轧辊磨损形貌图像特征及分形研究

分类号学号************学校代码1 0 4 8 8密级
硕士学位论文
学位申请人:黄英钢
学科专业:材料科学与工程
****:***
答辩日期:2015 年5 月
A Dissertation Submitted in Partial Fulfillment of the Requirements
for the Degree of Master in Engineering
自动滚喷机
Research of Image Feature and Fractal on Roll Surface Morphology in Wear Process
Master Candidate:Huang Yinggang
Major:Materials Science and Engineering Supervisor  :Prof. Li lixin
Wuhan University of Science and Technology
Wuhan, Hubei 430081, P.R.China
May, 2015
万方数据
摘要
最佳位置 PO轧辊是轧机上的重要零件,其表面形貌直接影响到板带钢产品的表面质量甚至其织构组成。本文以轧辊形貌图像为研究对象,采集了不同轧制阶段下的轧辊表面图像信息,基于MATLAB 平台,研究了轧辊在磨损过程中形貌图像特征及分形行为特征的变化规律。本文研究内容包括:保安单元
(1)结合实验所得的轧辊形貌图像,对常用的图像处理方法进行了研究、分析和比较,到适合轧
辊形貌图像的处理算法,为图像特征的提取奠定基础。
(2)对轧辊磨损形貌图像进行分析和特征提取,得出各图像特征参数随轧辊磨损的变化规律,结果表明,圆形度﹑等效面积圆半径﹑二阶矩﹑纹理熵四个特征参数随轧辊磨损程度的增加都呈现出一定的变化规律,能够将其作为有效的特征参数来定量评价轧辊磨损状态。
五氟化锑(3)将分形理论引入到轧辊形貌图像分析中,用盒计数法计算出其形貌分形维数D,并分析了分形维数与轧辊磨损之间的关系,结果表明,分形维数D 可以作为判断轧辊磨损状态的特征参数。
(4)建立了用于轧辊磨损状态识别的BP 神经网络模型,并在此基础上研制出集图像处理与图像计算分析的一体化软件程序,通过实验验证得到所建立的神经网络和所开发的软件都具有较好的适用性与可靠性。
上述研究工作对于保证轧件的表面质量、提高轧制生产率具有十分重要的意义,同时为建立轧辊磨损形貌的定量评价体系提供了新途径。
关键词:轧辊磨损;表面形貌;图像处理;分形;BP 网络定心支片
I
Abstract
采油助剂Roller is an important part of rolling mill, the surface morphology of roll is directly related to the strip products’surface quality and even the texture component. This paper takes the roll image as the research object, collecting the image information of a grinding roller cycle under different stages. Based on the MATLAB toll, the paper also study the variation of image features and fractal characteristic in the wear process of roll. The research work includes:
(1)The usual processing method of image was researched, analyzed and collated based on roll surface image in this paper. The processing method adapted to roll surface image was discovered. The foundation for realizing the image characteristic extraction was laid.
(2)The characteristic of roll surface image was extracted and analyzed. The variation regularity of characteristic parameter with rool wear was obtained. The results show that the image features,such as circularity, equal-area-cirde radius, texture entropy and second-order moment have a regular change and can be used as quantitative parameters to describe the surface morphology of roll.
(3)The fractal theory was introduced to roll surface image analysis. The paper calculates the surface fractal dimension D by using the box counting method, and analyzes the relationship between the fra
ctal dimension and roll wear. The results show that fractal dimension can be used to judge roll wear condition.
(4)BP neural network model used to recognize the roll wear condition was established, and the software program of the integration of image proeessing and analysing was developed. The results show that the neural network and the software have good applicability and reliability.
All of this research work is important for warranting the surface quality of the products and increasing the rolling productivity. It supplys a new approach to establish the quantitative evaluation system for the wear morphology of  roll.
Keywords: roll wear; surface morphology; image processing; fractal; BP  network
II

本文发布于:2024-09-23 01:40:34,感谢您对本站的认可!

本文链接:https://www.17tex.com/tex/3/159464.html

版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系,我们将在24小时内删除。

标签:轧辊   磨损   图像   形貌   分形   研究   分析   特征
留言与评论(共有 0 条评论)
   
验证码:
Copyright ©2019-2024 Comsenz Inc.Powered by © 易纺专利技术学习网 豫ICP备2022007602号 豫公网安备41160202000603 站长QQ:729038198 关于我们 投诉建议