側照式SMD-LED瑕疵自動光學檢測系統

An AOI System for Side View SMD-LED Defect

張晴晴

指導教授 ： 彭德保

國立交通大學/管理學院/工業工程與管理系所/碩士(2010年)

https://doi.org/10.6842/NCTU.2010.00380

摘要

近年來，側照式SMD-LED因體積小、低耗能、高效能等眾多優點，已獲取龐大之市場需求。在全球年需求破億顆的產量下，傳統人工目視檢測方法很難達成高檢測速率以及瑕疵判定標準化等全面品檢需求。因此，本研究模擬封裝現場狀況研發一套自動化光學檢測系統，探討可精確、快速、穩定地檢測出側照式SMD-LED瑕疵。
本研究擬針對封裝現場每顆SMD-LED進行瑕疵檢測，包括：缺件、側翻、極性反、缺口、表面不潔，以及電極遺失等六個項目。檢測系統主要包含硬體機構、軟體系統與檢測演算法。設計符合現場實際狀況之硬體設備及軟體流程。硬體取像機構取得影像後，透過人機互動，半自動取得元件之欲檢測區域規範及標準元件資訊，做為判斷瑕疵之準則。而後，運用影像處理與圖形識別之瑕疵檢測演算法檢測之。透過本研究開發之自動化光學檢測系統，對側照式SMD-LED品質檢測之效果和速度將可大幅提升。

關鍵字

側照式SMD-LED ； 自動光學檢測系統 ； 影像處理 ； 圖形識別 ； 瑕疵檢測

並列摘要

In recent years, side view SMD-LED has accessed market demand due to its many advantages, such as small size, low power consumption , high efficiency, etc. With billion demands and so as production volumn, it is difficult to meet the requirement of high detection rate and consistent defect standard by traditional manual visual inspection. Therefore, an AOI system was developed in this Thesis. Under the consideration of real production line, every side view SMD-LED, was to be inspected. The types of defect may include: missing component, wrong orientation, inverse polarity, missing polarity, dirty surface, and surface nick .The developed inspection system includes hardware system, software system and detection algorithm. First, the hardware systems was triggered to take the image of one SMD-LED component in the packaged tape. Second , the ROI and the quality specification to judge the defect were set interactively by inspection expert. Finally, a set of image processing and pattern recognition methods were designed to inspect the defects. After a great deal of experimentation, the developed side view SMD-LED auto-inspection system showed its efficiency and effectiveness in promoting the side view SMD-LED inspection quality.

並列關鍵字

side-view SMD-LED ； auto-optical inspection ； image process ； pattern recognition ； defect detection

參考文獻

[3] E. R. Davies, Machine vision: theory, algorithms, practicalities, 2nd ed.: Academic, pp. 647-661, 1997.

[4] E. N. Malamas, E. G. M. Petrakis, M. Zervakis, L. Petit, and J. D. Legat, “A survey on industrial vision systems, applications and tools,” Image and Vision Computing, vol. 21, pp. 171-188, 2003.

[5] N. Otsu, “A Threshold Selection Method from Gray Level Histograms”, IEEE Transactions on Systems, Man, and Cybernetics, SMC-9, 62-66, (1979)

[6] Mandel, J., “Repeatability and Reproducibility,” Journal of Quality Technology, Vol.4,No.2,pp.74-85

[7] Montgomery, D. C. and Runger, G. C. “Gauge Capability Analysis and Designed Experiments, Part I : Basic Methods,” Quality Engineering, Vol.6,No.1,pp.115-135