Artificial Physics Optimization Algorithm with a Feasibility-based Rule for Constrained Optimization Problems

摘要：

Artificial Physics Optimization (APO) Algorithm is a novel population-based stochastic algorithm for solving the unconstrained global problems. This paper first presents a simple mechanism to handle constrained optimization problems with APO. A feasibility-based rule is employed, because this rule can guide the swarm quickly to the feasible region and need not additional penalty parameters. The mass formula is constructed based on this rule, the feasible and infeasible individuals mass are calculated with different mass formulas. The force direction of the individual is determined based on the feasibility-based rule. The simulation results and comparisons with other methods in the literature show the feasibility, effectiveness, and efficiency of the proposed APO algorithm.

关键词： Artificial Physics Optimization constrained optimization feasibility rule mass force

作者: Jian Yin Liping Xie Jianchao Zeng Ying Tan

作者单位: Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technolog Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technolog Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technolog Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technolog

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 488-492

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）