• DocumentCode
    578373
  • Title

    A simulation assisted neural -networks forecasting system on the optimization between WIP and throughput for TFT-LCD color filter fabs

  • Author

    Huang, Potsang B. ; Yu, Cheng-wei ; Chen, James C. ; Chih-Cheng Chen ; Peng, Tzu-wei ; Wei, Yu-yao ; Feng, Chao-hsuan

  • Author_Institution
    Dept. of Ind. & Syst. Eng., Chung-Yuan Christian Univ., Taoyuan, Taiwan
  • Volume
    3
  • fYear
    2012
  • fDate
    15-17 July 2012
  • Firstpage
    991
  • Lastpage
    995
  • Abstract
    There are trade-offs between cost and effect for WIP and throughput. Management may need to stimulate environments to find the existing trade-off points and determine the actions needed to minimize their effect on WIP and throughput. Thus, the ANNF system is integrated with Artificial Neural Network and AutoMod Software. The combination of the ANNF system and mathematical theory resulted in a new trade-off system. This system enables planners to conduct what-if analysis for the production control policies without disturbing operations in the real plant. Better alternatives leading to higher system throughput can be identified by using system simulation in the fab.
  • Keywords
    digital simulation; forecasting theory; liquid crystal displays; neural nets; production control; production engineering computing; thin film transistors; work in progress; AutoMod software; TFT-LCD color filter fabs; artificial neural network; mathematical theory; production control policy; simulation assisted neural-networks forecasting system; system simulation; what-if analysis; work in process; Abstracts; Electron tubes; Throughput; Training; CONWIP; Color Filter; Simulation Neural-network; Trade-off;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Machine Learning and Cybernetics (ICMLC), 2012 International Conference on
  • Conference_Location
    Xian
  • ISSN
    2160-133X
  • Print_ISBN
    978-1-4673-1484-8
  • Type

    conf

  • DOI
    10.1109/ICMLC.2012.6359489
  • Filename
    6359489