An artificial immune system approach for solving type-e assembly line balancing problem with problem-specific information

Abstract

The advent of industrial 4.0 ushered a new era in the manufacturing industry where merely optimizing the available resources is not enough to fulfill the need of the growing market. Various approaches have addressed the assembly line balancing (ALB) problem for decades. Although solving the ALB problem is crucial, a bottleneck may still occur over the next operation stages. As such, two research directions are necessary. On top of proposing an efficient search mechanism, optimum information utilization is also needed where the expected outcome would benefit both ways. Also, the utilization of problem-specific information (bottleneck identification) is expected to improve the ALB problem's solution quality. This paper provides a proof-of-concept for such claims by proposing two artificial immune systems (AIS) approaches, namely as the contagious immune network (COMET) approach, catered for the ALB problem where problem-specific information was incorporated. The proposed AIS approaches were tested on 24 ALB benchmark data sets to determine its effectiveness and highlight the impact of incorporating bottleneck identification. Also, a comparative analysis of the proposed approaches against the approaches from the literature was statistically justified.

Interactive demo

A looping preview of the line-balancing model: an artificial immune system assigns precedence-constrained tasks to workstations under a cycle-time limit, rebalancing to raise line efficiency.