In furtherance of emerging research within smart production planning and control (PPC), this paper prescribes a methodology for the design and development of a smart PPC system. A smart PPC system uses emerging technologies such as the internet of things, big-data analytics tools and machine learning running on the cloud or on edge devices to enhance performance of PPC processes. It achieves this by using a wider range of data sources from the production system, capturing and utilizing the experience of production planners, using analytics and machine learning to harness insights from the data and allowing dynamic and near real-time action to the continuously changing production system. The proposed methodology is illustrated with a case study in a sweets and snacks manufacturing company, to highlight the key considerations and challenges production managers might face during its application. The case further demonstrates considerations for scalability and flexibility via a loosely coupled, service-oriented architecture and the selection of fitting algorithms respectively to address a business requirement for a short-term, multi-criteria and event-driven production planning and control solution. Finally, the paper further discusses the challenges of PPC in smart manufacturing and the importance of fitting smart technologies to planning environment characteristics.

为了推进智能生产计划和控制 (PPC) 领域的新兴研究，本文规定了一种设计和开发智能 PPC 系统的方法。智能 PPC 系统使用新兴技术，例如在云端或边缘设备上运行的物联网、大数据分析工具和机器学习，以提高 PPC 流程的性能。它通过使用来自生产系统的更广泛的数据源、捕获和利用生产计划人员的经验、使用分析和机器学习来利用数据洞察力并允许对不断变化的生产采取动态和近乎实时的行动来实现这一目标系统。提议的方法通过糖果和零食制造公司的案例研究来说明，强调生产经理在应用过程中可能面临的关键考虑因素和挑战。该案例进一步展示了通过松散耦合、面向服务的体系结构和拟合算法的选择对可扩展性和灵活性的考虑，以解决短期、多标准和事件驱动的生产计划和控制解决方案的业务需求。最后，本文进一步讨论了智能制造中 PPC 的挑战以及将智能技术与规划环境特征相匹配的重要性。面向服务的体系结构和拟合算法的选择分别解决了短期、多标准和事件驱动的生产计划和控制解决方案的业务需求。最后，本文进一步讨论了智能制造中 PPC 的挑战以及将智能技术与规划环境特征相匹配的重要性。面向服务的体系结构和拟合算法的选择分别解决了短期、多标准和事件驱动的生产计划和控制解决方案的业务需求。最后，本文进一步讨论了智能制造中 PPC 的挑战以及将智能技术与规划环境特征相匹配的重要性。