• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of management science and engineering management >Maintenance workload optimisation with accident occurrence considerations and absenteeism from work using a genetic algorithm
【24h】

Maintenance workload optimisation with accident occurrence considerations and absenteeism from work using a genetic algorithm

机译：使用遗传算法优化维护工作量并考虑事故发生和缺勤情况

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Optimal workforce size determination for workload management activities plays an important role in manufacturing systems. Still, the workload distribution problem is a challenging task under multi-objective considerations. This paper proposes a nonlinear multi-objective workload optimisation approach for maintenance systems.The proposed model considered the effects of workers'absenteeism and accident severity factors on workforce effectiveness and productivity. Consideration is given to conflicting workforce objectives with stochastic and deterministic workforce constraints using a genetic algorithm (GA) as a solution method. The performance of the proposed model is compared with an existing workforce model. GA and particle swarm optimisation (PSO) results are compared on the basis of their performance using the proposed model. It is observed that our model performs better than the existing model. The results from the GA are close to those of the PSO algorithm, while the GA results are better than those of the branch and bound algorithm, obtained from the existing model. The proposed model application shows that it has the capacity to determine optimal workload allocations in maintenance systems.The incorporation of workers' absenteeism and accident severity factors into this new decision making tool is the core contribution of this study.
机译：确定工作量管理活动的最佳劳动力规模在制造系统中起着重要作用。尽管如此，在多目标考虑下，工作负载分配问题仍然是一项具有挑战性的任务。本文提出了一种用于维护系统的非线性多目标工作量优化方法，该模型考虑了工人的旷工和事故严重性因素对劳动力有效性和生产率的影响。使用遗传算法（GA）作为解决方法，考虑具有随机和确定性劳动力约束的劳动力目标冲突。将该模型的性能与现有的劳动力模型进行比较。遗传算法和粒子群优化（PSO）结果在性能的基础上使用提出的模型进行了比较。可以看出，我们的模型比现有模型表现更好。遗传算法的结果与PSO算法的结果接近，而遗传算法的结果优于从现有模型中获得的分支定界算法的结果。所提出的模型应用程序表明，它具有确定维护系统中最佳工作负荷分配的能力。将工人的旷工和事故严重性因素纳入这一新的决策工具是本研究的核心贡献。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号