基于数字孪生技术的三维智能化系统设计

为了提升三维智能化水平,设计基于数字孪生技术的三维智能化系统。通过现场层管理数字孪生体映射的物理实体与监测对象,为三维智能化系统提供需要的基础数据;感知层利用温度传感器与颜色传感器等,感知现场层管理的物理实体相关数据;数据存储层利用分布式文件与关系型数据库,存储感知的数据;功能层利用数据预处理模块缺失值处理存储的数据;层次化建模模块,依据缺失值处理后的数据,建立物理实体的几何模型与属性模型,融合几何模型与属性模型,得到孪生体模型;孪生体模型驱动单元,利用三维模型驱动方法,驱动孪生体模型,实现物理实体与孪生体的同步映射,得到孪生数据;仿真与预测模块依据孪生数据,可视化监测与分析物理实体的工作状态;通过应用层为用户实时呈现物理实体的动作仿真与实时监控结果。实验证明：该系统可有效感知物理实体的相关数据,建立孪生体模型;该系统可有效实现物理实体的可视化管理,提升三维智能化水平。     

基于数字孪生的配电房监测方法

针对配电房传感器映射关系建立复杂、监测难度大的问题，研究一种新的数字孪生配电房监测方法，该方法映射关系和监测准确度更优。该方法是物理实体向虚拟空间映射的启发构造出来的，在配电房传感器数据提取的基础上，通过数字孪生技术实现配电房物理实体向虚拟模型的架构匹配、数字转换、运行仿真和实时监测，就可得到新的配电房监测方法。该方法已成功应用于配电房的状态监测中，在中国某城市的实例验证了该方法对配电房监测的有效性。     

断路器柔性装配车间数字孪生系统设计

为优化断路器装配车间的产线结构和作业方法,结合数字孪生技术,提出一种基于多机器人运动控制的断路器柔性自动化车间装配方案。面向自动化装配单元,结合工业机器人的柔性装配工艺及方法,对实体装配车间进行全物理属性的数字化建模,同时建立多机器人的运动学控制模型,将机器人的三维运动模型应用于虚拟孪生场景。通过数据的交互传递,实现物理单元与虚拟单元的实时链接,将车间机器人的运动轨迹、装配状态、作业运送流程等数据信息进行实时显示,从而实现断路器柔性装配数字孪生系统的搭建与同步映射。实验结果证明,所提方案对实现断路器柔性装配有显著效果。     

面向配电网终端设备的数字孪生映射方法研究

提出了一种面向配电网终端设备的数字孪生映射方法,推动电网企业数字化转型和电力系统自动化,降低成本与安全风险。方法利用虚拟数字孪生空间映射电网物理设备,实现对区域配电网多类型设备故障的实时诊断。首先,对配电网终端设备数据进行压缩转换和级联映射,提取感知终端监测信息与物理拓扑连接关系。其次,采用改进的轻量级Yolov4网络模型进行设备类型识别与分割,结合物理拓扑图进行数字孪生映射,形成设备孪生模型。最后,设计基于卷积注意力机制的状态评估模型,充分考虑区域设备关联与故障特征,实现对设备孪生模型的故障评估及物理空间设备的状态反馈。上述创新方法有望为电力行业带来更高效、安全的运行模式,推进电网智能化发展。     

基于数字孪生的虚拟仿真系统研究与应用

为解决全实物平台开发环境搭建困难、不便于测试与维护等问题,在研究PowerPC 处理器的实时嵌入式开发的基础上,采用数字孪生技术的设计思想,完成了一种拥有故障模拟与注入、协同仿真与模块化编程等功能的超实时虚拟仿真系统;提出了一种全数字仿真系统的设计与实现方法,基于数字孪生技术把硬件主板上的处理器以及外围设备虚拟化,集成到数字模型当中;各模型之间相互协同控制,实现CPU控制外部设备与动力学模型等设备之间的通信,以及数据收发、内存读写、串口输出等行为,最终实现与物理设备相同的功能;另外,采用了虚实结合的方法验证了运行结果的准确性,加快了软件执行效率,便于快速全面的系统开发与测试,从而更好地运用到各个领域当中。     

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。     

四川省数字孪生流域知识图谱的设计与实现

知识图谱是数字孪生流域建设知识平台的重要组成部分,本研究以数字孪生流域建设而汇聚的数据底板为基础,依托自顶向下和自底向上相结合的方法,通过总体框架设计,基于BERT-BiLSTM-CRF命名实体识别、Transformer模型的关系抽取、Neo4j的存储和可视化展示完成知识图谱的搭建,并基于知识图谱建设性构建智能问答系统,为四川省数字孪生流域物理流域的全映射提供了支撑,实现了知识的可视化表达、精准查询与智能推荐,为四川省河湖智能管理提供知识性参考。     

基于LabVIEW和MATLAB的数字孪生供热系统平台的设计与仿真

数字孪生技术充分利用物理结构、传感器更新、设备运行历史等数据通过集成多领域、多物理量、多可能性的模拟过程，在虚拟空间中进行镜像，以此表达相对应的实物装置的整个生命周期过程。从智慧供热的发展历史来看，依托现代工业系统理念，提出了基于"数字孪生"的智能供热系统结构。首先介绍了数字孪生的基本结构，给出了数字孪生的构建方式基于虚拟仪器Labview的大数据采集、处理、归档、仿真；然后以采集的数据为基础，得到供热系统的孪生模型，叙述了数字孪生技术解决的关键问题；最后，通过Labview仿真平台调用Matlab中神经网络智能算法，得到基于大数据采集以及经过智能算法优化后的参数，同时系统将参数反馈给物理实体设备，从而完成孪生模型的仿真、优化、反馈过程。通过热网系统优化仿真案例验证了Labview和Matlab混合编程在建立的孪生供热平台上、应用的有效性。     

工业互联网支持下的数字孪生车间

随着信息时代的发展,数字孪生技术已成为实现智能制造的方法之一。首先说明了数字孪生的产生背景,数字孪生技术是实现信息空间和物理空间信息数据融合的重要方法、手段。接着从模型、数据、应用等不同方面,对智能车间数字孪生技术进行了探讨,同时比对了不同公司对数字孪生技术在车间应用的侧重点。通过比较智能车间相关概念,得出了数字孪生车间是一种新的车间运行模式,其关键问题是实时数据传输。工业互联网是一种将人、数据和设备等连接起来的网络技术,通过物联网等技术可以实现实时数据传输。分析了工业互联网技术的发展及工业互联网技术对实现数字孪生车间的技术支持,最后对数字孪生技术的发展进行了展望。随着数字孪生技术在车间中的运用,数字孪生车间必将成为未来智能车间的一种重要的实现方式。     

面向智能矿山的数字孪生技术研究进展

智能矿山领域数字孪生技术的应用需面对较多复杂性、特殊性的技术突破。阐述了数字孪生在智能矿山领域的适用性,归纳梳理了数字孪生技术在煤矿安全、生产及运营管理等方面的研究及应用现状：在煤矿安全管理方面,数字孪生技术主要应用于灾害预警、风险管控、灾害救援等;在煤矿生产方面,数字孪生技术主要应用于采掘工作面区域整体、单机机械装备状态监测及控制、机械装备预测性维护。从物理实体、虚拟实体、连接交互、数字孪生数据及功能服务5个维度入手探讨了智能矿山领域数字孪生亟待解决的关键共性问题：物理实体维度需重点突破全面感知及控制装备的研发,虚拟实体维度需深入进行物理、行为、规则模型的研究,连接交互维度需攻关煤矿井下5G网络传输关键技术,数字孪生数据维度需解决高性能计算等问题,功能服务维度需研发仿真软件及人工智能算法,以便更好地适应现场环境。从矿井规划设计、开发、建设阶段的灾害预防性设计、生产系统设计、地质环境预测,矿井生产运营阶段的灾害预警及防控、生产调度决策优化、生产设备全生命周期管理等方面展望了数字孪生技术在智能矿山领域的发展趋势,认为宜针对关键部件或装备,核心环节,重要或危险场所、区域等进行精细化孪生。     

Product redesign using functional backtrack with digital twin

Digital twin, as a new industrial technology, provides great opportunities in various stages of product development. Product redesign is widely required in the process of product improvement, which is greatly depends on the functional analysis of product. Although traditional functional analysis can identify product design problems, the analyzed information is extremely detailed and verbose, which hinders the opportunity of product innovation. To expand the solution space for improving the innovation chance and ensuring solution quality of the product in the physical space, a digital twin is introduced in the redesign process. This study proposes a product redesign method using the functional backtrack obtained from a relational function model (RFM) to the hierarchical function model (HFM) with the digital twin. Based on a selected target product, the proposed method constructs the product RFM (sub-field) that originates from the reverse fishbone and relationships between components. Related parameters of components are obtained. A digital twin entity is built using the RFM (sub-field) and parameters based on the target physical product, and functions are extracted in the form of “verb + noun.” The RFM is formed considering four relations between functions. Furthermore, functions in the RFM are divided into various levels using the Dempster–Shafer theory based on functional levels and boundaries. In addition, the HFM is formed to indicate the level of problem functions and range area of the solution space. Components and parameters of harmful functions are obtained based on the digital twin entity. Creative ideas of product redesign are generated using the theory of inventive problem solving (TRIZ) to solve inventive problems at different functional levels. Technique for order preference by similarity to an ideal solution (TOPSIS) is introduced to evaluate and select solutions. Finally, the feasibility and effectiveness of the proposed method are verified in the redesign of an antenna mounted on vehicles.     

Digital twin-assisted fault diagnosis system for robot joints with insufficient data

The robot joint is an important component of the construction robot, and its fault diagnosis can ensure the exact execution of building jobs, stable operation, and timely prevention of probable safety mishaps. However, deep learning-based fault diagnosis needs a multitude of measured fault data, which is difficult to obtain for various reasons. To solve the problem of insufficient data, a digital twin-assisted fault diagnosis system for robot joints is proposed. First, a simplified dynamics model of the robot joint is developed to generate the virtual entity data which can be used as the X-domain data for the digital twin model. Second, a CycleGAN-based digital twin model is proposed to map the virtual entity (X-domain) data to the physical entity (Y-domain) utilizing only a small amount of measured data. In the end, a test-rig for the robot joint is built to simulate the robot's working conditions, and the CNN-ResNet classifier is utilized to verify the effectiveness of the simulated data generated by the digital twin model. The results show that the fault diagnosis accuracy can be increased from 32.5% to 98.86% utilizing only 400 sets of measured data.     

数字孪生驱动的汇流行星排故障预测研究综述

为了在第四次工业革命中抢占制高点,各国紧锣密鼓地进行着自己的信息化建设,数字孪生技术作为关键技术之一,可以实现物理世界与信息世界的交互,将该技术应用到装甲车辆汇流行星排的故障预测,可以实时预测车辆运行状态,有效降低了事故发生的概率,大大提高了车辆的安全性,对提高战斗力有重要意义;在综述数字孪生技术于故障预测研究方面的发展历程的基础上,针对装甲车辆汇流行星排实际工作过程中难以及时预测故障的问题,提出了4层数字孪生框架,即物理实体层、信息交互层、数据互动层和人机交互层,并阐述了每一层的具体功能要求,预期实现装甲车辆汇流行星排在发生故障前及时预警,从而达到提高设备使用寿命及驾驶安全性的目的 .     

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.     

Digital twin-driven surface roughness prediction and process parameter adaptive optimization

In the process of parts machining, the real-time state of equipment such as tool wear will change dynamically with the cutting process, and then affect the surface roughness of parts. The traditional process parameter optimization method is difficult to take into account the uncertain factors in the machining process, and cannot meet the requirements of real-time and predictability of process parameter optimization in intelligent manufacturing. To solve this problem, a digital twin-driven surface roughness prediction and process parameter adaptive optimization method is proposed. Firstly, a digital twin containing machining elements is constructed to monitor the machining process in real-time and serve as a data source for process parameter optimization; Then IPSO-GRNN (Improved Particle Swarm Optimization-Generalized Regression Neural Networks) prediction model is constructed to realize tool wear prediction and surface roughness prediction based on data; Finally, when the surface roughness predicted based on the real-time data fails to meet the processing requirements, the digital twin system will warn and perform adaptive optimization of cutting parameters based on the currently predicted tool wear. Through the development of a process-optimized digital twin system and a large number of cutting tests, the effectiveness and advancement of the method proposed in this paper are verified. The organic combination of real-time monitoring, accurate prediction, and optimization decision-making in the machining process is realized which solves the problem of inconsistency between quality and efficiency of the machining process.     

基于CPSO的混合核函数SVM参数优化及应用

支持向量机(SVM)建模的拟合精度和泛化能力取决于相关参数的选取,目前SVM中的参数的寻优一般只针对惩罚系数和核参数,而混合核函数的引入,使SVM增加了一个可调参数.针对混合核函数SVM的多参数选择问题,提出利用具有较强全局搜索能力的混沌粒子群(CPSO)优化算法对混合核函数SVM建模过程中的重要参数进行优化调整,每一...     

An update method for digital twin multi-dimension models

Digital twin, as an effective means to realize the fusion between physical and virtual spaces, has attracted more and more attention in the past few years. Based on ultra-fidelity models, more accurate service, e.g. real-time monitoring and failure prediction, can be reached. Against the background, some scholars studied the related theories and methods on modeling to depict various features of physical objects. Some scholars studied how to use Internet of Things to realize the connections and interactions, thereby keeping the consistency between the virtual and physical spaces. During this process, a new question arises that how to update the models once digital twin models are inconsistent with the practical situations. To solve the problem, this paper proposed a general digital twin model update framework at first. Then, the update methods for multi-dimension models are further explored. The cutting tool is the core component of machine tools which are the key equipment in industry. The precise cutting tool models are essential for realizing the digitalization and servitization of machine tools. Therefore, this paper takes a cutting tool as the application object to discuss how to conduct physics model update based on the proposed framework and methods. Through model update, a more accurate and updated tool wear model could be obtained, which contributes to the prognostics and health management for machine tools.     

Unified modeling for digital twin of a knowledge-based system design

While Model-Based Systems Engineering (MBSE) improves the ambiguity problem of the conventional document-based way, it brings management complexity. Faced with the complexity, one of the core issues that companies care about is how to effectively evaluate, predict, and manage it in the early system design stage. The inaccuracy of contemporary complexity measurement approaches still exits due to the inconsistency between the actual design process in physical space and the theoretical simulation in virtual space. Digital Twin (DT) provides a promising way to alleviate the problem by bridging the physical space and virtual space. Aiming to integrate DT with MBSE for the system design complexity analysis and prediction, based on previous work, an integration framework named System Design Digital Twin in 5 Dimensions was introduced from a knowledge perspective. The framework provides services for design complexity measurement, effort estimation, and change propagation prediction. Then, to represent the system design digital twin in a unified way, a modeling profile is constructed through SysML stereotypes. The modeling profile includes System design digital model in virtual space profile, system services profile, relationships profile and digital twin data profile. Finally, the system design of a cube-satellite space mission demonstrates the proposed unfiled modeling approach.     

Conceptual digital twin modeling based on an integrated five-dimensional framework and TRIZ function model

Digital twin represents a fusion of the informational and physical domains, to bridge the material and virtual worlds. Existing methods of digital twin modeling are mainly based on modular representation, which limits guidance of the modeling process. Such methods do not consider the components or operational rules of the digital twin in detail, thereby preventing designers from applying these methods in their fields. With the increasing application of digital twin to various engineering fields, an effective method of modeling a multi-dimensional digital twin at the conceptual level is required. To such an end, this paper presents a method for the conceptual modeling of a digital twin based on a five-dimensional digital twin framework to represent the complex relationship between digital twin objects and their attributes. The proposed method was used to model the digital twin of an intelligent vehicle at the concept level.