『您的瀏覽器不支援JavaScript功能,若網頁功能無法正常使用時,請開啟瀏覽器JavaScript狀態』

跳到主要內容區塊

工業技術研究院

:::

技術名稱: 智造檢測影像辨識技術

技術簡介

透過機器學習理論,蒐集大量已標註之檢測影像,以監督式學習的類神經網路模組,教導機器學習檢測與辨識的判斷標準,進而大幅提高自動化檢測與辨識之準確率。 AOI線寬比對與量測技術可將樣板影像與實際電路板因製程造成漲縮歪斜等現象之影像準確地對位,量測軟體會依據在樣板影像上定義量測項目於對應區域量測線寬。可量測60um線寬,重複精度±1um。同時,量測結果即時回饋給生產線人員作製程參數調整,提高生產良率。

Abstract

This technical using the supervise mode machine learning theory to train the model that can detect the defect of production. AOI line width measurement technology can accurately measure the width of the line in the PC Board. The measurement software will measure the corresponding items in the corresponding area based on the measurement items defined on the sample image. At the same time, the measurement results will feedback to the production line to adjust process parameters to improve production quality.

技術規格

. 使用AlexNet 8層之類神經網路架構 . 辨識率 > 99%、辨識誤報率(False Native Rate, FNR) < 30% . 以21”x 24” PCB為例,量測60 um之線寬其誤差小於1 um以下,量測時間為5分鐘/片

Technical Specification

. AlexNet 8 Layers Neural Networks . TPR > 99%、Inspection FNR < 30% . 21" x 24" PCB as an example, the measurement error was less than 1 um when the line width was 60 um. . Measurement time: 5 minute/piece.

技術特色

本技術透過機器學習理論,蒐集大量已標註之檢測影像,以監督式學習的類神經網路模組,教導機器學習檢測與辨識的判斷標準,進而大幅提高自動化檢測與辨識之準確率。 光學檢測之虛實整合檢測技術,除了應用在線寬量測之設備機台外,其中影像識別技術更是其關鍵能量。在影像識別技術部分,利用瑕疵分類技術,提高缺陷偵測率,並同時降低缺陷之錯誤分類率,提升良率與產品競爭力,擴大全球市佔率,帶動人均產值與產業鏈整體產值提升。

應用範圍

PCB缺陷檢測 線寬量測之設備機台

接受技術者具備基礎建議(設備)

光學檢測設備

接受技術者具備基礎建議(專業)

廠商擁有製造自動化光學檢測篩選機及檢測設備之研發能力,能承接工研院開發技術,但需要機器學習蒐集大量檢測影像,監督教導機器檢測與辨識,提高自動化檢測與辨識準確率。

技術分類 智慧視覺系統技術

聯絡資訊

聯絡人:翁季萍 智慧視覺系統組

電話:03-5915737 或 Email:cpweng@itri.org.tw

客服專線:+886-800-45-8899

傳真:03-5917531

[{"text":"企業網","weight":13.0},{"text":"材化所","weight":11.5},{"text":"機械所","weight":10.0},{"text":"綠能所","weight":9.4},{"text":"生醫所","weight":8.0},{"text":"半導體","weight":6.2},{"text":"南分院","weight":5.0},{"text":"太陽能","weight":5.0},{"text":"課程","weight":5.0},{"text":"遠紅外線","weight":5.0},{"text":"雷射","weight":4.0},{"text":"LED","weight":4.0},{"text":"LED可見光","weight":3.0},{"text":"5G","weight":3.0},{"text":"工研人","weight":3.0},{"text":"電光所","weight":3.0},{"text":"綠能與環境研究所","weight":3.0},{"text":"機械","weight":3.0},{"text":"資通所","weight":2.0},{"text":"面板","weight":2.0},{"text":"文字轉語音","weight":2.0},{"text":"實習","weight":2.0},{"text":"無人機","weight":2.0},{"text":"生醫","weight":2.0},{"text":"3D","weight":2.0},{"text":"v2x","weight":2.0},{"text":"員工","weight":2.0},{"text":"地圖","weight":2.0},{"text":"太陽光電","weight":2.0},{"text":"材料與化工研究所","weight":1.0}]