Using fuzzy sets to estimate the geometric parameters of surface damage

被引:3
作者
Konovalenko I.V. [1 ]
Pastukh O.A. [1 ]
Marushchak P.O. [1 ]
机构
[1] Ivan Pulyui Ternopil National Technical University, ul. Russkaya 56, Ternopil
关键词
damage detection; fuzzy distance; fuzzy geometry; fuzzy quasi-point; image recognition;
D O I
10.3103/S8756699016040014
中图分类号
学科分类号
摘要
This paper considers the influence of the variable parameters of a surface defect detection algorithm on the result of its operation. A method for estimating the influence of the variable parameters on the recognized geometric characteristics of the surface defect network is proposed. This method is based on representing the basic zones of the skeleton of the surface damage network in the form of compact fuzzy sets in two-dimensional space (fuzzy quasi-points). The set of points of the recognized object obtained for various combinations of the test algorithm parameters is represented in the form of a fuzzy set with a certain membership function. A method for calculating the geometric parameters of the damage network (length and slope) by means of fuzzy geometry is considered, and its use for determining the geometric parameters of the damage network of a continuous casting roller is demonstrated. © 2016, Allerton Press, Inc.
引用
收藏
页码:319 / 327
页数:8
相关论文
共 12 条
[11]  
Buckley J.J., Eslami E., Fuzzy Plane Geometry. I: Points and Lines, Fuzzy Sets Syst., 86, 2, pp. 179-187, (1997)
[12]  
Kuleshov E.L., Goodness-of-Fit Test Based on the Interval Estimation, Avtometriya, 52, 1, pp. 30-36, (2016)