Efficient rail repair machine based on image recognition technology

Yang, Menglan; Luo, Laizhen; Tao, Menglun

doi:10.1088/1742-6596/1486/4/042023

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine vision-based monitoring method [20,21] identifies bolt loosening by monitoring the changes in bolt rotation angles. Park et al [22,23] utilized machine vision and image processing technology to directly capture digital images and measure the angle change of the nut before and after bolt loosening.…”

Section: Introductionmentioning

confidence: 99%

Head surface strain measurement based wireless bolt sensor with self temperature compensating

Wang,

Zhang,

Yang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Bolt loosening detection is crucial for ensuring the safe operation of equipment. Loosened bolts are hard to detect, and if left undetected, it can lead to catastrophic failures, especially for numerous bolts in large-scale structures. Therefore, the development of distributed bolt monitoring method and related sensors is highly necessary. In this paper, a novel bolt preload sensor with self-temperature compensation is proposed, based on the strain distribution of the bolt head end face. This study enhances previous research by conducting a detailed analysis of strain distribution at the edge of the bolt head surface. The finite element analysis (FEA) results show that the bolt preload has almost no effect on the circumferential strain in the edge region of bolt head surface. Based on this feature, the strain gauge is applied circumferentially along the edge of the bolt head face as a temperature compensation gauge. In this way, the measuring strain gauge and the temperature compensation gauge can be integrated on the surface of the bolt head, thus achieving self-temperature compensation for the sensor. An experimental device has been established and the experimental results show that the designed sensor has excellent linearity to the bolt preload and effective temperature compensation. For the monitoring of numerous bolts with a wide distribution, a wireless sensing network utilizing the proposed sensor has been designed. The proposed wireless bolt sensor is easy to install and replace, without redesigning or changing the existing structure, thus providing a simple and effective way to monitor large number of bolts with wide distribution.

show abstract

Section: Introductionmentioning

confidence: 99%

Head surface strain measurement based wireless bolt sensor with self temperature compensating

Wang,

Zhang,

Yang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Inspired by the existing manual visual inspection method, which involves marking anti-loosening lines on bolts for rapid initial assessment of their service status, many researchers have utilized the noticeable color difference between the anti-loosening lines and the surrounding environment to locate the bolt area. Furthermore, they have conducted corresponding studies on the shape characteristic variations of the anti-loosening lines before and after bolt loosening to qualitatively characterize the behavior of bolt loosening [20]- [23]. By transforming the complex task of recognizing the overall shape characteristics of bolts into a single line recognition problem, our approach offers significant advantages in terms of computational cost and universality compared to the two aforementioned methods.…”

Section: Introductionmentioning

confidence: 99%

A Novel Full-Angle Detection Method for Bolt Loosening Based on Color Segmentation

Kang,

Zhang,

Sun

et al. 2024

Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development,

View full text Add to dashboard Cite

In response to the existing problem of the inability to perform full-angle detection of bolt loosening based on anti-loosening lines segmentation, this paper develops a method based on color segmentation and directional vector calculation. Initially, the anti-loosening line image is segmented using an optimal threshold segmentation method for the R component and a non-linear stretching method for the a component under the transformation of Lab and RGB color spaces. Subsequently, morphological operations are performed on the image using an open operation. Then, the minimum bounding rectangle of the anti-loosening line connected domain area is determined through an angle progressive minimum encapsulation method, and its directional vector is established. Consequently, the full-angle of bolt loosening is calculated based on the four-quadrant arctangent function and specific adjustments. Finally, an experimental scheme is designed to validate the feasibility and accuracy of the proposed algorithm. The experimental results show that the detection algorithm can achieve a 0 to 360-degree loosening angle detection of bolts, with a maximum absolute error of 0.6345 degrees and a maximum relative error of 0.75%. The accuracy of the algorithm can meet the needs of engineering practice and exhibits significant potential for application.

show abstract

Efficient rail repair machine based on image recognition technology

Cited by 2 publications

References 0 publications

Head surface strain measurement based wireless bolt sensor with self temperature compensating

Head surface strain measurement based wireless bolt sensor with self temperature compensating

A Novel Full-Angle Detection Method for Bolt Loosening Based on Color Segmentation

Contact Info

Product

Resources

About