Fault detection method for floor damage of railway wagon bottom

Abstract

The invention discloses a fault detection method for floor damage at the bottom of railway wagons, belonging to the technical field of railway wagon safety detection. The invention aims at the problem that the safety detection of the bottom floor of the existing railway wagon adopts manual image inspection, which has poor reliability and low efficiency. Including: collecting the line array images of the bottom of the railway truck under different conditions, and processing to obtain a sample data set; constructing a semantic segmentation neural network model based on the encoder and decoder and using the sample data set for training to find the optimal weight coefficient Then update the semantic segmentation neural network model; then collect the current full-vehicle line array image at the bottom of the moving railway freight car, and use the updated semantic segmentation neural network model to obtain the current target area to be detected, and then make a pre-judgment, which will be pre-judged as a fault The current target area to be detected uses a single-stage SSD model for fault detection. The invention realizes the automatic identification of the damage of the bottom floor.

Description

technical field [0001] The invention relates to a fault detection method for a damaged floor at the bottom of a railway freight car, and belongs to the technical field of railway freight car safety detection. Background technique [0002] The bottom floor of a railway freight car is huge, and many of the key components that keep the train running are distributed on it. Since there are various types of goods transported by railway wagons, which may be hard and slender steel bars or packed heavy objects, long-term use or accidental collisions will cause damage to the bottom floor, making the goods may fall out of the formed holes; In the process of falling out of the goods, they may be pressed against the steel pipes distributed on the bottom floor, which will further cause the failure of the truck. Therefore, regardless of the damage or loss of the goods or the friction between the hard goods and the bottom track of the truck, it will threaten the safe operation of the railw...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the safety detection of the bottom floor of the existing railway freight car adopts artificial image inspection, which has poor reliability and low efficiency, the present invention provides a method for detecting the damage fault of the bottom floor of the railway freight car

Images