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

Signaling System Renovation Plan for Suzhou Rail Transit Line 3 and Line 11 Through Train Operation

Objective To facilitate the integration of passenger flow between Suzhou and Shanghai, Suzhou Rail Transit Line 3 and Line 11 are connected at Weiting Station, where passengers currently transfer via the concourse within...

Research on Smooth Tracking and Control of Stair-like Target Speed with Compatible On-Board System in Urban Rail Transit

[Objective] In view of the special phenomenon that the target speed message period is longer than the on-board control period and the message interval is not fixed in urban rail transit compatible on-board system, a dual...

Analysis of Large-slope Metro Turnout Rail Creeping under Cycling Loads Action

Objective When turnouts are laid on slope, the longitudinal force increase on the track due to the cyclic braking of trains will cause uneven rail creeping phenomena, resulting in a more complex stress and deformation p...

Simulation Analysis on the Mud Film Stability for Urban Slurry Shield Tunnel

Objective As the sand layer located at the launching end of the slurry shield section is connected with seawater during the tunnel construction of Xiamen Metro Line 3, accidents like water and mud gushing, ground collaps...

Problems and Optimization Suggestions for Metro Interval Evacuation Design under Flood Conditions

Objective Evacuation in metro interval under flood conditions is often overlooked in metro engineering design. Besides, currently there are no industry standards for such scenarios. Attention should be paid to this issue...

Download PDF file
  • EP ID EP749252
  • DOI 10.16037/j.1007-869x.2024.10.049
  • Views 48
  • 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://europub.co.uk/articles/-A-749252