Railway Panorama: A Fast Inspection Method for High-Speed Railway Infrastructure Monitoring

Jiang, Xinlan; Wang, Shengchun

doi:10.1109/access.2021.3125645

Cited by 5 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Flywheels and supercapacitors are performed by high specific power and a large number of charge/discharge cycles. However, they present low specific energy [22]. In fact, they can be implemented in urban rail transit or metro stricture.…”

Section: Choose Of Energy Storage Devicesmentioning

confidence: 99%

See 1 more Smart Citation

Control and Management of Railway System Connected to Microgrid Stations

Cabrane

Lee

2022

IEEE Access

View full text Add to dashboard Cite

The recent railway system is a huge microgrid assembling multiplex structure with distributed active loads, sources and storage devices. The active load represents the train. The sources are a microgrid based on renewable energies. The big problem of the most of electrical train is that they can't recover energy recovery during regenerative breaking phases. another problem of the electrical train is the long charging time from the stations. This paper suggests a techno-economic process for the energy storage by using SCs in the train, with the aim to reduce the energy consumptions. The proposed design of railway station use PV and wind sources, and batteries for energy storage system (ESS). For the train, SCs are implemented to the ESS where they are alimented breaking phases and from stations by a pantograph installed in an air power line in each stop. SCs are distinguished by high characteristics power and a wide number of charge/discharge cycles, they provide low particular energy and a fast charging time. An energy management approach is suggested to control the DC bus by voltage and the buck-boost converter by current. The Sizing of PI controller used for the stabilization of the DC bus of train and station is given. The whole system is modeled in MATLAB-Simulink. Simulations for the train and station show the suitability of the suggested powertrain and control strategy.INDEX TERMS Energy management, railway system control, energy storage system, supercapacitors. ZINEB CABRANE received the B.S. and master's degrees in electrical engineering from the Faculty of Sciences and Techniques, Settat, Morocco, in 2010 and 2012, respectively, and the Ph.D. degree in electrical engineering from the

show abstract

Section: Choose Of Energy Storage Devicesmentioning

confidence: 99%

“…EMS on the system level with an integrated strategy into the railway structure often is ignored [19], [20]. The optimal control theory for railway vehicle is presented in many articles [21], [22]. EMS is implemented to control and connect different devices in railway system, energy storage devices, sources and train.…”

Section: Introduction a Motivationmentioning

confidence: 99%

Control and Management of Railway System Connected to Microgrid Stations

Cabrane

Lee

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, the analysis methods for tunnel image data and surface defects in this detection system are not satisfactory and mainly rely on manual recognition, which is time consuming and labor intensive. Jiang et al [9], from China, used imaging devices installed on a high-speed comprehensive inspection train to obtain railway environment videos and generate panoramic images by stitching four images together, enabling the fast intelligent inspection of the railway infrastructure. Wang et al [10], from the China Academy of Railway Sciences, used a performance imaging detection system based on a mobile platform to detect cracks in railway tunnels, achieving a detection rate of 92.6% for cracks wider than 0.3 mm.…”

Section: Introductionmentioning

confidence: 99%

High-Speed Rail Tunnel Panoramic Inspection Image Recognition Technology Based on Improved YOLOv5

Duan

Qiu

Jin

et al. 2023

Sensors

View full text Add to dashboard Cite

In order to meet the fast and accurate automatic detection requirements of equipment maintenance in railway tunnels in the era of high-speed railways, as well as adapting to the high dynamic, low-illumination imaging environment formed by strong light at the tunnel exit, we propose an automatic inspection solution based on panoramic imaging and object recognition with deep learning. We installed a hyperboloid catadioptric panoramic imaging system on an inspection vehicle to obtain a large field of view as well as to shield the high dynamic phenomena at the tunnel exit, and proposed a YOLOv5-CCFE object detection model based on railway equipment recognition. The experimental results show that the mAP@0.5 value of the YOLOv5-CCFE model reaches 98.6%, and mAP@0.5:0.95 reaches 68.9%. The FPS value is 158, which can meet the automatic inspection requirements of railway tunnel equipment along the line and has high practical application value.

show abstract

“…Previous machine vision inspection works are mainly based on the hand-designed feature descriptors and the template matching operation is usually performed to inspect assembly errors. Although it performs well when the features of target region are rich and the image background is relatively fixed, it is not suitable for dynamic assembly scenes with complex background and uncontrollable lighting conditions [6]. And the shortcoming of the traditional template matching-based inspection method is that when the relative position between the physical camera and the target changes, there will be a difference in perspective between the in-site image and the standard template.…”

Section: Introductionmentioning

confidence: 99%

Online Assembly Inspection Integrating Lightweight Hybrid Neural Network With Positioning Box Matching

Zhao,

Wang,

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Assembly inspection methods have been widely used in the process of mechanical product assembly for quality issues. However, some challenges remain to be solved, such as low detection efficiency, poor accuracy and sensitive to camera view. This paper proposes an online assembly inspection scheme based on hybrid neural network and positioning box matching. A hybrid multi-task learning neural network with transformer attention mechanism is proposed to simultaneously detect key points and assembly parts with high accuracy and strong robustness. Utilizing the key points detection results, the transformation relationships between the in-site assembly images and the standard templates are solved. According to the results of assembly parts detection, the detected 2D positioning bounding boxes are matched with those in the standard assembly templates, so as to evaluate whether the current step has quality problems. In addition, the proposed method is tested on an assembly dataset constructed in this paper. For key points detection, the average error is less than 1 pixel. For parts detection, the mean average precision is 97.66%. The missing and wrong assembly inspection results show that the average F1 score reaches 93.96%. This inspection method can be employed to detect the missing and wrong assembly faults of each assembly step online, improving the assembly quality of products.

show abstract

Railway Panorama: A Fast Inspection Method for High-Speed Railway Infrastructure Monitoring

Cited by 5 publications

References 14 publications

Control and Management of Railway System Connected to Microgrid Stations

Control and Management of Railway System Connected to Microgrid Stations

High-Speed Rail Tunnel Panoramic Inspection Image Recognition Technology Based on Improved YOLOv5

Online Assembly Inspection Integrating Lightweight Hybrid Neural Network With Positioning Box Matching

Contact Info

Product

Resources

About