摘 要
CMOS影像感測器(Complementary Metal-Oxide Semiconductor Image Sensor, CIS)產業乃是一種技術、資本高度密集之產業，因此如何使生產機台利用率最大化，以其於在短時間內能將設備成本攤平，降低產品製造成本，創造公司競爭優勢，成為業界不斷追尋之目標。
就CMOS影像感測器生產測試而言，Chroma測試機與電源供應機為CMOS影像感測器生產測試中，最為關鍵之設備。為能維護此機台正常運作與確保產出量，機台之異常需能即使診斷出發生原因為何。目前於生產機台之維修，依然仰賴資深維修人員之經驗，但諸多因素，造成這些資深維修人員流動率偏高，以至於知識、技術與經驗傳承不易，企業難以獲得有效蓄積。
透過學者成功運用類神經網路於半導體機台異常分析之經驗並結合產線機台之維修人員經驗、相關測試資料與類神經網路（Artificial Neural Network, ANN）技術進行異常分類與解析，建構一套CMOS影像感測器生產測試機台異常診斷模型。倒傳遞類神經網路(Back Propagation Neural Network, BPN)用以找出異常現象與異常原因之關係，模型之效能則以網路績效加以衡量。
研究結果顯示，本研究所提出之模式對於CMOS影像感測器生產機台之異常原因診斷，可獲得良好之效果，因此本模式應可應用於相關領域之生產測試機台。

關鍵字：類神經網路、製造成本、網路績效

Abstract
CMOS image sensor (Complementary Metal-Oxide Semiconductor Image Sensor, CIS) is technology driven and highly capital -intensive industry. Hence the way to maximize the utilization of production equipment becomes the stepping stone for business to minimize its cost of equipment and manufacturing, also to create competitive advantage.

For production testing of CMOS image sensors, Chroma testing machine with the power supply unit is the most critical tool among all. In order to maintain normal operations and ensure the output volume of the machine, currently the production line is still dependent on the experience of senior maintenance staff. However due to many reasons, high turnover rate of senior maintenance staff results in difficulty of obtaining effective accumulation the knowledge, skills and experience.

Through scholars used of neural networks in the success experience of semiconductor machine failure analysis and combined with the experience machine production line maintenance personnel, the relevant test data and neural network (Artificial Neural Network, ANN) technology for fault classification and analysis, constructing a CMOS image sensor production test machine fault diagnosis mode. Back Propagation Neural Network (BPN) is used to identify the relationship between symptom and cause of the fault. Model efficiency is measured by the network performance.

The results show that the proposed model for the diagnostics of CMOS image sensor test tool malfunction obtained good results, so this model should be applied to related fields of test equipment.

Key word: Neural Network、Cost Of Manufacturing、Network Performance

致謝.....................................................I
摘要...................................................III
Abstract...............................................IV
目錄.....................................................V
表目錄..................................................VI
圖目錄.................................................VII
第一章 緒論..............................................1
1.1 研究背景與動機.......................................1
1.2 研究目的............................................3
1.3 研究步驟............................................3
第二章 文獻探討...........................................5
2.1 CMOS影像感測器動作原理 ............................5
2.2 CMOS影像感測器測試...............................10
2.3 類神經網路介紹 ..................................12
2.4 交叉驗證理論........................................20
2.5 類神經網路於半導體製程之應用...........................21
第三章 研究方法..........................................23
3.1 模式架構說明.....................................23
3.2 類神經網路模型訓練與測試...........................31
第四章 實證結果..........................................34
4.1 資料收集........................................34
4.2 類神經網路模型績效................................36
第五章 結論.............................................48
5.1 結論...........................................48
5.2 建議...........................................49
參考文獻................................................51

參考文獻
1.Yang, D.X.D, & Gamal, A.E., & Fowler, Boyd, & Tian, H.
(1999), A 640×512 CMOS image sensor with ultrawide
dynamic range floating-point pixel-level ADC, Solid-State
Circuits, IEEE Journal, Volume 34, Issue 12, Pages 1821-
1834.
2.Kavadias, S., Dierickx, B., Scheffer, D., Alaerts, A.,
Uwaerts, D., & Bogaerts, J.(2000), A logarithmic response
CMOS image sensor with on-chip calibration,Solid-State
Circuits, IEEE Journal, Volume 35, Issue 8, Pages 1146-
1152.
3.Kwangho Yoon, Chanki Kim, Bumha Lee & Doyoung Lee(2002),
A single-chip image sensor for mobile applications, Solid-
State Circuits, IEEE Journal, Volume 37, Issue 12, Pages
1839-1845.
4.L. Chua and L. Yang(1988), Cellular Neural Networks:
Theory, IEEE Trans. on Circuits and Systems, Volume 35,
Issue 10, Pages 1257-1272.
5.L. Chua and L. Yang(1988), Cellular Neural Networks:
Applications, IEEE Trans. On Circuits and Systems, Volume
35, Issue 10, Pages 1273-1290.
6.Wen-Chin Chen, Amy H.I. Lee, Wei-Jaw Deng & Kan-Yuang Liu
(2007), The implementation of neural network for
semiconductor PECVD process, Expert Systems with
Applications, Volume 32, Issue 4, Pages 1148–1153.
7.Trevor S. Wiens, Brenda C. Dale, Mark S. Boyce, G. Peter
Kershaw(2008), Three way k-fold cross-validation of
resource selection functions, ScienceDirect, ecological
modelling, Volume 212, Issue3-4, Pages 244–255.
8.Chao-Ton Su, Taho Yang, & Chir-Mour Ke(2002), A Neural-
Network Approach for Semiconductor Wafer Post-Sawing
Inspection, IEEE Trans. On Semiconductor Manufacturing,
Volume 15, Issue 2, Pages 260-266.
9.Yang-Kun Oua, Yung-Ching Liu, Feng-Yuan Shih(2012), Risk
prediction model for drivers’ in-vehicle activities –
Application of task analysis and back-propagation neural
network, Sciverse ScienceDirect, Transportation Research
Part F, Volume 18, Pages 83–93.
10.Kweon, K. E., J. H. Lee, Y.-D. Ko, M.-C. Jeong, J.-M.
Myoung & I. Yun(2007), Neural Network Based Modeling of
HfO2 Thin Film Characteristics Using Latin Hypercube
Sampling, Expert Systems with Applications, Volume 32,
Issue 2, Pages 358–363.
11.Chang, M., J.-C. Chen, J.-W. Cheng & J.-S. Heh(2006),
Advanced Process Control Expert System of CVD Membrane
Thickness Based on Neural Network, Progress on Advanced
Manufacture for Micro/Nano Technology 2005, Pt 1 and 2
Materials Science Forum, Volume 505-507, Pages 313-318.
12.Park, S.-J., M.-S. Lee, S.-Y. Shin, K.-H. Cho, J.-T.
Lim, B.-S. Cho, Y.-H. Jei, M.-K. Kim & C.-H. Park(2005),
Run-to-Run Overlay Control of Steppers in Semiconductor
Manufacturing Systems Based on History Data Analysis and
Neural Network Modeling, IEEE Transactions on
Semiconductor Manufacturing, Volume 18, Issue 4, Pages
605-613.
13.Kim, J. Y., J. K. Sim, M. J. Song, C. H. Kim & L. K. Kwac
(2004), The Performance Advancement of Test Algorithm
Using Neural Network for Semiconductor Packages,
Advances in Fracture and Failure Prevention, Pts 1 and 2
Key Engineering Materials, Volume 261-263, Pages 411-416.
14.王進德、蕭大全(1992)，類神經網路與模糊控制理論入門，全華電腦圖書資
料股份有限公司，台北市。
15.蘇木春、張孝德(2010)，機器學習：類神經網路、模糊系統以及基因演算法
則，全華電腦圖書資料股份有限公司，台北市。
16.張斐章、張麗秋、黃浩倫(2010)，類神經網路：理論與實務，臺灣東華書
局，台北市。
17.賴建勳(2007)，應用類神經網路於積體電路之化學氣相沉積機台故障診斷分
析碩士論文，國立成功大學工業與資訊管理學系碩士在職專班。
18.施柏屹(2000)，倒傳遞類神經網路學習收斂之初步探討碩士論文，國立中央
大學機械工程研究所。
19.賴郁廷(2011)，類神經網路應用於溼蝕刻機台流量分析，國立彰化師範大學
電機工程學系。
20.數位影像感知器(Digital Image Sensor)基礎原理介紹，
http://www.starfpga.com/modules/tinyd2。
17.維基百科自由的百科全書之細胞式類神經網路介，
http://zh.wikipedia.org/wiki/。
19.SAS RESOURCE CENTER，Dr.SAS專欄，活學活用類神經網路，
http://www.sasresource.com/artical138.html。
20.逍遙工作室-交叉驗證理論，
http://cg2010studio.wordpress.com。