基于多智能体的数字孪生及其在工业中应用的综述

数字孪生是一种将物理实体数字化的技术,通过建立虚拟的数字孪生模型模拟实际的物理过程,以便进行模拟仿真、数据分析和优化设计等操作.鉴于此,分析数字孪生技术在复杂工业生产中的发展历程和研究现状,并重点讨论其概念、国家相关重点研究的政策,以及数字孪生使能技术在各行业的应用.主要途径是分析和综述基于多智能体的数字孪生、基于数字孪生的设计、制造和运维、数字孪生的集成在智能制造中的应用相关的研究成果.此外,提出高炉连续生产数字孪生方案和大飞机多智能体离散制造方案,高炉模型包括成分场大模型和增量学习小模型,该模型可以为数字孪生在复杂流程工业中的应用提供带有增量补偿的机理与计算机视觉相结合的解决方案.在复杂工业制造中,数字孪生和多智能体技术可以提高生产效率和质量,减少能源消耗和废品产生,同时也能够降低复杂度、安全风险和成本.     

智能制造下产品数字孪生体全生命周期研究

针对信息物理融合系统在智能制造领域中的应用新范式,提出了产品数字孪生体全生命周期的理论框架.数字孪生的出现为信息物理融合理念的实现提供可行的思路和途径.从数字孪生概念的发展背景出发,分别从物理对象和物理对象的发展过程分析数字孪生和数字孪生体的定义,在此基础上进一步分析了数字孪生体全生命周期的内涵和特征.数字孪生体全生命...     

数字孪生: 跨界赋能于多领域智能的新应用

随着大数据、5G、人工智能、CPS、云计算、物联网技术的发展与交叉融合, 使得世界朝着数字化、智能化方向发展. 数字孪生是以物理实体为原型建立多维虚拟模型, 通过安装在物理本体上的传感器实时反馈数据, 并结合以往的历史数据和人工智能技术, 最后利用软件分析并呈现. 由于数字孪生技术能与多个先进理念, 如: 工业4.0、航空航天、智慧城市、智慧医疗等良好的融合并应用, 这使其成为多个行业的热门研究方向与主要驱动技术, 在各行各业都有很大的发展空间. 本文首先阐述了数字孪生技术的基本概念, 梳理了数字孪生技术的发展脉络, 进一步理清了数字孪生技术与CPS技术之间的关系, 并介绍了数字孪生技术的研究现状. 其次, 介绍了数字孪生的关键技术即多维多尺度建模, 孪生数据管理和虚拟呈现. 最后, 探讨了数字孪生技术在智慧工厂领域、智慧城市领域、孪生医疗领域、航空航天领域的应用发展和方向, 并从方案、特点、关键技术等角度介绍了本研究团队在智慧工厂领域对原稳加热炉设备的数字孪生应用案例.     

基于数字孪生技术的船舶管件加工智能车间研究

数字孪生技术的研究成果在智能化制造领域得到推广应用。这已经引起国内外相关学术界与企业的高度关注。为研究数字孪生技术与智能车间生产融合应用效果,以船舶管件加工车间为研究对象,分析了传统管件加工车间的生产特点。采用数字孪生技术,建立了从管材入库、上料、管线切割、打磨、贴标、焊接到管零件制作完成的数字模型,创新构建了虚实结合的智能管件加工车间实时监控与反馈的信息技术架构。通过先在数字空间对虚拟工作流程的仿真优化,再将优化方案应用于直管产线的方式,大幅提升了管件加工车间的运行效率,提高了产品质量。研究表明,面向复杂智能制造产线,构建数字孪生空间可以有效打通制造执行、企业管理、物联网等系统,虚拟流程的仿真优化结果可以实现对实际产线工艺的指导和优化。     

数字孪生与生产线仿真技术研究

随着新一代信息技术与制造技术的深度融合,仿真技术正向着信息系统与物理系统深度融合和高效协同的方向发展,应运而生的数字孪生技术成为近年来的新兴研究热点.为探索采用新一代信息技术促进离散制造行业数字化转型升级,从仿真技术的发展脉络和应用场景入手,引入基于数字孪生技术开展生产线仿真分析的研究,介绍了数字孪生技术的概念和内涵,...     

数字孪生驱动的火箭控制系统故障诊断研究综述

在第四次工业革命中,智能制造成为各国工业发展的重点方向,数字孪生技术作为一项新兴技术,能够有效实现物理信息的融合;将其应用于火箭控制系统的故障诊断和健康管理,能够进一步提高故障诊断的事前准确性,提升火箭发射的可靠性;本文对数字孪生技术在航天领域的研究现状进行归纳整理;首先梳理了NASA的数字孪生目标,国内领域按照设计、生产、支持服务阶段对数字孪生应用进行分类;其次,按照故障树、专家系统、神经网络、数据驱动的方法阐述控制系统故障诊断的研究现状;在介绍数字孪生驱动的健康管理方法的基础上,提出数字孪生驱动的火箭控制系统的故障诊断方法;详细介绍其基本组成框架,分析关键技术及应用难点,并提出数字孪生健康管理平台的基本流程;该方法预期实现火箭控制系统的事前诊断和维修策略的制定     

可靠性数字孪生概念内涵和技术框架研究

在武器装备可靠性与数字孪生技术的基础上,提出了覆盖"全系统、全特性、全过程"的数字孪生体系结构,明确了可靠性数字孪生的定义,界定了可靠性数字孪生与性能数字孪生的相互关系.并且,从系统层级、系统特性、系统过程3个维度分析了产品数字孪生框架,以此为基准构建了包括故障物理模型、传感器数据监测、健康信息感知、使用与维修映射、数...     

基于数字孪生的力能控制式压力机虚拟调试

为降低调试周期和成本,提前预知系统级风险,基于数字孪生的虚实一致特性,提出了一种基于数字孪生的力能控制式压力机虚拟调试方法,设计了虚拟调试系统.根据力能控制式压力机的多系统协同调试任务,建立了其多物理领域统一模型,即机械、电气等的多领域数字孪生模型,并构建了虚拟控制系统,包括虚拟控制器和控制器-模型接口.通过应用于压力机虚拟调试的实例,展示了基于此数字孪生模型进行虚拟调试的有效性,构建的虚拟调试系统能够验证机械系统、电气系统和控制程序的设计,并确定和优化运行参数,有效避免了实机调试成本高、风险大、周期长等弊端.     

面向智能矿山与新工科的数字孪生技术研究

将数字孪生与人工智能(AI)技术相结合,提出了基于数字孪生+AI的智能矿山建设新思路。探索了智能矿山技术发展路径,研究了数字孪生技术的特征、应用领域及发展趋势,指出数字孪生是数字化矿山发展的必然趋势。提出了基于数字孪生+AI的智能矿山理论架构,构建了矿山数字孪生模型,模型自下而上分别为矿山全要素物理实体、矿山信息物理融合层、矿山数字孪生模型、矿山孪生数据交互层、矿山应用智能服务层,据此实现智能矿山的泛在感知、协同控制和智能决策与优化。从应用实际需求出发,探讨了智能矿山模型构建技术、智能开采数字孪生体技术、矿山智能控制技术、矿山设备故障预测、基于数字孪生的人机交互等关键技术。通过研究数字孪生在智能矿山中的应用,为AI技术在智能矿山应用落地提供思路,为未来智能矿山新工科建设提供理论借鉴。     

基于动力学的张拉整体柔性臂数字孪生系统

连续型机器人因其具有柔顺大变形、灵巧运动等特点,已成为未来提升机器人安全性和交互性的发展趋势,而数字孪生是实现机器人-环境-人之间共融共存的重要技术保障.本文以张拉整体连续型柔性臂为研究对象,结合数字孪生和虚拟仿真等技术,让张拉整体柔性臂在虚拟空间和实际物理空间中得以深度融合.搭建数据通讯架构实现数据实时传输和驱动,以提升柔性臂与人的协同工作效率,并可在复杂的环境中通过碰撞检测反馈实现动态避障.进一步,开发了一款基于动力学的张拉整体柔性臂数字孪生系统,并通过虚实双向操控验证了所建系统的有效性,为机器人远程智能监测与控制提供了参考.     

Automated manufacturing system discovery and digital twin generation

The latest developments in industry involved the deployment of digital twins for both long and short term decision making, such as supply chain management, production planning and control. Modern production environments are frequently subject to disruptions and consequent modifications. As a result, the development of digital twins of manufacturing systems cannot rely solely on manual operations. Recent contributions proposed approaches to exploit data for the automated generation of the models. However, the resulting representations can be excessively accurate and may also describe activities that are not significant for estimating the system performance. Generating models with an appropriate level of detail can avoid useless efforts and long computation times, while allowing for easier understanding and re-usability. This paper proposes a method to automatically discover manufacturing systems and generate adequate digital twins. The relevant characteristics of a production system are automatically retrieved from data logs. The proposed method has been applied on two test cases and a real manufacturing line. The experimental results prove its effectiveness in generating digital models that can correctly estimate the system performance.     

Towards a sustainable interoperability in networked enterprise information systems: Trends of knowledge and model-driven technology

In a turbulent world, global competition and the uncertainty of markets have led organizations and technology to evolve exponentially, surpassing the most imaginary scenarios predicted at the beginning of the digital manufacturing era, in the 1980s. Business paradigms have changed from a standalone vision into complex and collaborative ecosystems where enterprises break down organizational barriers to improve synergies with others and become more competitive. In this context, paired with networking and enterprise integration, enterprise information systems (EIS) interoperability gained utmost importance, ensuring an increasing productivity and efficiency thanks to a promise of more automated information exchange in networked enterprises scenarios. However, EIS are also becoming more dynamic. Interfaces that are valid today are outdated tomorrow, thus static interoperability enablers and communication software services are no longer the solution for the future. This paper is focused on the challenge of sustaining networked EIS interoperability, and takes up input from solid research initiatives in the areas of knowledge management and model driven development, to propose and discuss several research strategies and technological trends towards next EIS generation.     

On the design of emergent systems: an investigation of integration and interoperability issues

Many useful manmade systems in this world are extremely complex; a typical example is a large infrastructure. No design team ever invents these artifacts because they are too complex. These artifacts are made by combining existing elements (legacy) and by building new subsystems without explicit and comprehensive up-front coordination. To a large extent, these complex systems emerge and evolve. Experience shows that designers frequently fail to develop artifacts that, when combined, facilitate the emergence of effective and efficient systems. This paper formally elaborates the mechanism behind this phenomenon, and proposes principles for the design of components for emergent systems. The above insights were gained during the development of research prototypes for multi-agent manufacturing control; manufacturing systems are notorious for experiencing integration and interoperability problems as described above. Consequently, the design principles are discussed and illustrated on the design of multi-agent manufacturing control systems but also on work by others. Finally, although this paper mainly discusses the above in a generic fashion, and although the generic statements hold in an application-independent manner, it is important to appreciate that the applicability of the above insights and principles has significant limitations, which are discussed in the paper.     

面向飞行器结构健康管理的数字孪生及应用研究综述

数字孪生一词起源于美国国防部对飞行器机体数字孪生的研究,目前已经成为全球制造业的前沿热点领域.解析了数字孪生的概念及其中的结构健康管理元素,提出了包含生命周期维、仿真精度维、智能程度维的数字孪生成熟度模型;梳理了面向结构健康管理的数字孪生关键技术,特别是4项关键的数字工程技术能力,包括多尺度建模、多物理特性建模、模型与...     

Modeling and implementation of a digital twin of material flows based on physics simulation

Cyber-physical production systems enable adaptivity and flexibility when manufacturing customized products in small batches. Due to varying routes and a high variance of workpieces, material flows in cyber-physical production systems can get highly complex, which can lead to physically induced disturbances that can result in accidents or decreased throughput and high costs. This issue can be addressed by applying a physics engine to simulate the physical interaction between workpieces and the material handling systems during the operation. Connecting such a digital model to a real material handling system in order to derive simulation-based decision support leads to the concept of digital twins. To date, few practical implementations of digital twins in manufacturing outside the machine tool domain were reported. Therefore, this paper describes the modeling and the subsequent implementation of an integrated system that consists of a real material handling system and its digital twin, based on physics simulation. A practical use case demonstrates the versatile advantages of the implemented solution for a manufacturing system with respect to the three digital twin functions prediction, monitoring and diagnosis.     

Scheduling-Framework für Jobs auf parallelen Maschinen in komplexen Produktionssystemen

The paper describes a framework for parallel machine scheduling in complex manufacturing systems. Complex manufacturing systems are characterized by groups of parallel machines, machine dedications, sequence dependent setup times, batch processes, prescribed due dates of the jobs, and a diverse and over time changing product mix. In the present paper, a four-phase algorithm is suggested that covers a broad range of process conditions. The frameworks contains a first phase that deals with the formation of scheduling entities. The second phase is used to assign the scheduling entities to the parallel machines. The sequence of the scheduling entities is determined in the third phase on each single machine. The schedules are improved by the final, optional fourth phase. The paper describes software development issues, the integration of the framework into other information systems on the shopfloor, and the performance assessment of a case study.     

计算实验方法的溯源、现状与展望

随着信息技术的发展,复杂系统越来越多地呈现出社会、物理、信息相融合的特征.因为这些系统涉及到了人和社会的因素,其设计、分析、管理、控制和综合等问题正面临前所未有的挑战.在这种背景下,计算实验应运而生,通过“反事实”的算法化,为量化分析复杂系统提供了一种数字化和计算化方法.对于计算实验方法的发展现状与未来挑战进行了全面梳理:首先介绍了计算实验方法的概念起源与应用特征;然后详细阐述了计算实验的方法框架与关键步骤;接着展示了计算实验方法的典型应用,包括现象解释、趋势预测与策略优化;最后给出了计算实验方法所面临的一些关键问题与挑战.旨在梳理出计算实验方法的技术框架,为其快速发展与跨学科应用提供支撑.