An Artificial Immune System Approach for Solving Type-E Assembly Line Balancing Problem with Problem-Specific Information
An Artificial Immune System Approach for Solving Type-E Assembly Line Balancing Problem with Problem-Specific Information
复制标题
DOI：
10.1109/icca51439.2020.9264382
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
M. Khalid;U. K. Yusof;H. Iida
中科院分区：
文献类型：
--
作者：
M. Khalid;U. K. Yusof;H. Iida
工业4.0的到来开创了制造业的新时代，仅仅优化可用资源不足以满足不断增长的市场需求。几十年来，各种方法已经解决了装配线平衡（ALB）问题。虽然解决ALB问题至关重要，但在接下来的操作阶段仍可能出现瓶颈。因此，两个研究方向是必要的。除了提出一个有效的搜索机制，还需要最佳的信息利用，预期的结果将有利于双方。此外，利用特定问题的信息（瓶颈识别），预计将提高ALB问题的解决方案的质量。本文通过提出两种人工免疫系统（AIS）方法，即传染性免疫网络（COMET）方法，为此类索赔提供了概念验证，该方法适用于ALB问题，其中纳入了特定问题的信息。建议的AIS方法进行了测试，24 ALB基准数据集，以确定其有效性，并强调纳入瓶颈识别的影响。此外，所提出的方法对文献中的方法的比较分析是统计上合理的。
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.