An orthogonal design based constrained evolutionary optimization algorithm

作者：Wang Yong^*; Liu Hui; Cai Zixing; Zhou Yuren

来源：Engineering Optimization, 2007, 39(6): 715-736.

DOI：10.1080/03052150701280541

• constrained optimization
• orthogonal design
• multi-objective optimization
• non-dominated individuals

Solving constrained optimization problems (COPS) via evolutionary algorithms (EAs) has attracted much attention. In this article, an orthogonal design based constrained optimization evolutionary algorithm (ODCOEA) to tackle COPS is proposed. In principle, ODCOEA belongs to a class of steady state evolutionary algorithms. In the evolutionary process, several individuals are chosen from the population as parents and orthogonal design is applied to pairs of parents to produce a set of representative offspring. Then, after combining the offspring generated by different pairs of parents, non-dominated individuals are chosen. Subsequently, from the parent's perspective, it is decided whether a nondominated individual replaces a selected parent. Finally, ODCOEA incorporates an improved BGA mutation operator to facilitate the diversity of the population. The proposed ODCOEA is effectively applied to 12 benchmark test functions. The computational experiments show that ODCOEA not only quickly converges to optimal or near-optimal solutions, but also displays a very high performance compared with another two state-of-the-art techniques.

• 出版日期2007-9
• 单位中南大学; 华南理工大学