Railway structure monitoring solutions using fibre Bragg grating sensors

Kouroussis, Georges; Kinet, Damien; Moeyaert, Veronique; Dupuy, Julien; Caucheteur, Christophe

doi:10.1080/23248378.2016.1184598

Cited by 35 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The steady state waves for 150 Hz and 200 Hz were calculated for two different values of stiffness. As shown after substituting Equations (6) and (7) in Equation 5, h and L have a significant role to play in determining the amplitude of the steady state solution. Hence, a high stiffness results in low amplitude and this low amplitude does not allow for sufficient flexion of the FBG to sense the vibrations at high frequencies.…”

Section: Resultsmentioning

confidence: 99%

“…Assembling equipment or accessories near the tracks for obtaining measurements is also a challenge. Hence, fiber Bragg grating (FBG) sensors have been found to hold great promise in this area [6,7] since the fiber cables can run for several meters and allow for continuous and remote monitoring. In particular, in train tunnels, there is very little space for workers to conduct checks with conventional accelerometers when the lines are in operation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Passively Conducted Vibration Sensing with Fiber Bragg Gratings

2018

View full text Add to dashboard Cite

Measuring vibrations is a common method of monitoring the integrity of structures and heavy machinery, that are subject to dynamic loads. Strong vibrations for prolonged periods of time can be caused by various sources, such as trains, motors and heavy machinery. These strong vibrations should be identified and managed to ensure operational safety. This study proposes a flexible metal beam sensor with a fiber Bragg grating (FBG) mounted on the surface to measure the vibrational frequency. We present a sensor for measuring the vibrational frequencies on-site by placing the beam so that it makes physical contact with the vibrating body. The sensor has been tested in the range of 50–200 Hz. The sensing beam can detect the vibrations that are induced in other metallic bodies where there are metallic structures of low stiffness to conduct the vibration. The results show that the sensing beam is capable of detecting the frequency of forced vibrations from its periphery when placed in different orientations.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Passively Conducted Vibration Sensing with Fiber Bragg Gratings

2018

View full text Add to dashboard Cite

show abstract

“…A large amount of researches on the structural monitoring has been undertaken recently under the development of high-speed and heavy-haul rail lines (Zhai et al 2014;Kouroussis et al 2016). Kouroussis et al (2015), focusing on stress-based solutions, reviewed conventional and non-conventional methods to monitor the train traffic and presented their advantages and limitations.…”

Section: Test Methodsmentioning

confidence: 99%

Experimental Investigation on Dynamic Behaviour of Heavy-Haul Railway Track Induced by Heavy Axle Load

et al. 2019

View full text Add to dashboard Cite

The damage to the track structure and the influence to the line deformation have greatly deteriorated with the increase of the axle load compared with that of the ordinary trains. However, there is a paucity of experimental research on the dynamic influence of the heavier haul freight trains on the railway tracks. The objective of this study is to investigate the dynamic behaviour of heavy-haul railway track induced by heavy axle load by field experimental tests. The wheel–rail dynamic force, the track structure dynamic deformation and the track vibration behaviour are measured and analysed when the train operates in the speed range from 10 to 75 km/h and the axle load of vehicles varies from 21 to 30 t. Comparisons between the results for the axle conditions of 25 and 30 t are made in this paper to reveal the axle load effects. It is demonstrated that part of the indicators reflecting the dynamic behaviour of the railway track increases approximately linearly with the train running speed and axle load, while others are influenced negligibly

show abstract

“…Data-driven modeling and decision making are high priorities in modern transportation management (Wang 2000;Adeli and Samant 2000;Adeli and Jiang 2003;Ciresan et al 2012;Ma and Wang 2014;Qiu et al 2016;Kouroussis et al 2016;Ngo et al 2017). Pavement cracking is a common type of distress on pavement surfaces and is relied upon in both pavement management and design as input data for various modeling purposes.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning–Based Fully Automated Pavement Crack Detection on 3D Asphalt Surfaces with an Improved CrackNet

Zhang

Wang

Fei

et al. 2018

J. Comput. Civ. Eng.

221

View full text Add to dashboard Cite

CrackNet is the result of an 18-month collaboration within a 10-person team to develop a deep learning-based pavement crack detection software that demonstrated successes in terms of consistency for both precision and bias. This paper proposes an improved architecture of CrackNet called CrackNet II for enhanced learning capability and faster performance. The proposed CrackNet II represents two major modifications on the original CrackNet. First, the feature generator, which provides handcrafted features through fixed and nonlearnable procedures, is no longer used in CrackNet II. Consequently, all layers in CrackNet II have learnable parameters that are tuned during the learning process. Second, CrackNet II has a deeper architecture with more hidden layers but fewer parameters. Such an architecture yields five times faster performance compared with the original CrackNet. Similar to the original CrackNet, CrackNet II still uses invariant image width and height through all layers to place explicit requirements on pixel-perfect accuracy. In addition, the combination of a convolution layer and a 1 × 1 convolution layer was repeated in CrackNet II to learn local motifs with different sizes of local receptive fields. CrackNet II was trained with 2,500 diverse example images and then demonstrated to outperform the original CrackNet. The experiment using 200 testing images showed that CrackNet II performs generally better than the original CrackNet in terms of both precision and recall. The overall precision, recall, and F-measure achieved by CrackNet II for the 200 testing images were 90.20, 89.06, and 89.62%, respectively. Compared with the original CrackNet, CrackNet II is capable of detecting more fine or hairline cracks, while eliminating more local noises and maintaining much faster processing speed.

show abstract

Railway structure monitoring solutions using fibre Bragg grating sensors

Cited by 35 publications

References 27 publications

Passively Conducted Vibration Sensing with Fiber Bragg Gratings

Passively Conducted Vibration Sensing with Fiber Bragg Gratings

Experimental Investigation on Dynamic Behaviour of Heavy-Haul Railway Track Induced by Heavy Axle Load

Deep Learning–Based Fully Automated Pavement Crack Detection on 3D Asphalt Surfaces with an Improved CrackNet

Contact Info

Product

Resources

About