以機器視覺為基礎之內螺紋自動檢測系統

Abstract

由於內螺紋(Internal Thread)特殊的結構與空間位置的限制，目前尚未發現以機器視覺為基礎的內螺紋檢測機台。本研究發展一套光學螺紋塞規(Optical Thread Plug Gauge，OTPG)，可對內螺紋工件進行非接觸式的自動化檢測。OTPG乃以硬式工業內視鏡(Rigid Industrial Endoscope)及電荷耦合元件(Charge Coupled Device，CCD)組成取像光學模組，並透過觸發器(Trigger)與兩組馬達控制單元(Motion Control Unit)搭配，逐步拼貼連續拍攝到的部分螺紋影像，以重建出360度內螺紋壁的二維全周影像圖(Unwrapped Image)，接著，運用影像處理技術、以離散餘弦轉換(Discrete Cosine Transformation，DCT)為基礎之影像還原技術進行影像正規化、影像切割與瑕疵突顯。OTPG可偵測出螺紋坡(Flank)上凸起狀的刮痕(Scratch)，以及螺峰(Crest)或螺谷(Root)上凹陷狀的崩塌(Collapse)或裂痕(Flaw)。

This dissertation is to design and develop a novel optical thread plug gauge (OTPG) for internal thread inspection using machine vision. The OTPG is composed of a rigid industrial endoscope, a charge-coupled device (CCD) camera, and a two degree-of-freedom motion control unit. A sequence of partial wall images of an internal thread are retrieved and reconstructed into a two-dimensional unwrapped image. Then, a digital image processing, discrete cosine transformation-based image restoration scheme is used to normalize image, segment image, and enhance defect of the internal thread. The proposed OTPG provides an orientation-free and convenient method for detecting defects such as scratches, collapses, and flaws in an internal thread.