2025
article
OpenAlex
Yunhan Shi, Bin Gao, Geng Yang, Haoran Li et autres
The conventional anomaly detection (AD) methods typically rely on training normal samples without defects to identify deviations from the background. However, these methods suffer from issues, such as missing detection or false detection. Although subsequent research has attempted to improve algorithm performance, …
cn, gb
(code pays fourni par la source)
2023
article
OpenAlex
Bingchuan Yan, Jianfeng Zheng, Rui Li, Kuan Fu et autres
Traditional detection algorithms of pipeline non-destructive testing extract information from a large number of defect samples to ensure the detection performance, but even if an adequate of defect samples are collected, it is difficult to enumerate the possible defect morphology in nature. …
cn
(code pays fourni par la source)
2022
article
OpenAlex
Haoran Li, Bin Gao, Xiaolong Lu, Xiyuan Zhang et autres
The effectiveness of railway fault inspection has remained challenging. Conventional techniques are still functionally limited and unable to meet the increasing demand of railway diagnosis. To mitigate the variety of rail fault detection problems, this article proposes a dynamic railway inspection system …
cn, gb
(code pays fourni par la source)
2021
conference-paper
OpenAlex
Haoran Li, Yunhan Shi, Bin Gao, Xiyuan Zhang et autres
With the rapid development of railway networks, high-speed or intensive rolling of wheels will significantly increase the probability of fatigue damage and it has laid a hidden danger for major safety accidents. Thus, the timely development of rail rolling contact fatigue crack …
cn
(code pays fourni par la source)
2021
article
OpenAlex
Xiyuan Zhang, Bin Gao, Yunhan Shi, Wai Lok Woo et autres
With the development of railway, high speed and intensive rolling will significantly increase the probability of fatigue damage and they lay a hidden danger for major safety accidents. Therefore, it is vital to detect defects of the rail. The commonly used algorithms …
cn, gb
(code pays fourni par la source)