An improved multi-objective antlion optimization algorithm for assembly line balancing problem considering learning cost and workstation area

In order to adapt to the continuously changing product demands, enterprises often need to rearrange the equipment of assembly lines to produce different products, which increases the cost the production. To solve the challenge, we propose a multi-objective assembly line balancing model considering the learning costs caused by reallocation. The objectives are to minimize the cycle time, the smoothness index of the workstation area, and the learning cost. An improved multi-objective antlion optimization (IMOALO) algorithm is proposed to solve this model. A decoding method based on the Newton dichotomy is introduced to ensure that each individual satisfies the three constraints. Pareto optimization is employed to optimize the three objectives simultaneously. The proposed algorithm is compared with two state-of-the-art algorithms in terms of four metrics. Furthermore, the quality of the solution of the proposed model is compared with that of the algorithms without considering the learning cost and workstation area. Extensive results demonstrate its superiority in optimality.