本文選題：金屬表面 + 瑕疵檢測(cè)　； 參考：《江南大學(xué)》2013年碩士論文

【摘要】：金屬工件廣泛應(yīng)用，是各種器械不可缺少的部件，隨著生產(chǎn)力的發(fā)展，用戶對(duì)其質(zhì)量也有更高的要求，而表面質(zhì)量是最直觀的體現(xiàn)，要求也往往更加嚴(yán)格。金屬工件表面瑕疵使工件外表不美觀的同時(shí)，更惡劣的是會(huì)影響工件的使用性能，使產(chǎn)品的安全性降低，必須在出廠前剔除。目前國(guó)內(nèi)大部分廠家還是采用人工目測(cè)法檢測(cè)，抽檢率低，檢測(cè)速度慢，檢測(cè)結(jié)果易受檢測(cè)人員主觀因素影響，缺乏一致的、科學(xué)的指導(dǎo)，各金屬制品企業(yè)亟需先進(jìn)的表面瑕疵檢測(cè)技術(shù)和設(shè)備。國(guó)外設(shè)備和技術(shù)，不僅價(jià)格昂貴，維護(hù)費(fèi)用高，而且還沒(méi)有自主知識(shí)產(chǎn)權(quán)，這些都迫使我們要開(kāi)發(fā)出符合企業(yè)需要的自動(dòng)化瑕疵檢測(cè)設(shè)備和技術(shù)。 本文以實(shí)驗(yàn)室現(xiàn)有各種金屬工件為檢測(cè)研究對(duì)象，結(jié)合機(jī)器視覺(jué)、圖像處理和模式識(shí)別等技術(shù)完成對(duì)本課題的研究。 （1）分析了表面瑕疵檢測(cè)流程中預(yù)處理、圖像分割、特征提取階段現(xiàn)有的一些算法，對(duì)其原理和算法實(shí)現(xiàn)進(jìn)行研究，并實(shí)驗(yàn)論證，為下一步的工作提供充分的理論基礎(chǔ)和技術(shù)支持。 （2）以軸承為研究對(duì)象，提出一種基于機(jī)器視覺(jué)技術(shù)的軸承防塵蓋表面瑕疵檢測(cè)方法，從硬件環(huán)境的搭建，到軟件算法的實(shí)現(xiàn)進(jìn)行了詳細(xì)說(shuō)明。采用藍(lán)色同軸光源作為檢測(cè)系統(tǒng)所用光源，克服金屬反光；采用最小二乘法擬合軸承外圓，根據(jù)軸承型號(hào)比例分割出防塵蓋區(qū)域，然后利用Otsu閾值分割和Roberts邊緣提取處理圖像，再與模板軸承比較，求出相差角度，由此將防塵蓋字符、非字符區(qū)域分離，兩部分是否存在瑕疵分開(kāi)判別，互不干擾。 （3）以鐵氧化物--磁瓦為研究對(duì)象，分析其表面瑕疵的類型和特點(diǎn)，運(yùn)用紋理分析的方法實(shí)現(xiàn)特征的提取。通過(guò)對(duì)Gabor濾波器參數(shù)表達(dá)式的研究，構(gòu)造了不同尺度、不同方向的Gabor濾波器組，并針對(duì)磁瓦表面瑕疵特點(diǎn)對(duì)Gabor濾波器組進(jìn)行了改進(jìn)，為了去除數(shù)據(jù)相關(guān)性和冗余性，運(yùn)用主成分分析法和獨(dú)立成分分析對(duì)提取到的特征進(jìn)行了降維。 （4）對(duì)BP神經(jīng)網(wǎng)絡(luò)和支持向量機(jī)的基本原理和算法實(shí)現(xiàn)方法進(jìn)行了研究，針對(duì)BP神經(jīng)網(wǎng)絡(luò)存在的不足，利用附加動(dòng)量和變學(xué)習(xí)率學(xué)習(xí)的方法進(jìn)行改進(jìn)；針對(duì)支持向量機(jī)核參數(shù)c和懲罰因子g選取困難，采用網(wǎng)格法和K-CV法對(duì)其實(shí)現(xiàn)尋優(yōu)。最后用磁瓦表面瑕疵數(shù)據(jù)對(duì)兩種分類器的分類效果進(jìn)行實(shí)驗(yàn)比較和結(jié)果分析。 通過(guò)實(shí)驗(yàn)證明，本文提出的軸承防塵蓋表面瑕疵檢測(cè)方法，，檢測(cè)系統(tǒng)采集到的軸承圖像清晰，瑕疵檢測(cè)算法正確率在96%以上，可實(shí)時(shí)的完成軸承防塵蓋表面瑕疵自動(dòng)檢測(cè)。通過(guò)改進(jìn)的Gabor濾波器組，實(shí)現(xiàn)了磁瓦表面瑕疵的特征提取，采用PCA，ICA分析法實(shí)現(xiàn)了特征降維，采用本文算法對(duì)磁瓦表面瑕疵進(jìn)行分類，總體正確率可以達(dá)到93%以上，為表面瑕疵檢測(cè)分類提供了一種新方法。
[Abstract]:Metal workpieces are widely used and are indispensable parts of various instruments. With the development of productivity, users have higher requirements for their quality, and the surface quality is the most intuitive embodiment, and the requirements are often more stringent. The surface defects of metal workpiece make the appearance of workpiece unattractive, and at the same time, it will affect the performance of workpiece and reduce the safety of product, so it must be eliminated before leaving the factory. At present, most domestic manufacturers still use manual visual testing. The sampling rate is low, the detection speed is slow, the test results are easily influenced by the subjective factors of the examiners, and they lack consistent and scientific guidance. All metal products enterprises need advanced surface flaw detection technology and equipment. Foreign equipment and technology, not only expensive, high maintenance costs, but also do not have independent intellectual property rights, which force us to develop automatic defect detection equipment and technology that meet the needs of enterprises. In this paper, we take all kinds of metal parts in the laboratory as the detection object, and finish the research on this subject with machine vision, image processing and pattern recognition technology. (1) analyze the pretreatment and image segmentation in the process of surface defect detection. At the stage of feature extraction, some existing algorithms are studied, and the experimental results are presented to provide sufficient theoretical basis and technical support for the next work. (2) taking bearing as the research object, This paper presents a method for detecting the surface defects of bearing dust-proof cover based on machine vision technology, from the construction of hardware environment to the realization of software algorithm. The blue coaxial light source is used as the light source of the detection system to overcome the metal reflection, the least square method is used to fit the outer circle of the bearing, and the dust-proof cover area is segmented according to the bearing type ratio, and then the image is extracted and processed by Otsu threshold and Roberts edge. Then compared with the formwork bearing, the angle of difference is calculated, and the dust-proof cover character, the non-character area and the defect of the two parts are separated. (3) the iron-oxide magnetic tile is taken as the research object. The types and characteristics of surface defects are analyzed, and the feature extraction is realized by texture analysis. By studying the expression of Gabor filter parameters, Gabor filter banks with different scales and directions are constructed, and Gabor filter banks are improved to remove data correlation and redundancy. Principal component Analysis (PCA) and Independent component Analysis (ICA) are used to reduce the dimension of the extracted features. (4) the basic principles and algorithms of BP neural network and support vector machine are studied, and the shortcomings of BP neural network are pointed out. The method of learning with additional momentum and variable learning rate is improved, and the kernel parameter c and penalty factor g of support vector machine are difficult to select, and the mesh method and K-CV method are used to optimize them. Finally, the classification effects of the two classifiers are compared and analyzed by using the surface defect data of the magnetic tile. It is proved by experiments that the method proposed in this paper is clear in the image of bearing collected by the detection system, and the correct rate of defect detection algorithm is over 96%, which can be used to detect the surface defects of the dust proof cover in real time. Through the improved Gabor filter bank, the feature extraction of the surface defects of the magnetic tile is realized, and the feature dimension reduction is realized by using the PCACICA analysis method. The algorithm of this paper is used to classify the surface defects of the magnetic tile, and the overall correct rate can reach more than 93%. It provides a new method for the classification of surface defect detection.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP274

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 潘洪平,董申,梁迎春,陳汝欣;鋼球表面質(zhì)量評(píng)價(jià)系統(tǒng)[J];軸承;2000年07期

2 樂(lè)靜;郭俊杰;朱虹;;金屬球面缺陷的圖像檢測(cè)方法[J];電子學(xué)報(bào);2007年06期

3 張志偉;楊帆;夏克文;楊瑞霞;;一種有監(jiān)督的LPP算法及其在人臉識(shí)別中的應(yīng)用[J];電子與信息學(xué)報(bào);2008年03期

4 梁亮;楊敏華;李英芳;;基于ICA與SVM算法的高光譜遙感影像分類[J];光譜學(xué)與光譜分析;2010年10期

5 趙桂林;朱啟兵;黃敏;;基于高光譜圖像技術(shù)的蘋(píng)果粉質(zhì)化LLE-SVM分類[J];光譜學(xué)與光譜分析;2010年10期

6 米曾真;謝志江;陳濤;楚紅雨;范兵;;重軌圖像增強(qiáng)與邊緣提取的關(guān)鍵技術(shù)[J];光學(xué)精密工程;2012年07期

7 賀秋偉;王龍山;于忠黨;李國(guó)發(fā);高立國(guó);;基于圖像處理和支持向量機(jī)的微型齒輪缺陷檢測(cè)[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2008年03期

8 張飛;塔西甫拉提·特依拜;丁建麗;買買提·沙吾提;田源;;ICA結(jié)合紋理特征的SVM鹽漬化信息提取研究[J];計(jì)算機(jī)工程與應(yīng)用;2010年09期

9 余冰,金連甫,陳平;利用標(biāo)準(zhǔn)化LDA進(jìn)行人臉識(shí)別[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2003年03期

10 王宏漫,歐宗瑛;采用PCA/ICA特征和SVM分類的人臉識(shí)別[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2003年04期

相關(guān)博士學(xué)位論文 前1條

1 王義文;鋼球表面缺陷檢測(cè)關(guān)鍵技術(shù)研究及樣機(jī)研制[D];哈爾濱理工大學(xué);2010年

本文編號(hào)：2118012