Identification Method for Missing Cotter Pins in Catenary Systems Based on Stacked Denoising Autoencoder Network

Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 10

Abstract

Objective When using convolutional neural networks (CNNs) for the state detection of catenary system cotter pins, the imbalance between positive and negative samples leads to a low detection rate of missing pins in the network model. Thus, a single-stage detection network is employed for multi-level precise localization of cotter pins, the state features of the cotter pins are reconstructed in combination with SDAE (stacked denoising autoencoder), thereby achieving efficient detection of missing cotter pins. Method First, a single-stage localization detection network is employed for the regression of cotter pin positions, and the localization results are used as input for SDAE. Different levels of depth noise are introduced into various structural layers of the denoising autoencoder network. By minimizing reconstruction errors, the method enhances semantic understanding of the cotter pin localized images, allowing for accurate assessment of their condition. Additionally, due to the constraints on the size of the localized images, the computational load of the SDAE is relatively low, same with the network time complexity. Result & Conclusion Extensive experimental results demonstrate that the SDAE, based on YOLO v5 algorithm, can accurately detect missing cotter pins at various locations within the catenary system.

Authors and Affiliations

Chonghao SHAN

Keywords

Related Articles

Metro Tunnel Shield Construction in Highly Water-rich Karst Strata

[Objective] When a shield tunneling machine passes through highly water-rich karst development regions in shallow strata, the presence of karst cavities poses significant challenges to land subsidence control, creating...

Mechanism Analysis and Simulation Study of Closing Overvoltage Fault in EMU Circuit Breaker

Objective The overvoltage caused by circuit breaker closing will aggravate the insulation aging of high voltage equipment when EMU (electric multiple units)passes neutral section. The research on the mechanism and influe...

Application of Distributed Photovoltaic Power Generation at Urban Rail Transit Station Entrances and Exits

Objective Based on the goals of carbon peak and carbon neutrality in China and the demand for green, low-carbon and sustainable development of urban rail transit, the feasibility of applying distributed photovoltaic powe...

Influence Laws of Train Operation Parameters and Bypass Tunnel Parameters on Bypass Tunnel Ventilation Effect in Subway Station Track Zone

[Objective] Due to space constraints, some subway station piston ventilation shafts are set up in the station track zones, and a bypass tunnel is used for connecting the ventilation shaft to the main line tunnel outsid...

Impact Analysis of Large Shopping Malls on Inbound and Outbound Passenger Flow Rates at Urban Rail Transit Stations

[Objective] It is aimed to reveal the impact of large shopping malls on daily passenger flow and evening peak-hour outbound passenger flow at urban rail transit stations. Based on these findings, a revised passenger fl...

Download PDF file
  • EP ID EP749252
  • DOI 10.16037/j.1007-869x.2024.10.049
  • Views 51
  • Downloads 1

How To Cite

Chonghao SHAN (2024). Identification Method for Missing Cotter Pins in Catenary Systems Based on Stacked Denoising Autoencoder Network. Urban Mass Transit, 27(10), -. https://www.europub.co.uk/articles/-A-749252