Dynamic performance evaluation of an inspection wagon for urban railway tracks

Chang, Chao; Ling, Liang; Chen, Shiqian; Zhai, Wanming; Wang, Kaiyun; Wang, Guidong

doi:10.1016/j.measurement.2020.108704

Cited by 16 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model is trained based on alternating forward propagation of feature generation and backpropagation of loss calculation for updating the model parameters. In this study, the loss used in model training is , which is a combination of the damage classification loss ( ) and transfer loss ( ) [45]: (10) The damage classification loss aims to match the labels between the prediction and ground truth:…”

Section: B Model Trainingmentioning

confidence: 99%

“…In [8] and [9], the wavelet transform algorithm is employed to extract the characteristics of rail joint damage for rail joint monitoring. Chang et al [10] measures the dynamic response of rail to identify the misalignment-caused damage at rail joints. The above-mentioned studies have proposed effective methods to thoroughly investigate the damage mechanisms and recognize rail joint damage.…”

Section: Introductionmentioning

confidence: 99%

“…The above-mentioned studies have proposed effective methods to thoroughly investigate the damage mechanisms and recognize rail joint damage. However, the damage detection methods in [8]- [10] are realized through the track inspection wagon, which still relies on labor to collect massive data. Besides, these methods require manual feature extraction from data for damage detection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Discrepancy-Based Domain Adaptation Network to Detect Rail Joint Condition

Jiang,

Wang,

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Damage to maglev rail joints, which connect adjacent rail segments, threatens the safety and comfort of railway systems. Machine learning methods have been used in combination with online monitoring data to assess the health conditions of maglev rail joints. However, most of the existing methods rely on the data collected in controlled scenarios, such as those involving constant train operation speeds. Given the diversity of operational conditions, a model learned from one known case (source domain) cannot be directly applied to the case of interest (target domain). Therefore, this paper proposes a domain adaptation approach to diagnose the health conditions of maglev rail joints in complex operational conditions. The domain adaptation is unsupervised because the source and target domains are characterized by labeled and unlabeled samples, respectively. Domain adaptation is implemented by integrating the sample moments with different orders into the transfer loss of a neural network. By minimizing the transfer loss, the domain shift caused by the difference in the operational conditions can be reduced, and the knowledge of features learned from the neural network is transferred from the source domain to the target domain. The proposed approach is validated over a dataset of time-frequency spectrograms derived from the experimental acceleration data of maglev rail joints in two operation modes: stable passing and braking. The proposed approach can successfully identify the conditions of the maglev rail joints, i.e., bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition, even when the operation mode of the maglev train changes.

show abstract

Section: B Model Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Discrepancy-Based Domain Adaptation Network to Detect Rail Joint Condition

Jiang,

Wang,

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Also, it has been reported that the failures to which the vehicles are exposed are mostly caused by static and dynamic loads, especially in mountainous and climatic conditions. Due to *Corresponding Author Email: ounal@karabuk.edu.tr (Dr. O. Unal) these conditions, wagons are constantly modified with new design applications, and their components are constantly improved in terms of structural capability [10][11][12][13][14][15]. Prior to the design, development, analysis, and manufacturing of the railway vehicles, the features of the railway line should be examined, and the design criteria of the vehicles should be determined accordingly [16].…”

Section: Introductionmentioning

confidence: 99%

Design and finite element analysis of S355J2 wing holders on tank wagons

Unal,

Gursoy,

Duman

et al. 2023

JDAF

View full text Add to dashboard Cite

Wagon component failures that occur during service life can be reduced by applying appropriate geometric changes and using optimization techniques. Therefore, crucial changes are being studied to improve design and performance in structures such as connecting parts, braking systems, suspension, and transmission systems. The wing holders also have a load-bearing feature in connecting the body to the chassis. The strength of the wagon, component stabilization, and weight reduction are of great importance during transportation. In this study, finite element analysis was carried out for the novel type wing holders of the tank wagon system designed via simpler and stepless with various thicknesses. The von Mises stresses and total deformations, as finite element results, for the thicknesses of 10 mm, 12 mm, and 14 mm occurred due to the standard of EN 12663-2:2010 for both longitudinal and vertical loading conditions were extracted from the software. Finally, according to the design improvements, a new wing holder model was developed, which can contribute to the reduction of production and assembly costs.

show abstract

“…Automatic track surveying is based on patter analysis over sensed signals and images. Among sensing devices, different technologies such as thermal resistors [157], acoustic sensors [158,159], video recording [160][161][162][163][164][165]; [166,167]) or accelerators [149,[153][154][155][168][169][170][171][172][173][174][175][176][177][178][179][180][181][182][183][184][185][186][187] have been proposed. In particular, the use of acceleration sensors on axle-box has become more popular for detecting track irregularities of different wavelengths and occurrence.…”

Section: Railway Track Surveyingmentioning

confidence: 99%

Learning from limited labelled data: contributions to weak, few-shot, and unsupervised learning

Rodríguez¹

View full text Add to dashboard Cite

La presente tesis es el resultado de un largo camino formativo en el cual muchas personas han dejado su huella. Por ello, creo conveniente dedicar unas palabras de agradecimiento a las mismas.Me gustaría dedicar mis primeras palabras a mis directores, quienes me han otorgado la posibilidad de realizar esta tesis. A Ricardo y Pablo, por introducirme en el proyecto que ha hecho posible esta tesis. En especial, a Valery, por su consejo y ayuda en el día a día. Por ser la artífice de un grupo en el cual los jóvenes podamos crecer como investigadores, y aspirar a todas nuestras metas. Gracias.A quienes han compartido su conocimiento conmigo. A Adri, por apoyar mis primeros pasos en el ámbito de la visión por computador y el deep learning. A Jose Dolz, por abrirme nuevos caminos durante mi estancia en Montreal. Asímismo, querría acordarme del AlgoTeam de ContinUse, por apostar por mi y darme una invaluable formación en mis primeros años de investigador.Gracias a todos mis compañeros del CVBLAB por compartir ideas, bromas y amistad. A todos los que han compartido su camino con el mío: Gabri, Elena, Rocío, Cristian, Laëti y Claudio. A los que inician ahora el suyo: Alejandro, Pablo e Ilán. Mi eterna gratitud a quien más horas ha dedicado a esta tesis, día y noche, de forma desinteresada: gracias DGX, y gracias GPU-4.Finalmente, querría tener un agradecimiento especial a mi familia. A mis padres y hermano, por educarme, cuidarme, y apoyarme en todos mis proyectos. A Anny, por aguantar mi pasión, en ocasiones obsesiva, en este trabajo; por escucharme y aconsejarme siempre que lo necesitaba; y por acompañarme en este camino, y en los que están por venir. Os quiero.

show abstract

Dynamic performance evaluation of an inspection wagon for urban railway tracks

Cited by 16 publications

References 33 publications

Unsupervised Discrepancy-Based Domain Adaptation Network to Detect Rail Joint Condition

Unsupervised Discrepancy-Based Domain Adaptation Network to Detect Rail Joint Condition

Design and finite element analysis of S355J2 wing holders on tank wagons

Learning from limited labelled data: contributions to weak, few-shot, and unsupervised learning

Contact Info

Product

Resources

About