臺灣博碩士論文加值系統

現今社會因為3C產品充斥在我們的生活中，印刷電路板（PCB）變得越來越重要。幾乎所有的電子設備都需要使用到PCB，因此PCB是全球電子市場重要的部分。換句話說，對PCB的需求正在增加，因此公司需要加快他們的生產線。PCB在製造期間多少都會發生缺陷，這缺陷通常都是電鍍通孔（PTH）過程中所發生的孔隙（HVs），這會使得生產線的速度下降，雖然有很多方法可以快速檢測孔隙的產生，但這些方法的成本都太高。本論文將介紹一種基於相空間重構（PSR）和卷積神經網絡（CNN）預測孔隙發生的方法。目前這方法有11種參數當作輸入值，首先標準化每個參數，使每個參數都在同一個範圍內。第二，利用平均分佈來找出合理的參數範圍，並將超出範圍的值變成新的參數。第三，使用PSR方法為每個參數構建新值。第四，將訓練出來的多個模型進行整合方法(Ensemble)中的加權投票，使出來的結果更加準確。經測試後，我們建立的模型靈敏度為80％以上，準確率接近90%。 結果表明，該方法可以預測孔隙將發生或不發生。

Nowadays, printed circuit board (PCB) becomes more and more important, because the 3C products are omnipresent in our lives. Almost all electronic devices require PCB support, so the PCB is a big component in the global electronics market. In other words, the demand for PCB is increasing, so the company needs to speed up their production line. The defects (hole voids) happened during printed circuits boards manufacturing process, in particular the plating through the holes (PTH) process, and it made the production line slow down. Although there are many ways to check the defects quickly, the cost of these methods is too high. This thesis introduces a way to predict the hole voids based on the phase space reconstruction (PSR), and convolutional neural network (CNN). There are 11 kinds of parameters as the input of the method. First, we normalized each parameter. Second, the standard deviation is used to find the reasonable boundary of concentration, and take the value which out of the boundary as the new value. Third, we use PSR method to build the new value for each parameter. Forth, we take several CNN models to do the weighted vote in ensemble method to make the result much better. After testing, we established the model sensitivity is more than 80%, and accuracy rate is close to 90%. The results demonstrate that the approach has desirable predict to the hole voids to happen or not.

A Thesis……………………………………………………………………………………………………… i
ABSTRACT……………………………………………………………………………………………………… iii
誌謝………………………………………………………………………………………………………………… vi
Contents……………………………………………………………………………………………………… vii
List of Tables……………………………………………………………………………………… viii
List of Figures…………………………………………………………………………………… ix
Abbreviation…………………………………………………………………………………………… xi
Chapter 1: Introduction
1.1 Literature survey………………………………………………………… 1
1.2 Printed circuit board manufacturing process……………………………………………………………………………………………………… 4
Chapter 2: Methodology
2.1 Preprocessing…………………………………………………………………… 6
2.2 Phase space reconstruction………………………………… 13
2.3 Artificial neural network…………………………………… 18
2.4 Convolutional neural network…………………………… 19
2.5 Ensemble………………………………………………………………………………… 22
Chapter 3: Results
3.1 CNN……………………………………………………………………………………………… 24
3.2 CNN with ensemble………………………………………………………… 27
Chapter 4: Summary………………………………………………………………………… 29
References……………………………………………………………………………………………… 30

[1] Chamberlin, B. J., Chu, C. M., Hu, G. B., Kuczynski, J., & Tsang, K. K. C. (2016). U.S. Patent No. 9,250,192. Washington, DC: U.S. Patent and Trademark Office.
[2] Huang, X., Zhu, S., Huang, X., Su, B., Ou, C., & Zhou, W. (2015, August). Detection of plated through hole defects in printed circuit board with X-ray. In Electronic Packaging Technology (ICEPT), 2015 16th International Conference on (pp. 1296-1301). IEEE.
[3] Liao, C. T., Lee, W. H., & Lai, S. H. (2012). A flexible PCB inspection system based on statistical learning. Journal of Signal Processing Systems, 67(3), 279-290.
[4] Iwahori, Y., Kumar, D., Nakagawa, T., & Bhuyan, M. K. (2012). Improved defect classification of printed circuit board using SVM. In Intelligent Decision Technologies. Springer Berlin Heidelberg, 355-363.
[5] Iwahori, Y., Futamura, K., & Adachi, Y. (2011). Discrimination of true defect and indefinite defect with visual inspection using SVM. Knowledge-Based and Intelligent Information and Engineering Systems, 117-125.
[6] Moganti, M., Ercal, F., Dagli, C. H., & Tsunekawa, S. (1996). Automatic PCB inspection algorithms: a survey. Computer vision and image understanding,63(2), 287-313.
[7] Singh, A., Nayak, V. H., & Vayada, M. G. (2014). Automatic Detection of PCB Defects. International Journal for Innovative Research in Science and Technology, 1(6), 285-289.
[8] Ibrahim, I., Bakar, S., Mokji, M., Mukred, J., Yusof, Z. M., Ibrahim, Z. & Mohamad, M. S. (2012). A printed circuit board inspection system with defect classification capability. International Journal of Innovative Management, Information & Production ISME International, 3(1), 82-87.
[9] Doudkin, A., & Inyutin, A. (2014). The Defect and Project Rules Inspection on PCB Layout Image. International Journal of Computing, 5(3), 107-111.
[10] Mar, N. S. S., Yarlagadda, P. K. D. V., & Fookes, C. (2011). Design and development of automatic visual inspection system for PCB manufacturing. Robotics and Computer-Integrated Manufacturing, 27(5), 949-962.
[11] Acciani, G., Brunetti, G., & Fornarelli, G. (2006). Application of neural networks in optical inspection and classification of solder joints in surface mount technology. IEEE Transactions on industrial informatics, 2(3), 200-209.
[12] Belbachir, A. N., Lera, M., Fanni, A., & Montisci, A. (2005). An automatic optical inspection system for the diagnosis of printed circuits based on neural networks. In Industry Applications Conference, 2005. Fourtieth IAS Annual Meeting. Conference Record of the 2005 (Vol. 1, pp. 680-684). IEEE.
[13] Ishola, B. I., Povinelli, R. J., Corliss, G. F., & Brown, R. H. (2016). Identifying extreme cold events using phase space reconstruction. International Journal of Applied Pattern Recognition, 3(3), 259-275.
[14] Koulaouzidis, G., Das, S., Cappiello, G., Mazomenos, E. B., Maharatna, K., Puddu, P. E., & Morgan, J. M. (2015). Prompt and accurate diagnosis of ventricular arrhythmias with a novel index based on phase space reconstruction of ECG. International journal of cardiology, 182, 38-43.
[15] Amann, A., Tratnig, R., & Unterkofler, K. (2007). Detecting ventricular fibrillation by time-delay methods. IEEE Transactions on Biomedical Engineering, 54(1), 174-177.
[16] Gaxiola, F., Melin, P., Valdez, F., & Castillo, O. (2014). Interval type-2 fuzzy weight adjustment for backpropagation neural networks with application in time series prediction. Information Sciences, 260, 1-14.
[17] Mironov, K. V., & Pongratz, M. U. (2013). Applying neural networks for prediction of flying objects trajectory. Вестник Уфимского государственного авиационного технического университета, 17(6).
[18] Goyal, S., & Goyal, G. K. (2012). Time-Delay artificial neural network computing models for predicting shelf life of processed cheese. BRAIN. Broad Research in Artificial Intelligence and Neuroscience, 3(1), 63-70.
[19] Van den Oord, A., Dieleman, S., & Schrauwen, B. (2013). Deep content-based music recommendation. In Advances in neural information processing systems, 2643-2651.
[20] Collobert, R., & Weston, J. (2008). A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of the 25th international conference on Machine learning, 160-167. ACM.
[21] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 1097-1105.
[22] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1-9.
[23] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778.
[24] Graves, A., Mohamed, A. R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (icassp), 2013 ieee international conference on. IEEE, 6645-6649.
[25] Singh, A., Nayak, V. H., & Vayada, M. G. (2014). Automatic detection of pcb defects. International Journal for Innovative Research in Science Technology (IJIRST), 1(6).
[26] Hansen, L. K., & Salamon, P. (1990). Neural network ensembles. IEEE transactions on pattern analysis and machine intelligence, 12(10), 993-1001.
[27] Opitz, D., & Maclin, R. (1999). Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169-198.
[28] Rokach, L. (2010). Ensemble-based classifiers. Artificial Intelligence Review, 33(1), 1-39.
[29] Kuncheva, L. I., & Whitaker, C. J. (2003). Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Machine learning, 51(2), 181-207.
[30] Sollich, P., & Krogh, A. (1996). Learning with ensembles: How overfitting can be useful. Advances in neural information processing systems, 190-196.