Research of Computer Vision Fault Recognition Algorithm of Center Plate Bolts of Train

Yang, Xudong; Ye, Lianjie; Yuan, Jianbo

doi:10.1109/imccc.2011.246

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And then, inspectors indoor determine whether faults exist by observing the images, consuming a lot of time and manpower. Aiming to avoid disadvantages of manual inspection, some methods based on features of 2D images [7]- [12] were introduced. Although these approaches could recognize certain visible faults, it cannot detect bolt-loosening due to lack of depth information.…”

Section: Introductionmentioning

confidence: 99%

A Fast Bolt-Loosening Detection Method of Running Train’s Key Components Based on Binocular Vision

2019

View full text Add to dashboard Cite

Bolt-loosening can cause poor running quality of trains, even resulting in terrible accidents. Currently, existing bolt-loosening detection methods for running trains need 3D data of the whole train body, extremely decreasing the efficiency of fault detection. In this paper, we propose a fast bolt-loosening detection method for the running train's key components based on binocular vision. Since a train generally consists of many cars with the same structure, the position distribution of train's key components is regular and periodic. First, we propose a novel method to detect key component regions including bolts, taking full advantage of this periodic distribution rule. Second, the sub-pixel edges of the bolt cap and mounting surface in the localized regions are extracted and segmented, respectively, combining with the convolutional neural network (CNN). Finally, based on stereo matching and the binocular vision model, the 3D data of these edges are obtained to calculate the distance between the bolt cap and mounting surface. By comparing the calculated distance with the reference value, we can judge whether bolt-loosening has occurred. The experimental results indicate that multi-bolt looseness can be calculated simultaneously. The measurement repeatability and precision are superior to 0.03 and 0.08 mm, respectively, and the relative error is less than 1.42%. INDEX TERMS Binocular stereo vision, bolt loosening, convolutional neural network, edge extraction.

show abstract

Section: Introductionmentioning

confidence: 99%

A Fast Bolt-Loosening Detection Method of Running Train’s Key Components Based on Binocular Vision

2019

View full text Add to dashboard Cite

show abstract

“…TCPBL has a high incidence and can easily lead to the train derailment. In recent years, detection methods mainly focus on the statistical analysis of the shape and gray values of image for feature extraction, such as the constraint-rectangle calculator and gray average of local domain [4], the binary map and Hough transform [5] and the Haar-like features [6]. However these methods tend to suffer when variations in different factors (such as pose, illumination and occlusion etc.)…”

Section: Introductionmentioning

confidence: 99%

Fault Detection of Train Center Plate Bolts Loss Using Modified LBP and Optimization Algorithm

Zhang¹,

He²,

Yang³

2015

TOAUTOCJ

View full text Add to dashboard Cite

This paper presents a novel approach to fault detection of train center plate bolts loss based on Local Binary Patterns (LBP) and Gabor-GA optimization theory. A modified LBP operator including the positive-negative sign and magnitude components of local gray difference is introduced to extract much more texture information. Multi-channel Gabor wavelet with different scales and orientations is applied on the images to create new representations in the spatial domain. Then, the weight of each Gabor channel can be optimized through the Genetic Algorithm (GA) to obtain enhanced features. Finally, the weighted features are concatenated together and delivered into Support Vector Machine (SVM) network for classification. Experimental results show that the new approach can be an effective and reliable measure for monitoring fault.

show abstract

“…The photos can have the problems of blur, poor illumination, excess exposure, and occlusion. In recent years, only a few studies have been conducted with traditional feature extraction methods, such as the gray averages of local domain [4], the binary maps [5], and the Haar-like features [6]. However these methods tend to suffer when some factors (such as angle, illumination, and occlusion, etc.)…”

Section: Introductionmentioning

confidence: 99%

Fault Detection Based on Multi-Scale Local Binary Patterns Operator and Improved Teaching-Learning-Based Optimization Algorithm

Zhang

Yang

2015

Symmetry

Self Cite

View full text Add to dashboard Cite

Aiming to effectively recognize train center plate bolt loss faults, this paper presents an improved fault detection method. A multi-scale local binary pattern operator containing the local texture information of different radii is designed to extract more efficient discrimination information. An improved teaching-learning-based optimization algorithm is established to optimize the classification results in the decision level. Two new phases including the worst recombination phase and the cuckoo search phase are incorporated to improve the diversity of the population and enhance the exploration. In the worst recombination phase, the worst solution is updated by a crossover recombination operation to prevent the premature convergence. The cuckoo search phase is adopted to escape the local optima. Experimental results indicate that the recognition accuracy is up to 98.9% which strongly demonstrates the effectiveness and reliability of the proposed detection method.

show abstract

Research of Computer Vision Fault Recognition Algorithm of Center Plate Bolts of Train

Cited by 6 publications

References 8 publications

A Fast Bolt-Loosening Detection Method of Running Train’s Key Components Based on Binocular Vision

A Fast Bolt-Loosening Detection Method of Running Train’s Key Components Based on Binocular Vision

Fault Detection of Train Center Plate Bolts Loss Using Modified LBP and Optimization Algorithm

Fault Detection Based on Multi-Scale Local Binary Patterns Operator and Improved Teaching-Learning-Based Optimization Algorithm

Contact Info

Product

Resources

About