A Detection and Identification Method Based on Machine Vision for Bearing Surface Defects

Gu, Zhengyan; Liu, Xiaohui; Wei, Lisheng

doi:10.1109/icccr49711.2021.9349370

Cited by 10 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work [29] designed an online detection method for bearing side surface defects, and the experimental results show that the classification accuracy can reach 92.7%. The study of [30] proposed an automatic recognition method of bearing surface defects Compared with the existing work, the difference is that most of the datasets used in the existing research come from the laboratory, that is, artificial damages are made on healthy BRs, while our data are collected directly from the factory production site. The laboratory data is ideal.…”

Section: Upper and Lower End Surface Defect Detectionmentioning

confidence: 99%

Whole surface defect detection method for bearing rings based on machine vision

Zhou¹,

zhang²,

Zhou³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

As an important part of a bearing, a bearing ring (BR) is prone to producing various defects on each surface in the production process, which seriously affects the reliability of the bearing. To solve the problem in which multiple defects are randomly distributed on multiple surfaces and manual detection is difficult, an automatic method for detecting defects on the whole surface of BRs based on machine vision is proposed. Firstly, the characteristics of the BR's surface defects are analyzed, and an efficient scheme for acquiring the whole surface image of the BR is designed. Then, the method for detecting the defects on the whole surface of BRs is developed, and the corresponding image preprocessing, region of interest (ROI) extraction and defect recognition algorithms are designed. Finally, a visual inspection system to identify the defects on the whole surface of BRs based on a multi-station turnover process is developed. On the premise of determining the key parameters of the detection algorithm, the performance of the detection method is analyzed through the experimental method. The results show that the comprehensive accuracy of the proposed detection method is 95%, which meets the detection requirements. On this basis, the detection strategy is optimized, and the best parameter combination is obtained through the experiments, which further reduces the false detection rate of good products and the missed detection rate of defective products, both of which are less than 3.5%.

show abstract

Section: Upper and Lower End Surface Defect Detectionmentioning

confidence: 99%

Whole surface defect detection method for bearing rings based on machine vision

Zhou¹,

zhang²,

Zhou³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The effect of the traditional Canny algorithm relies on a manually set double threshold, and many scholars have optimized this problem. L. Wang et al proposed an adaptive double-threshold-improved Canny algorithm based on added gradients [ 27 ]; Gu et al adopted the improved Ostu algorithm [ 28 ] to adaptively generate Canny operator double thresholds according to the iterative threshold segmentation method [ 29 ]; Othman et al used the Canny operator for static gesture segmentation using the proposed adaptive thresholding method [ 30 ]. However, since the traditional Canny operator does not consider the influence of illumination changes, these algorithms perform adaptive processing on the threshold, but they still do not perform well in scenes with large illumination changes.…”

Section: Related Work and System Overviewmentioning

confidence: 99%

An Improved FAST Algorithm Based on Image Edges for Complex Environment

Ding

2022

Sensors

View full text Add to dashboard Cite

In complex environments such as those with low textures or obvious brightness changes, point features extracted from a traditional FAST algorithm cannot perform well in pose estimation. Simultaneously, the number of point features extracted from FAST is too large, which increases the complexity of the build map. To solve these problems, we propose an L-FAST algorithm based on FAST, in order to reduce the number of extracted points and increase their quality. L-FAST pays more attention to the intersection of line elements in the image, which can be extracted directly from the related edge image. Hence, we improved the Canny edge extraction algorithm, including denoising, gradient calculation and adaptive threshold. These improvements aimed to enhance the sharpness of image edges and effectively extract the edges of strong light or dark areas in the images as brightness changed. Experiments on digital standard images showed that our improved Canny algorithm was smoother and more continuous for the edges extracted from images with brightness changes. Experiments on KITTI datasets showed that L-FAST extracted fewer point features and increased the robustness of SLAM.

show abstract

“…Research on bearing defect detection has also evolved from using traditional image algorithms to deep learning methods. Zhengyan Gu et al [20] proposed a machine visionbased automatic detection and identification method for bearing surface defects. Tise method improves and combines the Ostu algorithm and the Canny algorithm to enhance the completeness and accuracy of bearing surface defect segmentation.…”

Section: Introductionmentioning

confidence: 99%

Research on Bearing Surface Scratch Detection Based on Improved YOLOV5

Jia,

Zhou,

Chen

et al. 2024

Sensors

View full text Add to dashboard Cite

Bearings are crucial components of machinery and equipment, and it is essential to inspect them thoroughly to ensure a high pass rate. Currently, bearing scratch detection is primarily carried out manually, which cannot meet industrial demands. This study presents research on the detection of bearing surface scratches. An improved YOLOV5 network, named YOLOV5-CDG, is proposed for detecting bearing surface defects using scratch images as targets. The YOLOV5-CDG model is based on the YOLOV5 network model with the addition of a Coordinate Attention (CA) mechanism module, fusion of Deformable Convolutional Networks (DCNs), and a combination with the GhostNet lightweight network. To achieve bearing surface scratch detection, a machine vision-based bearing surface scratch sensor system is established, and a self-made bearing surface scratch dataset is produced as the basis. The scratch detection final Average Precision (AP) value is 97%, which is 3.4% higher than that of YOLOV5. Additionally, the model has an accuracy of 99.46% for detecting defective and qualified products. The average detection time per image is 263.4 ms on the CPU device and 12.2 ms on the GPU device, demonstrating excellent performance in terms of both speed and accuracy. Furthermore, this study analyzes and compares the detection results of various models, demonstrating that the proposed method satisfies the requirements for detecting scratches on bearing surfaces in industrial settings.

show abstract

A Detection and Identification Method Based on Machine Vision for Bearing Surface Defects

Cited by 10 publications

References 3 publications

Whole surface defect detection method for bearing rings based on machine vision

Whole surface defect detection method for bearing rings based on machine vision

An Improved FAST Algorithm Based on Image Edges for Complex Environment

Research on Bearing Surface Scratch Detection Based on Improved YOLOV5

Contact Info

Product

Resources

About