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 16
- Downloads 0
Research on the Manufacturing Process of Steel Bridge Piers for Suspended Monorail Transit
［Objective］ Manufacturing accuracy of the steel bridge pier, which is an important part of the suspended monorail transit system, determines the erection and installation of track beams, thereby affecting the train smo...
Research Progress and Prospects on Pantograph-Catenary Arcing in Urban Rail Transit
［Objective］ Pantograph-catenary (PC) arcing degrades the train current collection quality, causes ablation of pantograph carbon strips and contact wires, and consequently affects safety and stability of train operation...
Optimization of Urban Rail Transit Signaling System Functions Based on Alternate Day Depot Return Operation Mode
Objective In the alternate day depot return operation mode, trains either stay overnight on the mainline or run continuously day and night. The relevant functions of existing urban rail transit signaling system can no lo...
Smoke Exhaust Schemes for Metro Terminal Station Storage Tracks and Reserved Main Lines
[Objective] The smoke exhaust paths for metro terminal station storage tracks and reserved main lines are different from those for various auxiliary lines in middle stations, thus it is necessary to study suitable smoke...
Influence of Different Opening Positions of Shield Method Connecting Passage on Main Tunnel Segment Internal Force
Objective In the 9 m level large-diameter shield tunneling, there are no engineering cases using shield method for constructing connecting passages yet. Due to the influence of clearance and evacuation platform height, a...