Contactless Rail Profile Measurement and Rail Fault Diagnosis Approach Using Featured Pixel Counting

Karaduman, Gulsah; Karaköse, Mehmet; Aydın, İlhan; Akın, Erhan

doi:10.31209/2019.100000125

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 6) We select the optimal coordinates and radii for the current population of circles to be propagated to the succeeding generation, employing a criterion that minimizes inaccuracies. (7) The individuals have a predetermined probability of undergoing partial swapping following the crossover process. (8) The aforementioned steps 3-7 should be reiterated.…”

Section: Coordinate Fitting For a R20 MM Circlementioning

confidence: 99%

See 1 more Smart Citation

Dynamic rail wear measurement: integration of RTK GNSS, IMU, and laser

Li,

Zhao,

Huang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Currently, laser sensors are widely utilized in railway systems for monitoring rail wear. However, the lack or insufficiency of rail waist data poses a challenge to accurately match profiles and calculate wear. In this paper, we propose a novel approach for dynamic rail wear monitoring that comprises three major modules: a filtering methodology to smooth rail profile data, fine compensation to calibrate the angle distortion, and fast profile alignment. Initially, the AF technique and Kalman filter are applied to reconstruct the profile. This is followed by integrating real-time kinematic (RTK) global navigation satellite system (GNSS), inertial measurement unit (IMU), and laser to precisely correct the rail profile dynamic distortion. Additionally, genetic algorithms (GA)-least squares (LS) method is used for rapid determination of the R20mm center of the profile. Rigorous testing and trials have demonstrated that our proposed approach achieves precision as low as 0.03 mm with significant potential in dynamic rail wear monitoring

show abstract

Section: Coordinate Fitting For a R20 MM Circlementioning

confidence: 99%

“…Extensive research has been conducted on rail profile measurement systems based on LVT [2][3][4][5]. In addition to providing real-time dynamic inspection capabilities [6,7], these systems also offer valuable insights into the overall condition of the rails [8,9].…”

Section: Introductionmentioning

confidence: 99%

Dynamic rail wear measurement: integration of RTK GNSS, IMU, and laser

Li,

Zhao,

Huang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Then, the obtained 2-D fastener images were transformed into a 1-D signal using the Gabor filter, and the fastener defects were classified with the multiple signal classification algorithm. Although techniques based on the Gabor filter [8] and edge detection [16,17] are used to locate the fastener, rail, and sleeper components, these techniques are often affected by noise and lighting conditions. A multi-tasking method has been proposed for the determination of tie and fastener defects using a deep learning method [8].…”

Section: Introductionmentioning

confidence: 99%

Defect Classification of Railway Fasteners Using Image Preprocessing and a Lightweight Convolutional Neural Network

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Railway fasteners are used to securely fix rails to sleeper blocks. Partial wear or complete loss of these components can lead to serious accidents and cause train derailments. To ensure the safety of railway transportation, computer vision and pattern recognition-based methods are increasingly used to inspect railway infrastructure. In particular, it has become an important task to detect defects in railway tracks. This is challenging since rail track images are acquired using a measuring train in varying environmental conditions, at different times of day and in poor lighting conditions, and the resulting images often have low contrast. In this study, a new method is proposed for the classification of defects on rail track fasteners. The proposed approach uses image enhancement to first filter the rail images and obtain a high contrast image. Then, the rail track and sleeper positions are determined from the high contrast image. The location of the fastener is determined by applying the Line Local Binary Pattern method and the defects of the fastener are classified using an improved lightweight convolutional neural network (LCNN) model. Features are extracted from two fully connected layers of the developed LCNN model and the feature vector is constructed by concatenating these layers. The concatenated features are processed using a number of machine learning methods and the optimum classifier is chosen. Experimental results show that Cubic SVM gives the best results with a detection accuracy rate of 99.7%.

show abstract

Contactless Rail Profile Measurement and Rail Fault Diagnosis Approach Using Featured Pixel Counting

Cited by 2 publications

References 0 publications

Dynamic rail wear measurement: integration of RTK GNSS, IMU, and laser

Dynamic rail wear measurement: integration of RTK GNSS, IMU, and laser

Defect Classification of Railway Fasteners Using Image Preprocessing and a Lightweight Convolutional Neural Network

Contact Info

Product

Resources

About