Defect Detection Model for Catenary Components in Environments with Few Samples and Small Targets
Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 12
Abstract
［Objective］ Aiming at the difficulties of detecting small-volume parts of rail transit catenary under few-sample conditions, a defect detection method integrating generative adversarial networks and deep segmentation models is proposed. ［Method］ The composition of the detection system, the improved DCGAN (deep convolutional generative adversarial network) structure and the improved YOLACT (single-stage conditional adversarial network) model are introduced, and the defect detection effect is verified based on the actual defect datasets. ［Result & Conclusion］ In the sample expansion part, the improved DCGAN model can improve the quality of generated samples by introducing several normalization operations and adding an efficient channel attention mechanism. In the model detection part, the improved ResNeXt-FPN (deep con-volutional neural network combining residual network and feature pyramid network) structure is used to replace the backbone network of the original YOLACT model, aiming to fully characterize the multi-scale features of the target. The introduction of CS (channel and space) attention mechanism in the mask branch network can effectively improve the detection accuracy of small-volume parts. The proposed defect detection model can achieve high-precision detection of cotter pins in complex contact network images, with a detection accuracy and recall rate of up to 88.63% and 87.49% respectively. Compared with the original YOLACT model, the comprehensive performance of the proposed defect detection model is improved by about 6.2%.
Authors and Affiliations
Xiaosi YU, Baoquan WEI, Zewen LI, Fangming DENG
Keywords
Related Articles
- EP ID EP752720
- DOI 10.16037/j.1007-869x.2024.12.015
- Views 5
- Downloads 0
Conversion Scheme Design of Power Supply Return Mode for Metro Connection Lines
Objective The metro lines connected by connection line may adopt different power supply current return modes. In order to improve the efficiency of train line transfer, it is necessary to set up the return mode conversio...
Causes and Countermeasures of Train Emergency Braking Failures under DRB Turn-back Mode on Xi’an Metro Line 14
Objective Under the DRB (driverless return button) mode on Xi’an Metro Line 14, the train emergency braking will occur after the train automatically switching its head car on the turn-back line, resulting in the train tu...
Door Howling Cause Analysis and Countermeasures of Urban Rail Transit Train Passing through Tunnels
Objective When the urban rail transit train with designed speed of 120 km/h passes through a tunnel at high speed, rear door howling problem of the tail car often occurs, seriously affecting passenger ride comfort. Thus...
Metro Vehicle Bogie Abnormal Vibration and Fatigue Failure
Objective Due to the increase of metro operation mileages and track conditions complexity, abnormal bogie vibrations caused by wheel-rail wear often occur. Bogie frame serves as an important load-bearing component, requi...
Sensitivity Analysis and Optimization Design of Brake System Pipeline Clamp Positions
Objective During the design phase of brake system pipeline for rail vehicles, optimizing the support positions of clamps can effectively avoid the excitation frequency of the vehicle carbody and reduce the risk of pipeli...