Intelligent detection method for high-speed rail overhead line system cotter pin defects

Abstract

The invention discloses an intelligent detection method and system for the cotter pin defect of an iron contact network, and the method comprises the steps: firstly obtaining a data set composed of a sample containing the cotter pin defect of the high-speed rail contact network and a normal sample of the cotter pin of the high-speed rail contact network, and dividing the data set into a training set and a test set according to a proportion; then, a Pytorch deep learning framework is used, and a recognition network model is built; training the recognition network model through a model training system, and testing the trained recognition network model through a model testing system, so that the recognition network model can recognize the defects of the high-speed rail overhead line system cotter pin; and finally, calling a real-time high-speed rail overhead line system image, intercepting a sub-image containing an inclined cantilever and a structure below the inclined cantilever, performing identification through the identification network model, obtaining an identification result, and further capturing a high-speed rail overhead line system image containing cotter pin defects.

Description

technical field [0001] The invention belongs to the technical field of high-speed rail, and relates to an identification technology for a cotter pin defect of a high-speed rail catenary, in particular to an intelligent detection method and system for a cotter pin defect of a high-speed rail catenary. Background technique [0002] The operating mileage of my country's high-speed rail is increasing year by year. During the operation of the high-speed rail, real-time power is supplied through the catenary, so the catenary will also receive the impact and vibration brought by the high-speed train, which may cause the catenary to be damaged due to shock and vibration. Therefore, it is very difficult to find the damaged part of the catenary in time and to repair and improve it in time to ensure the continuous operation of the high-speed railway for a long time. However, the high-speed railway line is extremely long, and it is very difficult to find the damaged part of the catenary i...

AI Technical Summary

Problems solved by technology

[0004] For the defects that may appear in different parts of the catenary, there are corresponding different detection schemes, and for the defects such as missing or damaged cotter pins that are more likely to occur in the catenary, there are also different treatment schemes, but the current treatment scheme The accuracy rate is low , the processing effect still needs to be improved

Images