【摘要】：輪廓線的變點識別是質(zhì)量管理的研究熱點之一,當(dāng)前研究多以輪廓整體變化為識別對象,而對局部變化問題研究相對較少,且更少有在發(fā)現(xiàn)變異時間的同時能夠?qū)ふ业阶兓瘏^(qū)域在個體輪廓曲線上位置的系統(tǒng)方法。本文針對輪廓線局部變化識別問題,提出基于小波變換和聚類分析的方法。通過仿真性能評價,并與現(xiàn)有方法進行比較,結(jié)果顯示本方法能夠在更小的差異度檢測出變化并準(zhǔn)確定位變化區(qū)域。在文章的末尾,本文采用了一個實例對該方法的效果進行驗證。
[Abstract]:The variable point recognition of contours is one of the research hotspots of quality management. At present, most of the research focuses on the overall change of contours, but there are relatively few studies on the local change problems, and there are few systematic methods to find the position of the changing regions on the individual contours at the same time as the variation time is found. In this paper, a method based on wavelet transform and clustering analysis is proposed to solve the problem of local change recognition of contours. The simulation performance is evaluated and compared with the existing methods. The results show that this method can detect the change and accurately locate the change area at a smaller degree of difference. At the end of the paper, an example is used to verify the effect of this method.
【作者單位】： 天津大學(xué)管理與經(jīng)濟學(xué)部;
【分類號】：O213.1

【參考文獻】

相關(guān)期刊論文 前3條

1 余晃晶;;小波降噪閾值選取的研究[J];紹興文理學(xué)院學(xué)報(自然科學(xué)版);2004年03期

2 李飛;薛彬;黃亞樓;;初始中心優(yōu)化的K-Means聚類算法[J];計算機科學(xué);2002年07期

3 陳希孺;變點統(tǒng)計分析簡介[J];數(shù)理統(tǒng)計與管理;1991年02期

【二級參考文獻】

相關(guān)期刊論文 前1條

1 杜浩藩,叢爽;基于MATLAB小波去噪方法的研究[J];計算機仿真;2003年07期

，

本文編號：2500456