Affiliations: [a] School of Mathematics Science, Tianjin Normal University, Tianjin, P. R. China | [b] State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, P. R. China
Correspondence:
[*]
Corresponding author. Huan Lian, School of MathematicsScience, Tianjin Normal University, Tianjin, 300387, P. R. China. Tel.: +86 138 213 95620; E-mail: lianhuan369@163.com.
Note: [1] This work is supported by the National Natural Science Foundation (11371002) and Specialized Research Fund for the Doctoral Program of Higher Education (20131101110048).
Abstract: This paper proposes a new fuzzy particle swarm optimization (NFPSO), which is based on a new defined population position and velocity diversity measure. The proposed NFPSO utilizes population diversity information to adjust the inertia weight and membership function of fuzzy variable charisma adaptively, aiming to improve the performance of fuzzy PSO algorithms for numerical optimization problems. Experiments compared the proposed NFPSO with standard PSO, fuzzy PSO, ARPSO, DE and ABC algorithms were conducted on a collection of 25 numerical benchmark problems provided by the IEEE Congress on Evolutionary Computation 2005 special session on real parameter optimization. The results and its statistical analysis show that the proposed NFPSO algorithm performed well when applied in the multi-modal numerical problems.
