• DocumentCode
    693158
  • Title

    Research of process parameters of molecular distillation on product purity based on rough sets neural network

  • Author

    Ke-Ping Liu ; Jian-Peng Zeng ; Quan Tao ; Chang-Hong Jiang

  • Author_Institution
    Coll. of Electr. & Electron. Eng., Changchun Univ. of Technol., Changchun, China
  • Volume
    01
  • fYear
    2013
  • fDate
    14-17 July 2013
  • Firstpage
    320
  • Lastpage
    326
  • Abstract
    Molecular distillation is a complex nonlinear chemical production process of which its mechanism is complex and contains several tight coupling variables, therefore it is difficult to establish precise mathematical model. Based on on product yield factors of the molecular distillation, this paper proposes a product purity prediction model based on rough sets and neural network theory, also the realization process is given. And the specific effects on manufacturing process from molecular distillation parameters are analyzed by simulation, the simulation result proves that the product purity prediction model based on rough sets and neural network theory accelerates the learning speed and improves prediction accuracy.
  • Keywords
    chemical engineering computing; chemical industry; distillation; neural nets; product development; production engineering computing; rough set theory; complex nonlinear chemical production process; molecular distillation; neural network theory; product purity prediction model; product yield factor; rough sets; DH-HEMTs; Erbium; Lenses; BP neural network; Molecular distillation; Prediction model; Rough sets;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Machine Learning and Cybernetics (ICMLC), 2013 International Conference on
  • Conference_Location
    Tianjin
  • Type

    conf

  • DOI
    10.1109/ICMLC.2013.6890488
  • Filename
    6890488