Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Optica Applicata

1 2025

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: EMU

Sortuj według:

Ogranicz wyniki do:

Based on fiber sensor network rail transit IoT monitoring system

Liu Zhao, Wang Yifang, Hou Yingjuan, Yu Chunrong

Optica Applicata

2025

Vol. 55, nr 1

5--17

In the process of train operation, the status information directly reflects the degree of safety of the operation. Online health monitoring and completion of train status assessment are important signs of train intelligent control. To obtain the stress field distribution of the support position (bearing area) of the train, proposed a EMU health monitoring and intelligent state assessment system based on fiber sensing internet of things (FS-IoT). The system adopts the method of combining multiple sensitized FBG sensors into a sensing network to obtain the stress field distribution at the measured location. When the train is faulty or the external environment affects the train’s operation, the stress field and vibration field on the train’s motion components will change significantly. Obtain real-time physical field information of sensitive locations through the FBG sensor array, which can realize online monitoring of train status. A distributed combinatorial optimization algorithm based on FS-IoT was designed, and the weight distribution of FBG test data at different locations on the inversion results was analyzed based on data mining. In the sensitization FBG testing experiment, under the same stress conditions, the sensitivity increased from 12.440 to49.935 pm/kN, and had good linearity. In dynamic testing, when the test carriage passes through the rail connection, there will be significant fluctuations in the center wavelength of the FBG, with a maximum wavelength offset of 2530.2 pm. The peak-to-peak values of the two test data are basically the same, indicating that stress changes can be inverted by the peak position. Finally, a trainstate inversion model based on FBG sensing network and a system framework for intelligent state evaluation are presented, providing new design ideas for train state monitoring.