The Application of Kalman Filter Algorithm in Rail Transit Signal Safety Detection

With the speedy prosperity and popularization of wireless communication, the informatization and automation level of rail transit systems is also improved. The rail communication transmission system is also affected by interference from wireless local area networks and rail foreign objects, leading...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhinong Miao, Qilong Liao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11009202/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the speedy prosperity and popularization of wireless communication, the informatization and automation level of rail transit systems is also improved. The rail communication transmission system is also affected by interference from wireless local area networks and rail foreign objects, leading to signal transmission failures. Therefore, research is being conducted to optimize the signal safety detection system for rail transit. Firstly, the improved Kalman filter algorithm is used to denoise the signal to ensure the accuracy of signal transmission. Then, in response to signal transmission failures caused by foreign object intrusion on the track, a track safety detection model based on improved You Only Look Once Version 8 (YOLOv8) is built. The outcomes reveal that the raised improved Kalman filtering has a high similarity between the denoised and the true signal, and a low root mean square error of 0.009. The improved Kalman filter algorithm also has a high signal-to-noise ratio of 2.086dB, a signal-to-noise ratio of 26dB, a reference signal received power of −61dBm, a handover success rate of 99.98%, and a handover delay of 97ms. The proposed improved YOLOv8 algorithm achieved an accuracy of 96.27%, a recall rate of 94.86%, a detection accuracy of 96.82%, a frame rate of 78.12fps, and an error value of 0.002 in the Track Obstacle Recognition Dataset. The experiment outcomes demonstrate the noise reduction and object detection capability of the raised model. The research results contribute to promoting the intelligent development of rail transit systems and improving their safety and operational efficiency.
ISSN:2169-3536