首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0502114-142607


URN etd-0502114-142607 Statistics This thesis had been viewed 1007 times. Download 3 times.
Author Chien-Chih Chen
Author's Email Address gdfriend@tp.edu.tw
Department Computer Science and Enginerring
Year 2013 Semester 2
Degree Ph.D. Type of Document Doctoral Dissertation
Language English Page Count 65
Title Automatic Clustering for Cell Formation Using Hybrid Evolutionary Algorithms
Keyword
  • Cell formation problems
  • Particle swarm optimization
  • Differential evolution
  • Fuzzy clustering
  • Automatic clustering
  • Automatic clustering
  • Fuzzy clustering
  • Differential evolution
  • Particle swarm optimization
  • Cell formation problems
  • Abstract To design an efficient cellular manufacturing system, the first fundamental task is to form machine cells and part families, called cell formation (CF). CF problems can be classified into two categories: standard CF and generalized CF (GCF). In standard CF each part has a single process routing, while in GCF each part has more than one process routing. One of the drawbacks of existing CF approaches is that the number of part families or machine cells has to be specified in advance. In practice, it is difficult for the machine cell designer to determine the optimal number of machine cells before the overall machine cell configuration is formed and the operational result is observed. In this dissertation, the author developed two hybrid evolutionary algorithms which can perform automatic clustering to solve standard CF and GCF problems, respectively. Experimental results indicate that effective hybrid optimization algorithms can achieve fast convergence and find global optimum more easily than an individual optimization algorithm.
    To solve standard CF problems, an automatic fuzzy clustering approach is proposed, in which a differential evolution (DE) algorithm is combined with the Fuzzy c-means (FCM) method. This CF algorithm can automatically determine the best number of machine cells and generate an optimal machine cell configuration at the same time. Experimental results demonstrate that the proposed algorithm performs well in searching solutions to the fuzzy machine CF problem with automatic cluster number determination. To solve GCF problems, the second automatic clustering approach can concurrently evolve the number and cluster centers of machine cells by using two particle swarm optimization (PSO) algorithms. In this approach, a solution representation, comprising an integer number and a set of real numbers, is adopted to encode the number of cells and machine cluster centers, respectively. Besides, a discrete PSO algorithm is utilized to search for the number of machine cells, and a continuous PSO algorithm is employed to perform machine clustering. Effectiveness of the proposed approach has been demonstrated for test problems selected from the literature and those generated in this study. The experimental results indicate that the proposed approach is capable of solving the generalized machine CF problem without predetermination of the number of cells.
    Advisor Committee
  • Yucheng Kao - advisor
  • none - co-chair
  • none - co-chair
  • none - co-chair
  • none - co-chair
  • none - co-chair
  • Files indicate in-campus access at 1 years and off-campus access at 3 years
    Date of Defense 2014-04-18 Date of Submission 2014-05-02


    Browse | Search All Available ETDs