Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/1961
標題: 粒子群演算法之改善及探討
Exploration of improvement of particle swarm optimization
作者: 紀梓民
Ji, Zih-Ming
關鍵字: optimization;最佳化設計;partcle swarm optimization;粒子群演算法
出版社: 機械工程學系所
引用: [1] J. Kennedy and R. C. Eberhart, “Particle swarm optimization,” Proc. IEEE Int. Conf. Neural Networks, pp. 1942-1948, 1995. [2] M. M. Millonas,“Swarm,phasetransitions,and collective intelligence,” C. G .Langton, Ed., Artificial Life III. Addison Wesley, Reading, MA. 1994. [3] V. Gerhard and S. S. Jaroslaw, “Particle swarm optimization,” Source: Collection of Technical Papers-AIAA/ASME/ASCE/AHS/ASC Structures ,Structural Dynamics and Materials Conference, Vol. 1, pp.282-290, 2002. [4] R. C. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory,” Proceedings of the Sixth International Symposium on Micromachine and Human Science, Nagoya, Japan, pp. 39-43, 1995. [5] R. C. Eberhart and Y. Shi, “Particle swarm optimization: development, applications and resources,” Evolutionary Computation, 2001. Proceedings of the 2001 Conqress on Vol. 1, pp. 81-86, 2001. [6] R. C. Eberhart and Y. Shi, “A modified particle swarm optimizer,” Evolutionary Computation Proceedings, 1998. IEEE World Conqress on Computational Itelligence. The 1998 IEEE International Conference on, pp. 69-73, May, 4-9, 1998. [7] L. Wang, Q. Kang, H. Xiao, and Q. Wu, “A Modified adaptive particle swarm optimization algorithm,”Proceedings of the IEEE International Conference on Industrial Technology, vol. 2005, 2005 IEEE International Conference on industrial Technology, ICIT 2005, pp. 209-214, 2005. [8] F. van den Bergh and A. P. Engelbrecht, “A study of particle swarm optimization particle trajectories,” Information Sciences, Vol. 176, No. 8, pp. 937-971, April, 22, 2006. [9] P. C. Fourie and A. A. Groenwold, “The particle swarm optimization algorithm in size and shape optimization,” Source: Structural and Multidisciplinary Optimization, Vol. 23, No. 4, pp. 259-267, May, 2002. [10] Z. Qingfu, J. Sun, E. Tsang and J. Ford, “Hybrid estimation of distribution algorithm for global optimization,” Source: Engineering Computations (Swansea, Wales), Vol. 21, No. 1, pp. 91-107, 2004. [11] C. A. C. Coello, G. T. Pulido and M. S. Lechuga, “Handling multiple objectives with particle swarm optimization,” Source: IEEE Transactions on Evolutionary Computation, Vol. 8, No. 3, pp. 256-279, June, 2004 [12] S. L. Ho, S. Yang, G. Ni and H. C. Wong, “A particle swarm optimization method with enhanced global search ability for design optimizations of electromagnetic devices,” Source: IEEE Transactions on Magnetics, Vol. 42, No. 4, pp. 1107-1110, April, 2006. [13] J. J. Liang, A. K. Qin, P. N. Suganthan and S. Baskar, “Comprehensive learning particle swarm optimizer for global optimization of multimodal functions,” Source: IEEE Transactions on Evolutionary Computation, Vol. 10, No. 3, pp. 281-295, June, 2006. [14] A. Stacey, M. Jancic, I. Grundy; “Particle swarm optimization with mutation,” Evolutionary Computation, 2003. CEC ''03. The 2003 Congress on Vol. 2, pp. 1425 – 1430, December, 8-12, 2003. [15] H. J. Meng, Z. Peng, R. Y. Wu, X. J. Hao and Z. Xie, “A hybrid particle swarm algorithm with embedded chaotic search,” Source: 2004 IEEE Conference on Cybernetics and Intelligent Systems, 2004 IEEE Conference on Cybernetics and Intelligent Systems, pp. 367-371, 2004. [16] 陳信昌, “可處理離散和混合變數之演化策略法,” 國立中興大學機械工程研究所碩士論文, 附錄A, 民國95年1月 [17] J. J. Liang, A. K. Qin, P. N. Suganthan and S. Baskar, “Evaluation of comprehensive learning particle swarm optimizer,” Springer’s Lecture Notes in Computer Science, ICONIP’04, Vol. 3316, pp. 230-235, 2004. [18] K. T. Fang, Y. Wang and P. M. Bentler, “Some applications of number-theoretic methods in statistics,” Statistical Science, Vol. 9, No. 3, pp. 416-428, August, 1994.
摘要: 
粒子群演算法對各類問題,皆能表現出一定的求解能力,而且它的觀念簡單易用且程式撰寫容易,為多個粒子同時搜尋,所以有較大的機會找到全域最佳解。雖然粒子群演算法具備了上述幾項優點,但是,由於每代皆需計算各粒子的適應值,計算次數繁多,而且對於參數的設定非常地敏感。有鑑於此,本文針對粒子群演化法之流程參考相關文獻並稍作改變,使得粒子群演算法在結果的收斂上更具優勢,本文的主要改進的方法包括:應用均勻設計的概念使得初始的粒子可以更均勻地分佈在空間上;利用突變增加粒子之間的差異性與多樣性;利用適當控制的最大速度限制及慣性權重控制,達到區域搜尋與全域搜尋的效果;應用新的邊界處理機制處理設計變數超過上、下限的問題;利用區域強化搜尋針對粒子附近地區,再作進一步的搜索以得到更佳之結果;將各種方法綜合後配合粒子群演算法使用,可以得到不錯的結果。

另外,由於一般的粒子群演算法,處理最佳化設計問題時,作完一次完整的搜尋,只能得到一個解,所以本文發展並討論多極值搜尋機制,使得粒子群演算法處理多極值問題也可以從一次求解中得到多個解,以彌補一般粒子群演法在此方面的不足。

The particle swarm optimization (PSO) method has good performance and is easy to be programmed. Since it uses multiple particle to search the optimum solution, it has the better chance to find the global solution. Althogh it has those advantages mentioned, it consumes a lot of computation time to compute the fitnesses of particles and some parameters in PSOmay affect the solution significantly. According to this understanding, this thesis tries to modify PSO algorithm in order to improve its quality of solutions. The main approches include: using uniform design to ensure the uniform distribution of initial particles in the design space; adding mutation operation to increase the diversity of particles; decreasing the maximum velocity limitation and the velocity inertia automatically to balance the local and the global search efforts; developing a new approach to treat the design variables exceeding the bounds; using extensive local searches to escape local minimum. The overall effect of these approaches can yield better results for most test problems.

For original PSO, itcan only find a solution in a single run. For multi-modal problems, many runs are needed find different solutions. To overcome this drawback, this thesis also developes a method incorporated with original PSO to find many solutions in a single run for muti-modal problems.
URI: http://hdl.handle.net/11455/1961
其他識別: U0005-3101200813400500
Appears in Collections:機械工程學系所

Show full item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.