Research on the wind-resistant structure of composite insulators for overhead contact system cantilever used based on fluid-structure interaction method

Gui, Cao; Cao, Baojiang

doi:10.1109/ichve.2016.7800601

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pantographs and contact networks are respectively mobile devices and fixed facilities in the current circuit of railway traction power supply systems [1], and reliable transmission of electric energy requires the cooperation of pantograph and catenary [2]. In addition, pantographs also bear the task of feeding power in reverse, so their electrical parameters, mechanical structure, and material requirements are more stringent.…”

Section: Introductionmentioning

confidence: 99%

Health detection of high-speed train pantograph based on deep belief network

Wu,

Feng

2024

Third International Conference on Testing Technology and Automation Engineering (TTAE 2023)

View full text Add to dashboard Cite

Pantograph is an important subsystem in the Pantograph-OCS system, and its health condition is related to the smooth running of high-speed train. This article, the structure of high-speed railway pantograph model is first optimized based on finite element analysis. After optimization, the average low-order vibration frequency was reduced by 7.75%, and it was concluded that the optimal pantograph sliding plate consists of four equally symmetrical structures. Then, the weak links in the pantograph structure were obtained by comprehensive static strength analysis, and acceleration sensors were arranged to collect the working status data of the pantograph. Finally, a deep belief network (DBN) is used to detect the health status of key pantograph components. The vibration signals collected by multiple sensors were segmented and extracted, and feature extracted for unsupervised DBN training. By comparing and analyzing the prediction results, an appropriate number of samples was selected to improve the diagnostic accuracy of the model to 97.87%. The experimental results show that the fully trained pantograph DBN network model can achieve high accuracy in identifying and classifying fatigue conditions.

show abstract

Section: Introductionmentioning

confidence: 99%