摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-调查人员讨论机器学习的新发现。根据NewsRx C orresponders从意大利卡塔尼亚传来的消息，研究表明：“受半导体行业现实问题的启发，我们为一家受到不可预测中断不利影响的公司引入了一种新颖的数字孪生模型。具体来说，该公司使用外部供应商提供的原材料制造产品，而由于中断事件，交货时间可能会突然改变。”这项研究的资助者包括卡塔尼亚大学、欧盟委员会联合研究中心、西班牙政府。我们的新闻记者从卡塔尼亚大学的研究中得到一句话:“公司采用平滑订货-交货规则作为补充政策。它的特点是有三个控制参数,必须优化这些参数以增强系统的弹性。为此,数字双子网络从实际的生产分布数据中提取并根据外部环境的变化周期性地自调整补货参数。数字双子网络结合了数据分析、仿真建模、机器学习和元启发式。更具体地说，人工神经网络从制造商的操作中学习并生成预测模型。这种网络嵌入了粒子群优化算法中，实验结果表明，在补货参数不变的情况下，数字孪生的性能优于传统的补货策略。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news originating from Catania, Italy, by NewsRx c orrespondents, research stated, "Inspired by a real-life problem in the semicond uctor industry, we introduce a novel digital twin model for a company subject to the adverse effects of unpredictable disruptions. Specifically, this company ma nufactures a product using a raw material provided by an external supplier, whos e lead times may abruptly change due to disruptive events." Funders for this research include University of Catania, European Commission Joi nt Research Centre, Spanish Government. Our news journalists obtained a quote from the research from the University of C atania, "The Smoothing Order-Up-To rule is adopted by the company as a replenish ment policy. It is characterized by three control parameters, which must be opti mized to enhance the resilience of the system. To this end, the digital twin lea rns from the real production-distribution data and periodically self-adjusts the replenishment parameters based on the evolution of the external environment. Th e digital twin architecture combines data analytics, simulation modeling, machin e learning, and a metaheuristic. More specifically, an Artificial Neural Network learns from the manufacturer's operations and generates predictive models. Thes e are embedded in a Particle Swarm Optimization, which provides the optimal comb ination of the replenishment parameters. An experimental campaign was performed to demonstrate that the digital twin outperforms the traditional strategy in whi ch the replenishment parameters are kept unchanged."
NETL
NSTL