哈尔滨工程大学 自动化学院,哈尔滨 150001
College of Automation,Harbin Engineering University,Harbin 150001,China
为了准确地求解组合权重的组合系数,将基于分解的多目标进化算法(multi-objective evolutionary algorithm based on decomposition,MOEA/D)思想引入评估领域,提出一种基于MOEA/D的组合权重方法.通常,利用加权和法将组合权重模型转化为单目标模型时,模型加权系数难以准确确定.对此,引入MOEA/D算法的分解思想,将组合权重模型转化为多个单目标子模型.MOEA/D算法仅适用于无约束优化问题,而较为常用的惩罚函数法难以表达进化初期无可行解的情况,因而提出改进自适应惩罚函数(improved adaptive penalty function,IAPF),将组合权重模型转化为无约束优化模型.应用所提出方法与其他方法进行仿真实验,实验结果表明,所提出算法具有有效性.
In order to solve the combination coefficients of combination weight accurately, the idea of the multi-objective evolutionary algorithm based on decomposition(MOEA/D) is introduced into the evaluation field, and a combination weight method based on MOEA/D is proposed. When the combination weight model is usually transformed into a single objective model by using the weighted sum method, the model weighting coefficients are difficult to determine accurately. To solve this problem, by introducing the decomposition idea of the MOEA/D algorithm, the combined weight model is transformed into multiple single objective sub-models. The MOEA/D algorithm is only suitable for unconstrained optimization problems. However, the commonly used penalty function method is difficult to express the situation where there is no feasible solution in the initial stage of evolution. An improved adaptive penalty function(IAPF) is proposed to transform the combination weight model into an unconstrained optimization model. Simulations are carried out using the proposed method and other literature methods. The results show that the proposed algorithm is effective.