论文标题
基于边缘云的参考体系结构,以支持过程行业的认知解决方案
An Edge-Cloud based Reference Architecture to support cognitive solutions in the Process Industry
论文作者
论文摘要
工艺行业(例如钢,金属,化学物质,水泥,沥青,陶瓷)是世界经济的主要领域之一,但其特征是环境的巨大影响和非常高的能源消耗。尽管PI的传统创新速度传统,但近年来,全球范围内的强烈努力朝着提高植物效率和产品质量的双重目标,大大降低了电力和二氧化碳排放的消耗。数字技术(即智能嵌入式系统,物联网,数据,AI和边缘到云技术)使驱动程序可以实现双数字绿色过渡,以及以人为中心,安全,舒适和包容的工作场所的基础。当前,植物中的数字传感器产生了大量数据,在大多数情况下,这些数据仅构成潜在的,而不是工艺行业的实际价值,通常是在密切专有系统中锁定的,很少被利用。数字技术通过数字双胞胎进行过程模型模拟,可以在物理和虚拟世界之间建造桥梁,从而以极大的效率和巨大减少浪费带来创新。根据Industrie 4.0的指南,H2020资助的CAPRI项目旨在基于开源软件的模块化和可扩展的参考体系结构来创新流程行业,这可以在Brownfield和Greenfield场景中实施。在创建数据的边缘,最大的计算资源的云之间分发处理的能力,有助于具有认知能力的集成数字解决方案的开发。参考架构正在沥青,钢和制药飞行厂进行验证,允许开发综合计划解决方案,并通过日程安排和控制工厂。
Process Industry (PI e.g. Steel, Metals, Chemicals, Cement, Asphalt, Ceramics) is one of the leading sectors of the world economy, characterized however by intense environmental impact, and very high energy consumption. In spite of a traditional low innovation pace in PI, in the recent years a strong push at worldwide level towards the dual objective of improving the efficiency of plants and the quality of products, significantly reducing the consumption of electricity and CO2 emissions has taken momentum. Digital Technologies (namely Smart Embedded Systems, IoT, Data, AI and Edge-to-Cloud Technologies) are enabling drivers for a Twin Digital-Green Transition, as well as foundations for human centric, safe, comfortable and inclusive work places. Currently, digital sensors in plants produce a large amount of data which in most cases constitutes just a potential and not a real value for Process Industry, often locked-in in close proprietary systems and seldomly exploited. Digital technologies, with process modelling-simulation via digital twins, can build a bridge between the physical and the virtual worlds, bringing innovation with great efficiency and drastic reduction of waste. In accordance with the guidelines of Industrie 4.0, the H2020 funded CAPRI project aims to innovate the process industry, with a modular and scalable Reference Architecture, based on open source software, which can be implemented both in brownfield and greenfield scenarios. The ability to distribute processing between the edge, where the data is created, and the cloud, where the greatest computational resources are available, facilitates the development of integrated digital solutions with cognitive capabilities. The reference architecture is being validated in the asphalt, steel & pharma pilot plants, allowing the development of integrated planning solutions, with scheduling and control of the plants.