Title page for 954206001


[Back to Results | New Search]

Student Number 954206001
Author Cheng-Lin Yang(FM)
Author's Email Address No Public.
Statistics This thesis had been viewed 1359 times. Download 0 times.
Department Graduate Institute of Industrial Management
Year 2007
Semester 2
Degree Master
Type of Document Master's Thesis
Language English
Title Optimum Design for BPNN with Taguchi Method to Study on Defects Classification in TFT-LCD Cell Process
Date of Defense 2008-06-30
Page Count 62
Keyword
  • BPNN
  • Defect classification
  • Orthogonal array
  • Taguchi method
  • Abstract TFT-LCDs have become one of the most popular flat panel display devices in these days and applied to various fields in the world. However, manufacturing the TFT-LCD panel indeed requires passing through many complex processes. It would be a tough task to analyze the causes of defects when the defects occur. As a result, manufactures need an efficient method to help employees quickly clear the causes of defects and then do the appropriate treatments to avoid resulting in a mass profit loss.
     In this study, we use BPNN to approach the relationship between defective characteristics and causes of defects so as to solve the defects classification problem in the TFT-LCD cell process. In order to make BPNN perform well, we adopt Taguchi method to study not only the significant parameters but the optimum parameter settings in BPNN.
     Numerical analysis results show the main and interaction effects of parameters- transfer function, learning rate, and epoch size have significant effects on the performance of BPNN in our case. Besides, the corresponding optimal levels of each significant parameter can be determined by two-way, one-way table, or Duncans Multiple Range Test. At last, we extract the final weights and biases from trained BPNN at the optimal condition and then provide this network model with the optimum designs for manufacturers to apply to defects classification problem in TFT-LCD cell process.
    Table of Content Kni
    Abstractii
    xiii
    Table of Contentiv
    List of Figuresvi
    List of Tablesvii
    Chapter 1 Introduction1
    1.1 Research motivation and background1
    1.2 Problem description4
    1.3 Research objectives5
    1.4 Research methodology and framework6
    1.4.1 Research methodology6
    1.4.2 Research framework7
    Chapter 2 Literature review9
    2.1 Defect classification9
    2.2 Back-propagation neural network11
    2.3 Taguchi Method15
    Chapter 3 Research methodology19
    3.1 Data processing19
    3.2 Parameters selection20
    3.3 Taguchi experiment23
    3.3.1 Identification of performance characteristic and design variables24
    3.3.2 Determination of the levels and an orthogonal array25
    3.3.3 Experimentation26
    3.3.4 Experiment analysis31
    3.3.5 Confirmation34
    Chapter 4 Numerical analysis36
    4.1 Data setting36
    4.2 Taguchi experiment42
    4.2.1 Experiment setting43
    4.2.2 Experimentation47
    4.2.3 Results and analysis48
    4.3 Results discussion55
    Chapter 5 Conclusion and future work57
    5.1 Conclusion57
    5.2 Future work58
    Reference59
    Reference [1]Bishop, C.M. (1995), Neural networks for pattern recognition. Clarendon Press, Oxford, UK.
    [2]Bounds, D.G., Lloyd, P,J. (1988), A multilayer perceptron network for the diagnosis of low back pain. Proc. Second IEEE Int'l. Conf. Neural Networks, San Diego, July 24-27, II-481-II-489.
    [3]Castillo, P.A., Merelo, J.J., Prieto, A., Rivas, V., Romero, G. (2000), Evolving multilayer perceptrons. Neural Processing Letters 12, 115-127.
    [4]Castillo, P.A., Merelo, J.J., Prieto, A., Rivas, V., Romero, G. (2000), G-Prop: Global optimization of multilayer perceptrons using GAs. Neurocomputing 35, 149-163.
    [5]Chu, C.Y., The research of defect solutions for TFT-LCD G4.5 cell process in BPN application, National Central University, Executive Master of Industrial Management, 2007.
    [6]Cybenko,G. (1989), Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems 2(4), 303-314.
    [7]Dayhoff, Judith E. (1990) Neural network architectures: an introduction. Van Nostrand Reinhold, New York.
    [8]Feng, C.X.J., Gowrisankar, A.C., Smith, A.E., Yu, Z.G.S. (2006), Practical guidelines for developing BP neural network models of measurement uncertainty data. Journal of Manufacturing System 25(4), 239-250.
    [9]Ham, J., Kamber, M. (2003) Data mining: concepts and techniques. Morgan Kaufmann, San Francisco, California.
    [10]Hart, A. (1992), Using neural networks for classification tasks-some experiments on datasets and practical advice. Journal of the Operational Research Society 43(3), 215-226.
    [11]Haykin, S. (1994), Neural networks: A Comprehensive foundation. Prentice-Hall International, Englewood Cliffs, NJ. 
    [12]Hsieh, K.L., Lu, Y.S. (2008), Model construction and parameter effect for TFT-LCD process based on yield by using ANNs and stepwise regression. Expert Systems with Application 34, 717-724.
    [13]Khaw, J.F.C, Lim, B.S., Lim, L.E.N. (1995), Optimal design of neural network using the Taguchi method. Neurocomputing 7, 225-245.
    [14]Kim, Y.S., Yum, B.J. (2004), Robust design of multilayer feedforward neural networks: an experimental approach. Engineering Applications of Artificial Intelligence 17, 249-263.
    [15]Lee, K.H, Yi, J.W., Park, J.S., Park, G.J. (2003), An optimization algorithm using orthogonal arrays in discrete design space for structures. Finite Elements in Analysis and Design 40, 121-135.
    [16]Leonard, J.A., Kramer, M.A. (1991), Radial basis function networks for classifying process faults. Control Systems Magazine 11(3), 31-38.
    [17]Lim, D.C., Seo, D.G., Jeong, D.H. (2005), Defect Classification for Inspection of TFT-LCD Glass. Proceedings of SPIE 6051, 60510F-1-60510F-6.
    [18]Lin, S.W., Chou, S.Y., Chen, S.C. (2007), Irregular shapes classification by back-propagation neural networks. International Journal of Advance Manufacturing Technology 34, 1164-1172.
    [19]Lin, S.W., Tseng, T.Y., Chou, S.Y., Chen, S.C. (2008), A simulated-annealing-based approach for simultaneous parameter optimization and feature selection of back-propagation networks. Expert Systems with Application 34, 1491-1499.
    [20]Lin, T.Y., Tseng, C.H. (2000), Optimum design for artificial neural networks: an example in a bicycle derailleur system. Engineering Application of Artificial Intelligence 13, 3-14.
    [21]Maier, H.R., Dandy, G.C. (1998), The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study. Environmental Modelling & Software 13, 193-209.
    [22]Maren, A., Harston, C., Pap, R. (1990), Handbook of Neural Computing Applications, Academic Press, San Diego, CA.
    [23]Montgomery, D.C. (1997), Design and Analysis of Experiments, 5th Edition, Wiley, New York.
    [24]NeuralWare Inc. (1991). Neural Computing, NeuralWorks Professional II/Plus and NeuralWorks Explorer.
    [25]Packianather, M.S., Drake, P.R., Rowlands, H. (2000), Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experiments. Quality and Reliability international 16, 461-473.
    [26]Park, S.H. (1996), Robust Design and Analysis for Quality Engineering, Chapman & Hall, London. 
    [27]Peace, G.S. (1993), Taguchi Method: A Hands-on Approach, Addison-Wesley, Reading, MA.
    [28]Pham, D.T., Sagiroglu, S. (2000). Neural network classification defects in veneer boards. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture 214(3), 255-258.
    [29]Sexton, R. S., Alidance, B., Dorsey, R. E. (1998). Global optimization for artificial neural network: a Tabu search application. European Journal of Operational Research 106, 570-584.
    [30]Sukthomya, W., Tannock, J. (2005), The optimization of neural network parameters using Taguchi's design of experiments approach: an application in manufacturing process modeling. Neural Computing and Application 14, 337-344.
    [31]Taguchi, G. (1987), System of Experimental Design, Vol. 1& 2. UNIPUB/Kraus International Publications, New York.
    [32]Tortum, A., Yayla, N., Celik, C., Gokdag, M. (2007), The investigation of model selection criteria in artificial neural networks by Taguchi method. Physica A 386, 446-468.
    [33]Wang, T.Y., Huang, C.Y. (2008), Optimizing back-propagation networks via a calibrated heuristic algorithm with an orthogonal array. Expert Systems with Application 34, 1630-1641.
    [34]Yang, T., Lin, H.C., Chen, M.L. (2006), Metamodeling approach in solving the machine parameters optimization problem using neural network and genetic algorithms: A case study. Robotics and Computer-Integrated Manufacturing 22, 322-331.
    [35]Yang, T., Olmen, R.V. (2004), Robust design for a multilayer ceramic capacitor screen-printing process case study. Journal of Engineering Design 15(5), 447-457.
    [36]Yuen, C.W.M., Wong, W.K., Qian, S.Q., Chan, L.K., Fung, E.H.K. (2008), A hybrid model using genetic algorithm and neural network for classifying garment defects. Expert Systems with Applications.
    Advisor
  • Gwo-Ji Sheen(H)
  • Files
  • 954206001.pdf
  • disapprove authorization
    Date of Submission 2008-07-14

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have dissertation-related questions, please contact with the NCU library extension service section.
    Our service phone is (03)422-7151 Ext. 57407,E-mail is also welcomed.