(34.204.185.54) 您好!臺灣時間:2021/04/16 19:18
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:葉典瓚
研究生(外文):Tien-Tsan Yeh
論文名稱:建構拉焊機感測系統之人機介面與機器學習
論文名稱(外文):Constructing Human-Machine Interface and Machine Learning for the Soldering Sensing System
指導教授:陳怡呈陳怡呈引用關係
學位類別:碩士
校院名稱:國立中央大學
系所名稱:光機電工程研究所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:中文
論文頁數:78
中文關鍵詞:烙鐵故障瑕疵焊點評估機器學習
相關次數:
  • 被引用被引用:1
  • 點閱點閱:78
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
電子焊接是連接器製造過程中最重要的一環,因為電子焊接會產生瑕疵焊點,直接導致產品功能失效,因此發展預測性維護是重要的。本研究以拉焊(Drag Soldering)工站為智慧化目標,以RJ45連接器為焊接對象,利用生產之參數建構機器學習模型,建立感測系統即時輔助產線人員判斷產品是否通過。
研究分為三個部分,分別是機台狀態評估與失效文獻回顧、設計實做軟硬體整合、實驗結果分析討論。首先對於拉焊製程進行評估,整理焊接瑕疵種類並評估感測器佈置之優先順序,決定以烙鐵失效為優先監測。再來以佇列式訊息處理器(Queued Message Handler)做為軟體系統架構,實做軟硬體模組並整合在主人機介面,佈署與烙鐵相關的影像與溫度訊號擷取、訊號前處理、訊號特徵擷取,佈署與焊接平台相關之步進馬達控制、焊點影像擷取、影像分析,佈署與外部系統或功能串連如MySQL資料庫模組,預測生產狀態之機器學習模型。
最後規劃焊接實驗,以多個分類算法作為生產預測狀態,以回歸算法作為因果關係確認。以生產參數作為輸入,焊接通過與否與不良率分別作為模型分類標記,其中最佳的分類模型是支持向量機,實驗預測準確度為88.88%,AUC值達0.97。回歸模型使用之參數與良率t檢定有顯著,證明結果非隨機。
Electronic soldering is the most important part of the connector manufacturing process. Because electronic soldering can produce solder joints, which directly leads to product failure, it is important to develop predictive maintenance. In this study, the Drag Soldering station was used as the intelligent target, and the RJ45 connector was used as the soldering object. The machine learning model was constructed by using the parameters of the production, and the sensing system was established to assist the production line personnel to judge whether the product passed.
The research is divided into three parts, namely, machine state evaluation and failure literature review, design implementation of software and hardware integration, and analysis of experimental results. First, the soldering process was evaluated, the types of soldering defect were sorted and the priority of the sensor arrangement was evaluated, and the failure of the soldering iron was prioritized. Then use the Queued Message Handler as the software system architecture, and implement the software and hardware modules and integrate them into the host computer interface. The image and temperature signals related to the soldering iron are extracted and pre-processed. Signal feature acquisition, stepper motor control related to soldering platform, solder joint image capture, image analysis, subordinate and external system or function serial connection such as MySQL database module, machine learning model for predicting production status.
Finally, the soldering experiment is planned, and multiple classification algorithms are used as the production prediction state, and the regression algorithm is used as the causal relationship confirmation. Taking the production parameters as input, the soldering pass or fail and the defect rate are respectively used as model classification labels. The best classification model is support vector machine, the experimental prediction accuracy is 88.88%, the AUC value is 0.97. The parameters used in the regression model and the yield rate were significant, indicating that the results were not random.
目錄
摘要 ii
Abstract iii
致謝 iv
目錄 i
圖目錄 iv
表目錄 vii
符號定義 viii
第1章 緒論 1
1.1研究背景 1
1.2 文獻回顧 2
1.2.1先進製造系統 2
1.2.2電子零組件焊接分析方法 6
1.3研究動機與目的 10
1.4 論文架構 11
第2章 基本理論 12
2.1 機器視覺 12
2.1.1 機器視覺組成與影像處理原則 12
2.1.2 相機、鏡頭與照明評估 13
2.2 機器學習分類算法與模型評估 18
2.2.1 決策樹 18
2.2.2 羅吉斯回歸 19
2.2.3 支持向量機 20
2.2.4 隨機森林 23
2.3資料庫系統 23
2.3.1 關聯式資料庫 23
2.3.2 結構化查詢語言 24
2.4產品不良評估 26
2.4.1 RJ45焊接瑕疵探討 26
2.4.2烙鐵失效探討 28
第3章 軟體系統架構與模組 29
3.1佇列訊息處理架構 31
3.2系統功能模組 37
3.2.1烙鐵影像特徵擷取演算法模組 37
3.2.2 MySQL資料庫整合模組 38
3.2.3 Python機器學習與Labview整合模組 40
3.2.4 瑕疵焊點視覺檢測模組 42
第4章 RJ45焊接應用 43
4.1 拉焊實驗平台佈署 43
4.1.1自動焊錫機 45
4.1.2溫度訊號量測佈署 45
4.1.3烙鐵表面影像量測佈署 45
4.4.4移動平台與電路板影像佈署 47
4.2 研究量測架構 47
4.2.1 系統量測與模型分析流程 47
4.2.2 自動焊錫機運作流程 49
4.2.3 量測軟體自動量測流程 50
4.2.4 Python機器學習分析流程 52
第五章 實驗結果與討論 53
5.1 焊接瑕疵迴歸評估模型 55
5.2 焊接瑕疵機器學習分類模型 57
第六章 結論與未來工作 59
6.1 結論 59
6.2 未來工作 60
參考文獻 61
[1] 科技產業資訊室,「工業4.0與機械4.0範疇及內涵」,取自http://iknow.stpi.narl.org.tw/Post/Read.aspx?PostID=11726(2019.06.14)。
[2] J. Lee, B. Bagheri, and H. A. Kao, "A Cyber-Physical Systems Architecture for Industry 4.0-Based Manufacturing Systems", Manufacturing Letters, Vol. 3, pp. 18-23, 2015.
[3] F. T. Cheng, H. Tieng, H. C. Yang, M.-H. Hung, Y. C. Lin, C. F. Wei, and Z.-Y. Shieh, "Industry 4.1 for Wheel Machining Automation", Robotics and Automation Letters, Vol. 1, No.1, pp. 332-339, 2016.
[4] H. C. Huang, Y. C. Lin, M. H. Hung, C. C. Tu, and F. T. Cheng, "Development of Cloud-Based Automatic Virtual Metrology System for Semiconductor Industry", Robotics and Computer-Integrated Manufacturing, Vol. 34, pp. 30-43, 2015
[5] H. Rostami, J. Y. Dantan, and L. Homri, "Review of Data Mining Applications for Quality Assessment in Manufacturing Industry: Support Vector Machines", International Journal of Metrology and Quality Engineering, Vol. 6, No. 4, pp. 401-418, 2015.
[6] S. Lv, H. Kim, B. Zheng, and H. Jin, "A Review of Data Mining with Big Data Towards Its Applications in The Electronics Industry", Applied Sciences, Vol. 8, No. 4, p. 582, 2018.
[7] Z. Shi, J. Lee, and P. Cui, "Prognostics and Health Management Solution Development in LabVIEW: Watchdog Agent® Toolkit and Case Study", Prognostics and System Health Management Conference, pp. 1-6, 2016.
[8] A. Lukindo, “LabVIEW Queued State Machine Consumer Producer Architecture”, 取自http://www.mezintel.com/blog/labview-queued-state-machine/(2019.06.14)
[9] 莊寶鵰,張添盛,黃仕慶,「電子組裝製程失效模式與效應分析之探討」,中華民國品質學會第38 屆年會暨第8 屆全國品質管理研討會,2002。
[10] E. D. Castillo, “Process Optimization: A Statistical Approach. Springer Science & Business Media”, 2007.
[11] W. Sauer, M. Oppermann, G. Weigert, S. Werner, H. Wohlrabe, K. J. Wolter, and T. Zerna, “Electronics Process Technology: Production Modelling, Simulation and Optimization”, Springer Science & Business Media, 2007.
[12] E. Alhoniemi, “Unsupervised Pattern Recognition Methods for Exploratory Analysis of Industrial Process Data”, Doctoral thesis, Helsinki University of Technology, Finland, 2002.
[13] M. Liukkonen, E. Havia, and Y. Hiltunen, “Computational Intelligence in Mass Soldering of Electronics–A survey,” Expert Systems with Applications, Vol. 39, No. 10, pp. 9928-9937, 2012.
[14] M. Liukkonen, T. Hiltunen, E. Havia, H. Leinonen, and Y. Hiltunen, “Modeling of Soldering Quality by Using Artificial Neural Networks,” IEEE Transactions on electronics packaging manufacturing, Vol. 32, No. 2, pp. 89-96, 2009.
[15] M. Liukkonen, E. Havia, H. Leinonen, and Y. Hiltunen, “Application of self-Organizing Maps in Analysis of Wave Soldering Process”, Expert Systems with Applications, Vol. 36, No. 3, pp. 4604-4609, 2009.
[16] T. N. Tsai and C. W. Tsai, “ Development of A Closed-Loop Diagnosis System for Reflow Soldering Using Neural Networks and Support Vector Regression”, International Journal of Industrial Engineering, Vol. 21, No. 1, pp. 19-33, 2014.
[17] J. J. Sha, and E. S. Pan, “Soldering Parameter-Setting Approach Based on Improved Adaptive Neuro Fuzzy Inference Model”, Journal of Shanghai Jiaotong University, Vol.45, No.12, pp. 1741-1746, 2011.
[18] F. Howie, D. Tilbrook, and C. Lea, “Blowholing in PTH Solder Fillets: Part 7 Optimising the Soldering,” Circuit World, Vol. 13, No. 2, pp. 42-45, 1987.
[19] P. Mesenbrink, J. C. Lu, R. McKenzie, and J. Taheri, “Characterization and Optimization of a Wave-Soldering Process", Journal of the American Statistical Association, Vol. 89, No. 428, pp. 1209-1217, 1994.
[20] Y. H. Lin, W. J. Deng, J. R. Shie, and Y.-K. Yang, “Optimization of Reflow Soldering Process for BGA Packages by Artificial Neural Network”, Microelectronics international, Vol. 24, No. 2, pp. 64-70, 2007.
[21] A. McAndrew, J.H. Wang, and C.S. Tseng, “Introduction to Digital Image Processing with MATLAB”, 2011.
[22] 陳煜彬,「應用機器視覺之新式晶圓定位方法」,國立中央大學光機電工程研究所碩士論文,民國100年。
[23] 張軒慈,「應用繞射光學元件之齒輪量測系統開發」,國立中央大學光機電工程研究所碩士論文,民國105年。
[24] 陳智怡,「應用投射疊紋技術於齒輪精度量測」,中央大學光機電工程研究所碩士論文,民國106年。
[25] 歐智達光源,「同軸光源產品詳細資訊」,取自http://omnitek-lights.com/products/?p=OKCL&t=%E5%90%8C%E8%BB%B8%E7%87%88(2019.06.14)
[26] 周至華,「機器學習」,清華大學出版社,2016。
[27] L. Breiman, ”Classification and Regression Trees”, Routledge, 2017.
[28] 「支持向量機」,取自https://zh.wikipedia.org/wiki/支持向量機(2019.06.14)。
[29] N. J. Nalini, and S. Palanivel, "Music emotion recognition: The combined evidence of MFCC and residual phase", Egyptian Informatics Journal, Vol 17, pp. 1–10, 2016.
[30] 「邏輯回歸」,取自https://en.wikipedia.org/wiki/Logistic_regression(2019.06.14)。
[31] L. Breiman, ”Random forests”, Machine Learning, Vol 45, pp 5–32, 2001
[32] "IPC-A-60 Post Solder Solvent Cleaning Handbook", 取自http://www.ipc.org/toc/ipc-sc-60a.pdf(2019.06.14)
[33] OK International Inc, “ Technical Note: Extending Soldering Iron Tip Life”, 2006.
[34] R. C. Martin, “Clean Architecture: A Craftsman's Guide to Software Structure and Design”
[35] 游峰碩,「UML物件導向系統分析與設計」,博碩文化,2017。
[36] National Instruments, “Queued Message Handler Template documentation”, 取自 http://www.ni.com/tutorial/53391/en/ (2019.06.14)
[37] J. A. Swets, ”Signal detection theory and ROC analysis in psychology and diagnostics : collected papers”, Lawrence Erlbaum Associates, 1996.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔