首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0904115-115802


URN etd-0904115-115802 Statistics This thesis had been viewed 374 times. Download 0 times.
Author Wei-Lun Huang
Author's Email Address No Public.
Department Electrical Engineering
Year 2014 Semester 2
Degree Master Type of Document Master's Thesis
Language zh-TW.Big5 Chinese Page Count 59
Title DIFFERENTIAL EVOLUTION WITH ADAPTIVE WINNER MUTATION STRATEGY FOR PID CONTROLLER OPTIMIZATION
Keyword
  • current-to-winner
  • benchmark function
  • parameter adaption
  • control parameter
  • control parameter
  • parameter adaption
  • benchmark function
  • current-to-winner
  • Abstract This thesis base on winner mutation strategy, proposed current-to-winner mutation strategy. Traditional mutation strategies have the most suitable control parameters-mutation factor and crossover rate, but during the search need lots of experience to adjust the control parameters to the most suitable value. Therefore, this thesis join parameter adaption to make the algorithm can not only renew the control parameters automatically but also avoid lots of experience on adjusting control parameters. The proposed mutation strategy for different benchmark functions, joining the parameter adaptation adjustment method so that can improve algorithm’s performance. Simulation results show that the mutation strategy has good searching ability, also can achieve good control performance.
    Advisor Committee
  • Hung-Ching Lu - advisor
  • Files indicate in-campus access at 5 years and off-campus access at 5 years
    Date of Defense 2015-07-22 Date of Submission 2015-09-04


    Browse | Search All Available ETDs