An Improvement Based Evolutionary Algorithm with Adaptive Weight Adjustment for Many-Objective Optimization

For many-objective optimization problems (MaOPs), how to get a set of solutions with good convergence and diversity is a difficult and challenging work. In this paper, a new decomposition-based evolutionary algorithm with adaptive weight adjustment is designed to obtain this goal. Firstly, a new method based on uniform design and crowding distance is designed to generate a set of weight vectors with good uniformly. Secondly, an adaptive weight adjustment is used to solve some MaOPs with complex Pareto optimal front (PF) (i.e. PF with a sharp peak of low tail or discontinuous PF). Thirdly, a selection strategy is used to help each sub-objective space to obtain a non-dominated solution (if have). Comparing with some efficient state-of-the-art algorithms, e.g., MOEA/D and HypE on some benchmark functions, the proposed algorithm is able to find a set of solutions with better diversity and convergence.