Abstract
随着“工业4.0”“智能制造”等概念规划的提出以及大数据、人工智能等高新技术的普及,工业领域制造行业呈现高度信息化、自动化趋势,生产过程和生产模式逐步智能化、一体化。传统生产模式下通过实际生产过程获得的数据进行指标测量并制定决策的方式已经不再能够满足当下制造企业对多单元复杂生产系统的管控需要,因此,面向制造企业全生命周期的数字孪生成为制造企业转型升级的新突破点、成为智能制造领域的新兴研究热点。本文通过与传统仿真技术进行横向对比,系统分析基于大数据、人工智能、虚拟现实等的数字孪生技术内涵以及其与传统仿真技术存在的关联和异同,重点分析面向制造企业全生命周期、针对制造企业多单元复杂生产系统智能运行和维护的数字孪生的优势和具体应用方式,阐述数字孪生对实现制造企业全生命周期管理的可行性,并展望其未来的发展趋势和方向。 With the introduction of concept planning such as Industry 4.0 and Intelligent Manufacturing, at the same time, the popularization of high and new technologies such as big data and artificial intelligence, the manufacturing industry in the industrial field presents a high degree of informatization and automation trend; the production process and production mode are gradually intelligent and integrated. Under the traditional production mode, the index measurement and decision making method based on the data obtained from the actual production process can no longer meet the current manufacturing enterprises’ control needs for the multi-unit complex production system; therefore, digital twinning oriented to the whole life cycle of manufacturing enterprises has become a new breakthrough point for the transformation and upgrading of manufacturing enterprises and an emerging research hotspot in the field of intelligent manufacturing. This paper makes a horizontal comparison with the traditional simulation technology, systematically analyzes the connotation of digital twin technology based on big data, artificial intelligence and virtual reality, as well as its correlation, similarities and differences with traditional simulation technology. The analysis focuses on the whole life cycle of manufacturing enterprises, aims at the advantages and specific application of digital twin for intelligent operation and maintenance of complex multi-unit production system, expounds the feasibility of digital twinning to realize the whole life cycle management of manufacturing enterprises, and looks forward to its future development trend and direction.

This publication has 5 references indexed in Scilit: