Iterative Beam Search for Simple Assembly Line Balancing with a Fixed Number of Work Stations

Abstract

The simple assembly line balancing problem (SALBP) concerns the assignment of tasks with pre-defined processing times to work stations that are arranged in a line. Hereby, precedence constraints between the tasks must be respected. The optimization goal of the SALBP-2 version of the problem concerns the minimization of the so-called cycle time, that is, the time in which the tasks of each work station must be completed. In this work we propose to tackle this problem with an iterative search method based on beam search. The proposed algorithm is able to obtain optimal, respectively best-known, solutions in 283 out of 302 test cases. Moreover, for 9 further test cases the algorithm is able to produce new best-known solutions. These numbers indicate that the proposed iterative beam search algorithm is currently a state-of-the-art method for the SALBP-2.