• DocumentCode
    3352190
  • Title

    Fault diagnosis of oil pump based on high speed and precise genetic algorithm neural network

  • Author

    Gao, Meijuan ; Tian, Jingwen ; Cao, Liting ; Xu, Jin

  • Author_Institution
    Dept. of Autom. Control, Beijing Union Univ., Beijing
  • fYear
    2008
  • fDate
    21-24 Sept. 2008
  • Firstpage
    965
  • Lastpage
    970
  • Abstract
    Considering the issues that the relationship between the fault of oil pump existent and fault information is a complicated and nonlinear system, and it is very difficult to found the process model to describe it. According to the physical circumstances of oil pump, a fault diagnosis method of oil pump based on high speed and precise genetic algorithm neural network is presented in this paper. The high speed and precise genetic algorithm neural network is combined the adaptive and floating-point code genetic algorithm with BP which has higher accuracy and faster convergence speed. With the ability of strong self-learning and function approach and fast convergence rate of high speed and precise genetic algorithm neural network, the diagnosis method can truly diagnose the fault of oil pump by learning the fault information of oil pump. The real diagnosis results show that this method is feasible and effective.
  • Keywords
    fault diagnosis; genetic algorithms; mechanical engineering computing; neural nets; oils; pumps; fault diagnosis; floating-point code genetic algorithm; function approach; genetic algorithm; neural network; nonlinear system; oil pump; self-learning approach; Chemical technology; Convergence; Costs; Fault diagnosis; Genetic algorithms; Information science; Neural networks; Petroleum; Production; Pumps; fault diagnosis; genetic algorithms; neural network; oil pump;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cybernetics and Intelligent Systems, 2008 IEEE Conference on
  • Conference_Location
    Chengdu
  • Print_ISBN
    978-1-4244-1673-8
  • Electronic_ISBN
    978-1-4244-1674-5
  • Type

    conf

  • DOI
    10.1109/ICCIS.2008.4670935
  • Filename
    4670935