Digital Twin-Based Control Approach for Industrial Cloud Robotics

Digital twin-based industrial cloud robotics: Framework, control approach and implementation

The development and progress in information and communication technologies will transform traditional products into smart products and allow to offer novel smart services [1]. Herein, the digital twin (DT) concept is regarded as a key technology to create value with smart services [2]. Although the research and applications of DTs emerge continuously many concerns are to be scrutinized [3]. The lack of a shared conceptual framework for DTs with an unambiguous terminology [4] complicates cross-functional discussions. Therefore, a systematization of the main dimensions of DTs is proposed in the form of an ontology and a conceptual framework thereof derived. The research questions addressed in this paper are a) «Which dimensions are used to classify and structure DTs in academic literature?», b) «What are the fundamental differences or specifications within these dimensions?» and c) «How do these different specifications relate to each other?» The focus of the research is on the objective to find classification systematics that are a) representing the entire spectrum of DTs, b) universally valid in all DT related domains and c) applicable in research and practice. A systematic literature review on the relevant aspects of DTs was conducted and the findings iteratively advanced within workshop sessions with academic experts. DTs are considered as integrators of physical and digital worlds as well as internal and external value creation. Further, the creation of DTs requires per definition the use of digital data. Hence, the proposed ontology and conceptual framework for DTs include the following main dimensions to consider for every DT: Data resources, external value creation and internal value creation. The main subdimensions of the data resources are the data sources to obtain the data, the data categories and the data formats. The main subdimension of the external value creation are the attributes of the services as the basis of the value propositions, the level of smartness of the connected products and the actors on the different levels of the ecosystem. The main subdimensions of the internal value creation are the lifecycle phases of products, the product management levels and the different generations of both. The proposed ontology and conceptual framework support researchers and practitioners in positioning and structuring their intended DT activities and communicating them to internal and external stakeholders. The holistic view on the data resource dimension further allows to easily deduct the needed data for certain applications or deduct possible applications from already available data.

The concept of Digital Twin (DT) is increasingly getting attention due to its support for digital transformation as part of Industry 4.0. A core component of a DT is the virtual entity (VE) that is meant to ‘mirror’ the physical entity (PE). A particular challenge for developing this VE is the integration between the different models that typically make up such a VE. These models, covering different disciplines or aspects of a system, commonly are developed by different engineers and expressed in different formalisms given their strengths and weaknesses. This makes integration between these models and formalisms a challenge. Such integration has two aspects: the communication among the models, and their orchestration, which concerns the order of model step execution and data exchange. In this paper, we consider the suitability of Ptolemy II, an open source framework based on an actor-oriented structure, to implement such integration. We use the Ptolemy II framework to reproduce the implementation of a DT of an autonomous scaled-down truck, which originally required a more manual configuration and execution and was developed in a monolithic way. The results show that Ptolemy II can be used to implement different communication technologies as actors, and show the expressiveness of the orchestrators by reproducing the existing DT’s behavior. This shows Ptolemy II in principle to be suitable as an integration and orchestration tool for models in the context of DTs. As future work, we plan to apply the framework to more complex DTs using different communication technologies, so as to validate its broader suitability for VE orchestration in DTs.

Migrating the industry and society into digital area have gradually been increased in recent years. Digitalization has made our life more efficient and faster. As a result of digitalization, the Fourth Industrial Revolution, also known as Industry 4.0, was born. The Fourth Industrial Revolution, like previous revolutions, aims to facilitate life and improve the quality of life. Two terms are especially important for digitalization. These terms are Industry 4.0 and Internet of Things (IoT). Industry 4.0 and the IoT focus on the networking and automation of devices both used human being and industry. Digitalization and IoT technologies play an important role in improving energy efficiency. Digital twin (DT) technology is one of the most important key of Industry 4.0 technologies under digitalization. DT represents a digital copy of a physical system or entity. Physical objects and DT models created interact with each other. DT technologies have a wide range from manufacturing to healthcare sectors and from maritime transportation to the heavy industry. DT provides many conveniences for industries to grow with digitalization. Meanwhile, DT draws attention with its development in the academic field. In this study, an overview of DT is presented, a DT roadmap is proposed, some algorithms emerging in the concept of DT for industrial processes are explained and a case study is analyzed. This roadmap shows different methods to be applied in order to make accurate forecasting for the future applications and sustainable manufacturing with DT. As a result, DT concept is thought to attract much attention in the near future.

Propelled by recent advances in Mobile Edge Computing (MEC) and the Internet of Things (IoT), the digital twin technique has been envisioned as a de-facto driving force to bridge the virtual and physical worlds through creating digital portrayals of physical objects. In virtue of the flourishing of edge intelligence and abundant IoT data, data-driven modelling facilitates the implementation and maintenance of digital twins, where simulations of physical objects are usually performed based on Deep Neural Networks (DNNs). A significant advantage of adopting digital twins is to enable decisive prediction on the behaviours of objects in near future without waiting for that really happen. To provide accurate predictions, it is vital to keep each digital twin synchronized with its physical object in real-time. However, it is challenging to maintain the real-time synchronization between a digital twin and its physical object due to the dynamics of physical objects and sensing data drift over time, i.e., the live data from a physical object diverge from the model training data of its digital twin. To address this critical issue, continual learning is a promising solution to retrain models of digital twins incrementally. In this paper, we investigate digital twin synchronization issues via continual learning in an MEC environment, with the aim to maximize the total utility gain, i.e., the enhanced model accuracy. We study two novel optimization problems: the static digital twin synchronization problem per time slot and the dynamic digital twin synchronization problem for a finite time horizon. We first formulate an Integer Linear Program (ILP) solution for the static digital twin synchronization problem when the problem size is small; otherwise, we develop a randomized approximation algorithm at the expense of bounded resource violations for it. We also devise a deterministic approximation algorithm with guaranteed performance for a special case of the static digital twin synchronization problem. We thirdly consider the dynamic digital twin synchronization problem by proposing an efficient online algorithm for it. Finally, we evaluate the performance of the proposed algorithms for continuous digital twin synchronization through simulations. Simulation results show that the proposed algorithms are promising, outperforming counterpart benchmarks by no less than 13.2%, in terms of the total utility gain.

Objective of the paper is to describe and present results of using a "Digital Twin" in Drilling Operations (Planning and Engineering, Training and Operational Support) in the last 10 years for Operators worldwide. The concept of Digital Twin was first introduced by Michael Grieves at the University of Michigan in 2003 through Grieves’ Executive Course on Product Lifecycle Management. Winning a Formula 1 race is no longer just about building the fastest car, hiring the bravest driver and praying for luck. These days, when a McLaren technology group races in Monaco or Singapore, it beams data from hundreds of sensors wired in the car to Woking, England. There, analysts study that data and use complex computer models to relay optimal race strategies back to the driver. The McLaren race crew and the online retailers both harness data and use algorithms to make reasonable projections about the future, Parris explains. The concept is called Digital Twin [1]. A Digital Twin contains information such as a piece of equipment or asset, including its physical description, instrumentation, data and history. A Digital Twin can be created for assets ranging from a well to a piece of equipment to an entire oilfield. For example, a subsea system could have a Digital Twin via a simulation model of a subsea system's components, including the blowout preventer, tiebacks, risers, manifolds, umbilical and moorings. Drilling and extracting simulations can determine whether virtual designs can actually be built using the machines available," GE said. "Last but not least, real-time data feeds from sensors in a physical operating asset are now used to know the exact state and condition of an operating-asset product, no matter where it is in the world"[2].

The mass digitization efforts associated with the e-COL+ project, focusing on French natural history collections, provide an invaluable opportunity to reassess the need to build a comprehensive 3D digital collection to complement existing 2D digital repositories. This article explores the importance of incorporating 3D data into digital collections, highlighting its significant impact on scientific research, conservation efforts, and public outreach campaigns. Although the e-COL+ project faces practical obstacles related to digitization, it also raises important theoretical questions about the complex interplay between physical and digital objects. Here, we challenge the concepts of digital clone and digital twin that are commonly used in the construction of digital collections. The digital twin concept more accurately captures the intricate and adaptive connection between physical and digital entities that results from the precise digitization techniques used and the evolving characteristics of the specimens found in natural history collections.

Digital Twin (DT) has only been widely used since the early 2000s. The concept of DT refers to the act of creating a computerized replica of a physical item or physical process. There is the physical world, the cyber world, a bridge between them, and a portal from the cyber world to the physical world. The goal of DT is to create an accurate digital replica of a previously existent physical object by combining AI, IoT, deep learning, and data analytics. Using the virtual copy in real time, DTs attempt to describe the actions of the physical object. Battery based DT's viability as a solution to the industry's growing problems of degradation evaluation, usage optimization, manufacturing irregularities, and possible second-life applications, among others, are of fundamental importance. Through the integration of real-time checking and DT elaboration, data can be collected that could be used to determine which sensors/data used in a batteries to analyze their performance. This research proposes a Linked Clustering Model using VGG 16 for Lithium-ion batteries health condition monitoring (LCM-VGG-Li-ion-BHM). This work explored the use of deep learning to extract battery information by selecting the most important features gathered from the sensors. Data from a digital twin analyzed using deep learning allowed us to anticipate both typical and abnormal conditions, as well as those that required closer attention. The proposed model when contrasted with the existing models performs better in health condition monitoring.

A digital twin (DT) is an electronic replica of a real-world item. It is built on top of asset-specific data items and is often enhanced using semantic technologies and simulation environments. The DT lays the way for anything from routine monitoring to hands-off administration of a physical entity. With the development of the metaverse concept of DT gains importance. As it helps to manage the physical entity in the metaverse. Therefore, it is beneficial to use DT for the detection and mitigation of different types of cyber attacks. In this context, we use the concept of DT for the identification and detection of DDoS attacks in the IoT network. Our proposed approach uses the concept of support vector machine (SVM) learning technique for the identification and detection of DDoS attacks. In our proposed approach, the DT of physical routers is stored in the metaverse, which makes it secure against any type of physical attack. Our proposed approach detected the malicious packets with an accuracy of 93.25% accuracy.

Since its first mentioning in the literature, the concept of Digital Twin has gained traction in both industry and academia. However, there are still many open challenges when applying Digital Twins to industry-scale use cases. Applying Model-Driven Engineering techniques to the creation and maintenance of Digital Twins (also referred to as Model-Driven Digital Twin Engineering) promises automation and consistency throughout the life cycle of a Digital Twin. The exemplar provided in this paper can be used to identify open challenges when it comes to Model-Driven Digital Twin Engineering, and to demonstrate how approaches can solve them. This exemplar applies Digital Twins to an indoor air quality management use case, where CO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> , temperature, and humidity values of rooms within a building are measured. These values can be used to derive actions to improve work productivity and reduce the risk for virus infections. We describe three applications that make use of this Digital Twin (i.e., runtime visualization, physical simulation, and ML-based predictions), and provide an online repository with the artefacts of this exemplar.

The rapid advancement of Industry 4.0 and the Internet of Things (IoT) has underscored the importance of effective diagnostics for electric motors, which are critical components in industrial, energy, and transportation systems. Traditional diagnostic methods, such as vibration, thermographic, and electromagnetic analyses, often lack adaptability and pre-dictive capabilities, limiting their ability to proactively identify faults under variable operating conditions. The digital twin concept, a virtual representation of physical assets synchronized with real-time sensor data, offers a transformative approach to technical condition monitoring. This paper reviews the state of diagnostic methods for electric mo-tors and evaluates the integration of digital twins to enhance diagnostic accuracy and pre-dictive maintenance. By leveraging platforms like Ansys Twin Builder and MATLAB/Simulink, digital twins enable real-time simulation, fault detection, and opera-tional optimization. The study proposes a novel methodology for diagnosing electric motor conditions using digital twins, incorporating mathematical modeling and real-time signal processing. Key findings include improved fault detection accuracy (MAE &lt; 2.5%, RMSE &lt; 3.1%) and the ability to simulate typical defects like rotor imbalance and insula-tion breakdown. The results demonstrate the potential of digital twins to revolutionize condition-based and predictive maintenance, offering scalable solutions for industrial applications. Future prospects include integrating machine learning for adaptive diagnos-tics and expanding digital twin applications to complex electromechanical systems.

Chapter 3 - Five-Dimension Digital Twin Modeling and Its Key Technologies

Hybrid knowledge based system supporting Digital Twins in the Industry 5.0

With the developments and applications of the advanced information technologies such as cloud computing, internet of thing, artificial intelligence and virtual reality, industry 4.0 and smart manufacturing era are coming. In this respect, one of the specific challenges is to achieve a connection of physical resources on the shop floor with virtual resources, for real-time response, real time process optimization, and simulation, which is merged by big data problem. In this respect, Digital Twins (DT) concept is introduced as a key technology, which includes physical resources, virtual resources, service system, and digital twin data. DT considers current condition of physical resource and prediction of future events to make a responsive decision. However, due to the complexity of building a digital equivalent in virtual space to its physical counterpart, very little applications have been developed with this purpose, especially in the industrial manufacturing area. Therefore, the types of data and technology required to build the DT for a manufacturing system are presented in this work, trying to develop a framework of DT based manufacturing system, which is supported by the virtual reality for virtualization of physical resources.

Geometric parameter updating in digital twin of built assets: A systematic literature review