運用視覺辨識與機器手臂之微型天線自動化組裝系統

科技日新月異，電腦運算速度的提升，使得電腦不僅僅成為生活中重要的幫手，更是工廠生產線上不可或缺的主角，工業上的機械視覺應用廣泛，視覺檢測、影像追蹤、精密定位…等，皆可透過電腦來幫忙完成。而機械手臂也為工業中自動化最為便利的設備，它的活動範圍廣，可塑性高，能因應不同的環境，配合不同的設備方便且有效率的達到組裝、取放、搬運的功能，消費性電子產品由於體積小，所需的天線屬於微型天線，貼合精度要求甚高，利用影像辨識輔助機械手臂貼合天線，不但能克服人工貼合的缺點，並提高精度。　　本研究主要以Visual Studio C#/C++為基礎，建立一個影像定位的影像視覺系統，搭配EPSON的四軸機械手臂來完成空間平面上的定位，系統主要包括兩個部分，第一部分為影像處理，以攝影機擷取影像後，透過灰階化、濾波、二值化、和輪廓偵測找出所需要的目標位置，來進行定位，另一部分為座標計算，將第一部分所求出的目標座標，算出相對於機械手臂固定座標之偏移量，並控制其機械手臂到達其修正座標。本系統在生產時所產生的數據，可導入工業4.0的生態鏈，加以分析數據、修正參數、遠端監控、預測機械疲勞等應用。

關鍵字

自動化系統；視覺辨識；機器手臂

並列摘要

With the ever-changing nature of technology and the improvement of computing speed, computers have not only become an important part of our daily lives but also indispensable tools for factory production lines. Machine Vision can be widely used in varieties of industrial purposes, such as visual inspection, image tracking and precise positioning. Automatic robotic arms are also very important in the computer industry. They can reach into restricted work spaces from different angles with smooth motion. They can also complete a lot of tasks efficiently, such as grasping and carrying different objects or working on the auto assembly lines. With high precision and efficiency these robotic arms combined with Machine Vision, will in the future, replace manpower. This research is based on Visual Studio C#/C++ to introduce how to combine the automatic robotic system and Image Processing System to create an Image Visual System that will detect and position an image. We design a user interface that allows you to use Image Processing System to analysis and define final offset position. You can then control the robotic arms to move precisely into targeted location. This system can be used on Industry 4.0, Data Analysis, Corrected Parameter, Remote Monitoring and Fatigue Life Prediction.