http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces
( Linna Zhang ),( Shiming Chen ),( Yigang Cen ),( Yi Cen ),( Hengyou Wang ),( Ming Zeng ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.12
Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods.
Statistical evaluation method for cylindricity deviation using local least squares cylinder
Peng Zheng,Dongliang Liu,Fengxia Zhao,Linna Zhang 한국정밀공학회 2019 International Journal of Precision Engineering and Vol.20 No.8
Accurately evaluating cylindricity deviation is the most important requirement for the quality analysis and control of cylindrical products in modern industrial manufacturing processes. The cylindricity deviation of a whole cylinder is usually evaluated with measured points from the target surface. In practice, there are many local intrinsic characteristics that can be related to defects or manufacturing errors, and some precision cylindrical workpieces such as large bearings and rollers are very sensitive to the local cylindricity quality. Hence, it is necessary to evaluate and analyze the local cylindricity variation. In previous works, few methods have focused on the deviation evaluation of local patches of the measured workpieces, and variation of local characteristics could not be directly reflected. In this paper, we propose a new statistical evaluation method for cylindricity deviation using local least squares reference cylinder, which not only evaluates the local and global cylindricity deviations, but also presents deviation change features. This paper illustrates the theoretical basis of the statistical evaluation method, provides the evaluation operation process and parameters, and finally demonstrates the accuracy and feasibility of the proposed method according to the experimental results. The proposed method can be effectively used to provide a reliable verification of the product quality and to analyze the error sources in manufacturing and inspection phases.
Manyi Cao,Peng Zheng,Dongliang Liu,Jingjing Chang,Linna Zhang 한국정밀공학회 2021 International Journal of Precision Engineering and Vol.22 No.4
For workpieces with discontinuous surface characteristics such as shafts with keyways, obtaining continuous and valid measurement data is essential for assessing machining quality. In this paper, a Bayesian approach based on prior knowledge is proposed to evaluate the geometric characteristics of the discontinuous surface. Effective measurement data for discontinues surface is supplemented by accurate Bayesian parameter estimation. By using the supplemented data, the dimensional error and roundness error can be calculated. Using the in-process measurement method, the process progress can be adjusted in time according to the error value to realize the fusion control of dimension and roundness. Experimental investigations for machining multi-keyway shaft are carried out based on the proposed method. The results show that grinding workpieces with discontinuous surface by using the in-process measurement method based on Bayesian theory can significantly improve product quality and efficiency.