Robust planning of production networks at an automotive supplier
研究了汽车供应商生产网络的稳健规划，使用蒙特卡洛模拟和聚类生成场景，结合随机建模和数字孪生概念处理数据不完整问题，帮助企业在复杂网络中高效利用资源。
As global trends like individualisation continue to drive significant changes in industrial production within international networks, it has become increasingly crucial for companies to maintain competitiveness through the efficient utilisation of resources. The rising complexity in production networks originates from an increasing number of constraints due to company-specific requirements, coupled with expanding networks that broaden the solution space, ultimately leading to prolonged planning processes. Furthermore, current planning tasks are predominantly performed manually, as the extensive efforts required for data acquisition often render the use of solution algorithms infeasible due to incomplete or inaccurate data. Therefore, this study explores robust planning of production networks, employing Monte–Carlo simulation and clustering for scenario generation, stochastic modelling concepts to tackle the mathematical problem, and utilising DT concepts for data integration at the network level.