Using an intelligent algorithm for performance improvement of two-sided assembly line balancing problem considering learning effect and allocation of multi-skilled operators

Two-sided assembly lines have been extensively studied due to their application in various auto industries. this paper investigates balancing problem type-ii, which serves to minimize cycle time and consider learning effect based on a predefined workstation and costs pertaining to the assignment of operators with various skills. to this end, an integrated approach based on discrete event simulation (des), artificial neural network (ann), and data envelopment analysis (dea) is utilized to optimize the performance of two-sided assembly line balancing (2s-alb) problem type-ii. the developed approach is applied to a real case study. since many scenarios (suggestions for production line improvement) are needed for the simulation, the 2^k factorial design of experiment (doe) is used to reduce their number. ann and dea were then used to select the best scenarios. it has been shown that incorporating learning effect and multi-skilled operators can improve the performance of 2s-alb problem type-ii better than does the conventional approach.