首页--工业技术论文--自动化技术、计算机技术论文--自动化基础理论论文--人工智能理论论文

粒子群优化算法及其在电磁设计中的应用

摘要第5-7页
Abstract第7-8页
1 Inverse Problem第12-23页
    1.1 Introduction第12-15页
    1.2 State of Art of Global Optimization第15-21页
        1.2.1 State of arts of vector optimizer第17-18页
        1.2.2 State of arts of robust optimization methodology第18-21页
    1.3 Work of Dissertation第21-23页
        1.3.1 Objective第21-22页
        1.3.2 Dissertation outline第22-23页
2 Particle Swarm Optimization第23-54页
    2.1 Introduction第23-25页
    2.2 Swarm Intelligence第25页
    2.3 Basic PSO Model第25-29页
        2.3.1 Global best PSO model第27-28页
        2.3.2 Local best PSO第28-29页
    2.4 Algorithm Parameters第29-31页
        2.4.1 Swarm size第29页
        2.4.2 Iteration numbers第29页
        2.4.3 Velocity components第29-30页
        2.4.4 Learning parameter第30-31页
    2.5 Geometrical Demonstration of Particle第31-33页
    2.6 Neighborhood Topologies第33-36页
        2.6.1 Star topology第34页
        2.6.2 Ring topology第34-35页
        2.6.3 Wheel topology第35-36页
    2.7 Previous Research Work第36-53页
        2.7.1 Improvement on exploration searches第36-44页
        2.7.2 Selection of basis parameters第44-48页
        2.7.3 Mutation Mechanism第48-50页
        2.7.4 Hybridization第50-53页
    2.8 Conclusion第53-54页
3 Improvements of PSOs第54-98页
    3.1 Introduction第54-55页
    3.2 First Improved PSO第55-58页
        3.2.1 Introduction of mutation operator第55-57页
        3.2.2 Dynamic inertia weight第57-58页
    3.3 Second Improved PSO第58-63页
        3.3.1 The proposed modified PSO第58-60页
        3.3.2 A new variation in inertia weight第60-61页
        3.3.3 A new strategy for learning parameters第61-62页
        3.3.4 Introduction of an improved parameter第62-63页
    3.4 Third Improved PSO第63-69页
        3.4.1 Introduction of global best particle第63-66页
        3.4.2 Dynamic control parameter第66-67页
        3.4.3 The learning factors updating第67-69页
    3.5 Case Study and Parameter Settings of the New Improved PSOs第69-71页
        3.5.1 First improved PSO parameter setting第69-70页
        3.5.2 Comparison of second and third improved PSOs with other PSO variants第70-71页
    3.6 Results and Statistical Analysis of First Improved PSO第71-77页
        3.6.1 Comparisons of the solution accuracy第71-74页
        3.6.2 Convergence comparison第74-77页
    3.7 Second Improved PSO Results and Discussion第77-88页
        3.7.1 Convergence comparison第81-88页
    3.8 Third Improved PSO Results and Statistical Analysis第88-97页
        3.8.1 Comparisons results of optimal algorithms第88-93页
        3.8.2 Convergence performances of different optimal algorithms第93-97页
    3.9 Conclusion第97-98页
4 Application第98-110页
    4.1 Introduction第98-99页
    4.2 Team benchmark Workshop Problem 22第99-101页
    4.3 Solution of the Direct Problem Using Finite Element Method第101-105页
        4.3.1 Introduction第101页
        4.3.2 The finite element method for two-dimensional magneto static field第101-102页
        4.3.3 Parallel plane field第102-104页
        4.3.4 Axisymmetric field第104-105页
    4.4 Finite Element Equation Solution and Post-processing Technology第105-107页
        4.4.1 The solution of finite element equation第105-106页
        4.4.2 Post-processing methods第106-107页
    4.5 Results and Discussion第107-110页
        4.5.1 Comparisons results of first improved PSO第107-108页
        4.5.2 Second and third improved PSOs' results第108-110页
5 Conclusion第110-112页
Acknowledgments第112-113页
Publications第113-114页
References第114-130页

论文共130页,点击 下载论文
上一篇:基于定子磁链控制的IPMSM驱动系统研究
下一篇:个性化驾驶员模型及其在驾驶行为评估中的应用