首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于小波消噪技术的平直度模式识别方法
引用本文:贾春玉,单修迎,刘宏民.一种基于小波消噪技术的平直度模式识别方法[J].东北重型机械学院学报,2011(1):23-28.
作者姓名:贾春玉  单修迎  刘宏民
作者单位:[1]燕山大学轧制设备及成套技术教育部工程研究中心,河北泰皇岛066004 [2]燕山大学亚稳材料制备技术与科学国家重点实验室,河北秦皇岛066004
基金项目:国家高技术研究发展计划(863计划)资助项目(2009AA04Z143); 河北省自然科学基金资助项目(E2006001038); 河北省科技计划资助项目(10212101D)
摘    要:为了提高平直度模式识别的精度,引入小波消噪技术对平直度信号进行预处理,然后采用以1次、2次、3次和4次勒让德多项式作为平直度基本模式的基于最小二乘原理的多项式回归方法进行模式识别,提出了一种计算精度高、抗干扰能力强的平直度模式识别方法。该方法能够从本质上提高平直度模式识别的精度,计算过程稳定可靠,能够为平直度控制模型提供准确的平直度信息,适合在线应用。

关 键 词:平直度  模式识别  最小二乘法  勒让德多项式  小波消噪

A flatness recognition method based on wavelet de-noising techniques
Authors:JIA Chun-yu  SHAN Xiu-ying  LIU Hong-min
Affiliation:1.Engineering Research Center of Rolling Equipment and Complete Technology of Ministry of Education,Yanshan University,Qinhuangdao,Hebei 066004,China;2.State Key Laboratory of Metastable Materials Science and Technology,Yanshan University,Qinhuangdao,Hebei 066004,China)
Abstract:In order to increase the precision of flatness recognition,a new flatness recognition method is brought forward with high precision and strong anti-jamming ability by the Legendre polynomial regression method based on least square theory.It processes with the original flatness data by wavelet de-noising techniques with linear,quadratic,cubic and biquadratic Legendre orthogonal polynomials as flatness basic patterns.The method can increase the precision of flatness recognition with steady computational process and provide exact flatness information for flatness control model,being fit for on-line applications.
Keywords:flatness  pattern recognition  least square method  Legendre orthogonal polynomials  wavelet de-noising
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号