• DocumentCode
    1561536
  • Title

    CMAC neural networks based combining control for marine diesel engine generator

  • Author

    Weifeng Shi ; Tang, Tianhao

  • Author_Institution
    Dept. of Electr. Autom., Shanghai Maritime Univ., China
  • Volume
    3
  • fYear
    2004
  • Firstpage
    2651
  • Abstract
    In neural networks control system, CMAC neural networks control is provided with characteristic of learning online and rapidly. Combine with CMAC neural networks and PID controlling, a combining control was built for marine diesel engine generator system. The CMAC neural networks control was not simply copy from PID control in the generator combining control system. Through learning of CMAC neural networks continuously, the CMAC neural networks control become main effect control. In a power system control simulation of a marine electric propulsion vessel, this control method was used. Under the simulating test of adding 50% or 16% active load of generator rating value suddenly and simulating test of three phase grounding fault, the control dynamic characteristic was satisfactory with CMAC neural networks combine control of marine diesel engine generator system.
  • Keywords
    adaptive control; cerebellar model arithmetic computers; diesel engines; diesel-electric generators; earthing; electric propulsion; electrical faults; learning systems; marine systems; neurocontrollers; power system control; three-term control; CMAC neural networks; PID control; active load; combining control system; control dynamic characteristic; generator rating value; marine diesel engine generator; marine electric propulsion vessel; neural networks control system; online learning control; power system control simulation; three phase grounding fault; Character generation; Control systems; Diesel engines; Grounding; Neural networks; Power system control; Power system simulation; Propulsion; System testing; Three-term control;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
  • Print_ISBN
    0-7803-8273-0
  • Type

    conf

  • DOI
    10.1109/WCICA.2004.1342078
  • Filename
    1342078