment failure accounted for 31.3%, and other electrical reasons accounted for 6.5%. Among the 65 large fires, 35 were caused by electricity, accounting for 53.9% of the large fires. Among the 6 major fires, 3 were caused by electricity, accounting for 50% o...

AI Technical Summary

Problems solved by technology

[0012] In view of the above problems, the purpose of the present invention is to provide a series-type arc fault test platform and its test method based on deep learning, to solve the problem that the existing series-type arc fault test platform has a single function and cannot independently train the arc fault model

Images