A Health state-related ensemble deep learning method for aircraft engine remaining useful life prediction

Cheng, Yujie; Zeng, Jiyan; Wang, Zili; Song, Dengwei

doi:10.1016/j.asoc.2023.110041

Cited by 13 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, unmanned aerial vehicles (UAVs) and deep learning have been developed rapidly and widely applied to the civil infrastructure field (Rafiei & Adeli, 2018a, 2018b including the railway operation and maintenance field (C. Li et al, 2022;Oudshoorn et al, 2022;Wang et al, 2023) and other fields (Y. Cheng et al, 2023;Macias-Garcia et al, 2021;Martins et al, 2020) because of their superior performance. The mounted camera on UAVs is developed to inspect the inaccessible or unreachable areas of civil structures and facilities effectively.…”

mentioning

confidence: 99%

Anchor‐adaptive railway track detection from unmanned aerial vehicle images

Tong

Jia

Geng

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

Autonomous railway inspection with unmanned aerial vehicles (UAVs) has huge advantages over traditional inspection methods. As a prerequisite for UAV‐based autonomous following of railway lines, it is quite essential to develop intelligent railway track detection algorithms. However, there are no existing algorithms currently that can efficiently adapt to the demand for the various forms and changing inclination angles of railway tracks in the UAV aerial images. To address the challenge, this paper proposes a novel anchor‐adaptive railway track detection network (ARTNet), which constructs a dual‐branch architecture based on projection length discrimination to realize full‐angle railway track detection for the UAV aerial images taken from arbitrary viewing angles. Considering the potential capacity imbalance of the two branches that can be caused by the uneven distribution of railway tracks in the dataset, a balanced transpose co‐training strategy is proposed to train the two branches coordinately. Moreover, an extra customized transposed consistency loss is designed to guide the training of the network without increasing any computational complexity. A set of experiments have been conducted to verify the feasibility and superiority of the ARTNet. It is demonstrated that our approach can effectively realize full‐angle railway track detection and outperform other popular algorithms greatly in terms of both detection accuracy and reasoning efficiency. ARTNet can achieve a mean F1 of 76.12 and run at a speed of 50 more frames per second.

show abstract