雷射切割技術已廣泛地應用於半導體封裝製程中，如BGA(Ball Grid Array)和QFN(Quad Flat Non-lead)等，但由於雷射切割引起的熱效應問題，導致切割後會產生焦黑之現象，或切割深度問題仍待改善。因此，本論文之目的在進行雷射切割BGA及QFN之參數與輸出品質的塑模與預測，並找出最佳切割參數組合，能快速、完全地切下晶片，且產生較小的熱效應及切割線寬。
首先利用灰關聯分析(GRA)，分別以較少的BGA及QFN實驗組合，探討每一雷射參數對於切割品質之貢獻度，及獲得一組較佳之切割參數組合。接著使用較完整的實驗組合，利用複迴歸分析(MRA)及類神經網路(ANN)中的倒傳遞網路(BP)來分別建構BGA及QFN之雷射切割品質預測模型。在BGA之樹脂和基座方面，以雷射的電流、頻率、切割速度及切割次數為4個輸入參數，以切割深度、熱效應寬度及切割線寬度為3個輸出品質參數。在使用81組實驗組合之訓練部分及40種隨機實驗組合之測試部分後，發現採用類神經網路中的Levenberg-Marquardt (LM)演算法所獲得之誤差最低。在樹脂部份，其誤差分別為0.496%及1.786%；在基座部份，其誤差分別為0.797%及1.532%。在QFN方面，以雷射的電流、頻率及切割速度為3個輸入參數，樹脂及樹脂+銅分別的切割深度、熱效應寬度、切割線寬度為6個輸出品質參數。在使用27組實驗組合之訓練部分及14種隨機實驗組合之測試部分後，發現採用類神經網路中的LM演算法所獲得之誤差最低，其誤差分別為0.51%及1.665%。最後，根據類神經網路所建立之預測模型，再以基因演算法(GA)，找到了BGA之樹脂及基座、QFN之另一組最佳切割參數組合。
比較GRA、ANN結合GA之兩組切割參數組合及驗證實驗結果後，發現ANN結合GA之組合，可產生最佳的切割品質。本論文所提出之方法及找到的最佳參數組合，已經成功地使用在市售雷射切割機上，期待此方法能應用於其他相關之加工製程產業。

The laser cutting technology has been widely applied in Semiconductor Packaging Processes, such as BGA (Ball Grid Array), QFN (Quad Flat No-lead), etc. But the laser cutting leads to the heat affected zone (HAZ) and produces burn or the cutting depth control which may be improved. Therefore, the purpose of this dissertation intends to build a model and make prediction for laser cutting parameters related to laser output cutting qualities. An optimal cutting combination which has less widths of HAZ and cutting line and fast cutting speed in the complete cutting, is also located by using GA method.
Firstly, Grey relational analysis (GRA) is used to discuss the contribution of each laser parameter affecting cutting qualities and obtain a better cutting combination. Secondly, the multiple regression analysis (MRA) and back-propagation (BP) of artificial neural network (ANN) are employed to build the predicting models. The model for epoxy or substrate of BGA includes 4 laser parameters (the current, frequency, cutting speed, repetitive cutting times) and 3 laser output cutting qualities (the cutting depth, widths of HAZ and cutting line), respectively. After 81 sets of training data and 40 sets extra of testing data, the least average predicting errors by using the Levenberg-Marquardt (LM) algorithm of a BP for epoxy are 0.496% and 1.786%, and substrate are 0.797% and 1.532%. The model for QFN includes 3 laser parameters (the current, frequency, cutting speed) and 6 laser output cutting qualities (the cutting depth, widths of HAZ and a cutting line of epoxy and epoxy + Cu). After 27 sets of training data and 14 sets extra of testing data, the least average predicting errors by using the LM algorithm of a BP are 0.51% and 1.665%. Finally, an optimal cutting combination is located by utilizing the genetic algorithm (GA) based on the ANN predicting model. Compared confirmation experimental results of above two cutting combinations, the combination of ANN with GA can produce the best cutting qualities. The proposed methods and the obtained optimal cutting combination are used successfully in the laser cutting machines, and expected to be applied in other process industries.

Ajith A., “Meta learning evolutionary artificial neural networks”, Neurocomputing 2004;56:1-38.
Armitage P, Berry G, Statistical methods in medical research (4th ed), Matthews JNS, Blackwell Science; 2002.
Badran S.M., Al-Duwaish H.N., “Optimal output feedback controller based on genetic algorithms”, Electric Power Systems Research 1999;50:7-15.
Bariani P.F, Brushi S., Dal Negro T., “Studies on the prediction of springback in air vee bending of metallic sheets using an artificial neural network”, Journal of Materials Processing Technology 2004;152:395-400.
Beach, David P., Shotwell, Allen., Essue, Paul., Applications of lasers and laser systems, Englewood Cliffs, N.J., PTR Prentice Hall; 1993.
Benardos P.G., Vosniakos G.C., “Prediction of surface roughness in CNC face milling using neural networks and Taguchi's design of experiments”, Robotics and Computer Integrated Manufacturing 2002;18:343-354.
Cenna A.A., Mathew P., “Analysis and prediction of laser cutting parameters of fibre reinforced plastics (FRP) composite materials”, International Journal of Machine Tools & Manufacture 2005;42:105-113.
Chelani A.B., Chalapati Rao C.V., Phadke K.M., Hasan M.Z., “Prediction of sulphur dioxide concentration using artificial neural networks”, Environmental Modelling & Software 2002;17(2):159-166.
Chen N., Chian K., Her T.D., Lai Y.L., Chen C.Y., “Electrical characterization and structure investigation of quad flat non-lead package for RFIC application”, Solid-State Electronics 2003;47:315-322.
Cheng P.J., Lin S.C., “Using neural networks to predict bending angle of sheet metal formed by laser”, International Journal of Machine Tools & Manufacture 2000;40:1185-1197.
Chong E.K.P., Zak S.H., An Introduction to Optimization, Wiley, New York, 1996.
Chung J.S., Hwang S.M., “Application of a genetic algorithm to the optimal design of the die shape in extrusion”, Journal of Materials Processing Technology 1997;72:69-77.
Deng J., “Control problems of grey systems”, Systems and Control Letters 1982;5:288-294.
Deng J., “Introduction to grey system”, Journal of Grey System 1989;1:1-24.
Dias Jr. T., Milanez L.F., “Optimal location of heat sources on a vertical wall with natural convection through genetic algorithms”, International Journal of Heat and Mass Transfer 2006;49:2090-2096.
Din D.R., Tseng S.S., “A genetic algorithm for solving dual-homing cell assignment problem of the two-level wireless ATM network”, Computer Communications 2002;25:1536-1547.
Dobrzanski L.A., Owalski M.K., Madejski J., “Methodology of the mechanical properties prediction for the metallurgical products from the engineering steels using the Artificial Intelligence methods”, Journal of Materials Processing Technology 2005;164-165:1500-1509.
Dubey AK, Yadava V., “Multi objective optimization of NdYAG laser cutting of nickel-based superalloy sheet using orthogonal array with principal component analysis”, Optics and Lasers in Engineering 2008;46:124-132.
Goldberg D.E., Genetic Algorithms in search optimization and machine learning, Addision-wisley, New York, 1989.
Hagan M.T., Demuth H.B., Beale M.H., Neural network design, PWS Published company; 1996. pp.19-27.
Hamoudi W.K., “The effects of speed and processing gas on laser cutting of steel using a 2 kW CO2 laser”, International Journal for Joining of Materials 1996;9(1):31-36.
He X., Zhang X., Zhang S., Liu J., Li C., “Prediction of phase equilibrium properties for complicated macromolecular systems by HGALM neural networks”, Fluid Phase Equilibria 2005;238:52-57.
Holland J.H., Adaptation in natural and artificial systems, University of Michigan Press, Ann Arbor, MI; 1975.
Huang W., Lam H.N., “Using genetic algorithms to optimize controller parameters for HVAC”, Energy and Building 1997;26:277-282.
Kaebernick H., Jeromin A., Mathew P., “Adaptive control for laser cutting using striation frequency analysis”, Annals of CIRP — Manufacturing Technology 1998;47(1):137-140.
Karakus M., Kumral M., Kilic O., “Predicting elastic properties of intact rocks from index tests using multiple regression modeling”, International Journal of Rock Mechanics & Mining Sciences 2005;42:323-330.
Li C.H., Tsai M.J., Yang C.D., “Optimization of Laser Cutting Parameters for QFN Packages by Taguchi’s Matrix Experimental Method”, Optics & Laser Technology 2007;39(4):786-795.
Li K., Sheng P., “Plane stress model for fracture of ceramics during laser cutting”, International Journal of Machine Tools & Manufacture 1995;35:1493-1506.
Lin C.Y., A Study on Camera Calibration of Autonomous Vehicle Based on Genetic Algorithm, Master thesis, Taiwan, 2000. pp. 11-17.
Lin JL, Lin CL., “The use of the orthogonal array with grey relational analysis to optimize the electrical discharge machining process with multiple performance characteristics”, International Journal of Machine Tools & Manufacture 2002;42:237-244.
Mitchell M., An Introduction to Genetic Algorithms, The MIT press, London, 1996.
Moller A.F., “A scaled conjugate gradient algorithm for fast supervised learning”, Neural Networks 1993;6:525-533.
Nagarajan R., Parametric study of the effect of laser cutting variables on the cut quality, Master thesis, Wichita State University, Wichita, Kansas, 2000.
Neimeyer R., Smith R.N., Kaminski D.A., “Effects of operating parameters on surface quality laser cutting of mild steel”, Journal of Engineering for Industry 1993;115:359-366.
Olympus Company
Olsen F., Investigations in optimizing the laser cutting process, In: Lasers in materials processing, Conference Proceedings, American Society for Metals, Los Angeles, USA, 1983. pp. 64-80.
Petropoulos G., Vaxevanidis N.M., Pandazaras C., “Modeling of surface finish in electro-discharge machining based upon statistical multi-parameter analysis”, Journal of Materials Processing Technology 2004;155-156:1247-1251.
Rajaram N., Sheikhahmad J., Cheraghi S.H., “CO2 laser cut quality of 4130 steel”, International Journal of Machine Tools & Manufacture 2003;43:351-358.
Rajendran N., Pate M.B., “The effect of laser beam velocity on cut quality and surface temperature”, American Society of Mechanical Engineers, Heat Transfer Division 1988;104:121–127.
Rofin-Baasel Company
Sheng P.S., Joshi V.S., “Analysis of heat-affected zone formation for laser cutting of stainless steel”, Journal of Materials Processing Technology 1995;53:879-892.
Sheng P., Cai L.H., “Model-based path planning for laser cutting of curved trajectories”, International Journal of Machine Tools & Manufacture 1996;36:739-754.
Singh U.K., Tiwari R.K., Singh S.B., “One-dimensional inversion of geo-electrical resistivity sounding data using artificial neural networks—a case study”, Computers & Geosciences 2005;31:99-108.
Singh V., Tathavadkar V., Rao S.M., Raju K.S., “Predicting the performance of submerged arc furnace with varied raw material combinations using artificial neural network”, Journal of Materials Processing Technology 2007;183:111-116.
Sitek W., Dobrzanski L.A., “Application of genetic methods in materials’ design”, Journal of Materials Processing Technology 2005;164-165:1607-1611.
Steen W.M., Kamalu J.N., Laser Cutting. In: Bass M, editor. Laser Materials Processing, vol. 3, New York: North Holland; 1983. pp. 17-111.
Taguchi G., Introduction to quality engineering, Tokyo: Asian Productivity Organization; 1990.
Tee T.Y., Zhong Z., “Board level solder joint reliability analysis and optimization of pyramidal stacked die BGA packages”, Microelectronics Reliability 2004;44(12):1957-1965.
Thawari G., Sarin Sundar J.K., Sundararajan G., Joshi S.V., “Influence of process parameters during pulsed Nd:YAG laser cutting of nickel-base superalloys”, Journal of Materials Processing Technology 2005;170:229-239.
Tsai M.J., Li C.H., Chen C.C., “Optimal Laser Cutting Parameters for QFN Packages by Utilizing Artificial Neural Networks and Genetic Algorithm”, Journal of Materials Processing Technology 2008;208:270-283.
Tsai M.J., Li C.H., “The use of grey relational analysis to determine laser cutting parameters for QFN packages with multiple performance characteristics”, Optics and Laser Technology 2009;41:914-921.
Yilbas B.B., “Laser cutting quality assessment and thermal efficiency analysis”, Journal of Materials Processing Technology 2004;155-156:2106-2115.
Zhou B.H., Mahdavian S.M., “Experimental and theoretical analyses of cutting nonmetallic materials by low power CO2-laser”, Journal of Materials Processing Technology 2004;146:188-192.