Микро-потоки работ: сочетание потоков работ и потоковой обработки данных для поддержки цифровых двойников технологических процессов

Biopharma Is Going Digital … Bit by Bit

Digital manufacturing aims to make manufacturing more productive, resilient, and competitive by improving production efficiency and enhancing product quality. To achieve this, this paper proposes a novel digital twin framework for representing complex industrial machines, materials, and products in manufacturing production lines. In the framework, digital twins comprise a physical twin, a virtual twin, and digital threads interconnecting these. The physical twin incorporates relevant physical entities in manufacturing production lines, such as production machines, a material, or a product, as well as additional attached sensors needed for measuring the properties of the physical twin. The virtual twin, which contains the description of physical twin, such as the product’s properties, and AI models use the measurements collected from the production machine or the sensors in the physical twin to optimize production efficiency and ensure products consistency/quality. The digital threads provide for bidirectional communication using industrial protocols between the physical and virtual entities, and also between the AI model(s) and the orchestration component of the virtual twin. The paper also proposes a digital twin-based platform for digital manufacturing. The platform supports the creation and lifecycle management of digital twins for the production machines, materials, and products in each production line. In addition, the platform for digital manufacturing supports the development and management of digital manufacturing solutions that enhance the productivity and resiliency of entire production lines. The paper presents a case study from the composite airframe manufacturing sector that includes a sample framework-based implementation of a digital twin of an airframe part product. This product digital twin incorporates sensors that measure the temperature and viscosity of the composite product and AI model that used these real-time measurements to predict the product quality and reduce its curing time, ensuring both the product quality and production efficiency.

Digital twins: Representation, Replication, Reality, and Relational (4Rs)

The production of food is highly complex due to the various chemo-physical and biological processes that must be controlled for transforming ingredients into final products. Further, production processes must be adapted to the variability of the ingredients, e.g., due to seasonal fluctuations of raw material quality. Digital twins are known from Industry 4.0 as a method to model, simulate, and optimize processes. In this vision paper, we describe the concept of a digital food twin. Due to the variability of the raw materials, such a digital twin has to take into account not only the processing steps but also the chemical, physical, or microbiological properties that change the food independently from the processing. We propose a hybrid modeling approach, which integrates the traditional approach of food process modeling and simulation of the bio-chemical and physical properties with a data-driven approach based on the application of machine learning. This work presents a conceptual framework for our digital twin concept based on explainable artificial intelligence and wearable technology. We discuss the potential in four case studies and derive open research challenges.

The latest development trend in rolling industry is the combination of various technological operations in continuous production lines. In the production of long products, the combination of rolling and drawing processes looks promising. A wire drawing mill developed by the team of authors of this work belongs to the conceptually new, integrated lines. The creation of new integrated rolling mills requires a research phase, where relevant concepts are scrutinized using the methods of mathematical modeling. This requires the development of digital (Digital Twin) models that reliably describe the technological processes. It seems efficient to create a Digital Twin for individual units, with their subsequent integration into a complex digital model. This approach was applied in the development of models of electrical systems for the new line. Such models should take into account a wide range of real-life physical relationships. At the same time, a three-high continuous train of stands with an idle inter-stand is the least studied technological unit of the new mill. The absence of an electric drive of the middle stand determines the particulars of deformation processes and the stands’ interconnections through the processed metal. To date, a comprehensive study of such objects has not been carried out. Therefore, the task of studying this technological unit is of immediate interest. The presented publication is devoted to the development of digital models of deformation zones of drive stands and idle stands, as well as of their relationship through the processed metal. The task is solved using the example of an operating pilot production line that implements rolling technology with an idle stand. The authors describe individual Digital Twins and present the structure of the complex model of the studied unit. The most important purpose of the model is to use it in the development of a control method for electric drives of stands to ensure the stability of the rolling process. The developed method should provide a reduction in energy consumption due to the use of friction force reserves present in the idle stand. The authors also substantiate the control principle based on continuous monitoring and alignment of critical angles in the deformation zones of the drive stands. The paper describes a structure of the control system and explains the technical implementation of this principle. The results of mathematical modeling and oscillograms of typical transient processes are presented. The advantages provided by implementing the proposed control method are shown. The work provides an indirect confirmation of the adequacy of the model to the physical object. Recommendations are given on the use of the developed Digital Twin in the study of rolling processes on sheet and sectional mills.

Application of artificial intelligence in digital twin models for stormwater infrastructure systems in smart cities

Digital Twins are increasingly being introduced for smart manufacturing systems to improve the efficiency of the main disciplines of such systems. Formal techniques, such as graphs, are a common way of describing Digital Twin models, allowing broad types of tools to provide Digital Twin based services such as fault detection in production lines. Obtaining correct and complete formal Digital Twins of physical systems can be a complicated and time consuming process, particularly for manufacturing systems with plenty of physical objects and the associated manufacturing processes. Automatic generation of Digital Twins is an emerging research field and can reduce time and costs. In this paper, we focus on the generation of Digital Twins for flexible manufacturing systems with Automated Guided Vehicles (AGVs) on the factory floor. In particular, we propose an architectural framework and the associated design choices and software development tools that facilitate automatic generation of Digital Twins for AGVs. Specifically, the scope of the generated digital twins is controlling AGVs in the factory floor. To this end, we focus on different control levels of AGVs and utilize graph theory to generate the graph-based Digital Twin of the factory floor.

Manufacturing as a Service (MAAS) is a promising business model, especially with relatively new technologies such as cloud computing, data integration and digital twins. The article presents the characteristics of MAAS by comparing it to the characteristics of successful Software as a Service (SAAS) solution, which is open, modular, and standardized. It also describes the product, production and network data that MAAS requires to be modelled, managed and shared as a requirement for data modelling. In particular, it focuses on the modelling of product, processes and resources. Among the modelling methods, visual product-process models, matrix methods used to describe system structures, general graphical methods and methods used in system dynamics are briefly discussed. The expressive power of the methods is taken into account, and they are grouped into qualitative and quantitative modelling methods. A case study on metal additive manufacturing is presented, resulting in a generalized model of a key part of the process. The case study results with a model on how the external and internal and output parameters of melt pool influence on the output economic, quality and environmental impact characteristics. Finally, the ability of the modelling methods, the case and the MAAS features are compared. As the model is a tool for interaction between different actors and it needs to be maintained, it is concluded that qualitative and quantitative methods need to be integrated in the case of MAAS.

The past years have witnessed an increasing interest and concern regarding the development of security monitoring and management mechanisms for Critical Infrastructures, due to their vital role in ensuring the availability of many essential services. This task is not easy due to the specific characteristics of such systems, and the natural resistance of Critical Infrastructures operators against actions implying downtime. Digital Twins, as accurate virtual models of physical objects or processes, can provide a faithful environment for security analysis or evaluation of potential mitigation strategies to be deployed in face of specific situations. Nonetheless, their on-premises deployment can be expensive, implying a significant CAPEX whose return will depend on the ability to plan and deploy a suitable support infrastructure, as well as implementing efficient and scalable data collection and processing mechanisms capable of taking advantage of the acquired resources. This paper presents an off-premises approach to design and deploy Digital Twins to secure critical infrastructures, developed in the scope of the ELEGANT project. Such Digital Twins are built using real-time, high fidelity replicas of Programming Logic Controllers, coupled with scalable and efficient data collection processes, supporting the development and validation of Machine Learning models to mitigate security threats like Denial of Service attacks. The validation approach of ELEGANT, which leveraged from the capabilities of the Fed4Fire federated testbeds evaluated the feasibility of using cloudified Digital Twins, thus converting a significant part of the projected CAPEX for the in-premises model into on-demand, pay-as-you-go OPEX, eventually paving the way for the establishment of a DTaaS (Digital Twin as a Service) paradigm. The achieved results demonstrate that the data pipelines providing support for the ELEGANT Digital Twins have low impact in terms of resource usage in Denial of Service and Distributed Denial of Service attack scenarios, when higher volumes of data are generated.

The integration of discrete simulations, artificial intelligence methods, and the theory of probability in order to obtain a high flexibility of the production system is crucial. In this paper, the concept of a smart factory operation is proposed along with the idea of data exchange architecture, simulation creation, performance optimization, and predictive analysis of the production process conditions. A Digital Twin for a hybrid flow shop from the automotive industry is presented as a case study. In the paper, the Ant Colony Optimization (ACO) algorithm is developed for multi-criteria scheduling problems in order to obtain a production plan without delays and maximum resource utilization. The ACO is compared to the immune algorithm and genetic algorithm. The best schedules are achieved with low computation time for the Digital Twin. By predicting the reliability parameters of the limited resources of the Digital Twin, stable deadlines for the implementation of production tasks are achieved. Mean Time To Failure and Mean Time of Repair are predicted for a real case study of an electric steering gear production line. The presented integration and data exchange between the elements of the smart factory: a Digital Twin, a computing module including an optimization, prediction, and simulation methods fills the gap between theory and practice for Industry 4.0. The paper presents measurable benefits of integration of discrete simulation tools, historical data analysis, and optimization methods.

While large enterprises are actively preparing for digital transformation by leveraging technologies such as digital twins, smaller companies face challenges due to economic constraints and market uncertainties, leading to a relative lack of awareness and readiness.To address this situation, this study proposes a digital twin development framework tailored for small and medium-sized enterprises (SMEs).This framework utilizes attachable IoT devices for real-time collection of manufacturing data and leverages public server systems for data management.Moreover, it enables the refinement and optimization of digital twins by training machine learning models on collected data.Additionally, the framework includes the integration of simulation models and machine learning models for comprehensive digital twin modelling.Finally, the paper suggests a process for applying and validating this framework in real manufacturing companies, demonstrating the effects of digital twin implementation on productivity enhancement in the production lines of two SMEs.

At automotive manufacturing sites, meeting the delivery schedule is difficult owing to the occurrence of unpredictable abnormal scenarios such as product defects and equipment failures. To overcome this, manufacturing technologies developed as part of the Fourth Industrial Revolution are employed to meet the delivery schedule set by the customer. We propose a digital twin (DT)–based cyber-physical system (CPS) that can predict whether a product can be manufactured as per the schedule requested by a customer at an automotive body production line where abnormal scenarios occur. We designed a product, process, plan, plant, and resource information model for automotive body production lines; the proposed DT employs this model. Unlike in previous research on DTs focusing on independent engineering application development, we designed and implemented a CPS combined with a DT and other components for a Web-based integrated manufacturing platform. To the best of our knowledge, this is the first time a DT-based CPS is implemented for abnormal scenarios involving automotive body production lines; the capability of the proposed system was verified via experiments. The experimental results indicate that the proposed system achieved an average prediction performance of 96.83% for the actual production plan. We confirmed that the DT-based CPS can be applied to automotive body production lines, and it provides an advanced solution to predict whether production is possible according to the production plan.

Background A production line is the basic unit of smart factories and smart manufacturing. However, owing to the development of the industrial Internet of Things, sensors, and other technologies, more data are being collected, leading to a data explosion, and the heterogeneous nature of multiple sources makes it difficult to manage data in a unified manner. Methods A production line data collection, storage, and management system based on cloud-fog-edge computing collaboration and a digital twin was designed. Multi-source heterogeneous data were collected and transmitted based on the OPC UA, and an information model of the production line was established. Modules for data mapping, publishing, and receiving were developed to achieve unified data collection and transmission. The data storage and management platform was constructed by front-end and back-end separation technologies. Results The developed data collection and management system was verified for functionality and performance on a digital twin production line. Functional tests show that the system has the functions of data acquisition and transmission, device addition and viewing, device data querying and downloading, data and model visualization, and user rights setting. The average time for edge data collection and transmission is 183.6ms. The average response time of the cloud for fog requests is less than 1s. This shows that the system can satisfy the real-time requirements of a digital twin production line. Conclusions The proposed system is real-time and stable, providing support for big data and virtual-reality interaction in digital twins.

Beside all the challenges regarding climate change, resources scarcity and quality degradation of deposits, the mining industry is becoming an environment that is constantly under pressure and restrictive. The increasing of raw materials prices, the unstable and high volatile commodity prices, the decreasing ore grades and the rising energy cost have shown a clinical impact on the mining sector. One way to mitigate the variability caused by these external forces is to take advantage of the latest advanced information technologies and set up an innovative strategy to optimise the processing cost. A key enabler for the optimisation of the mineral processing value chain and for the digital disruption of the mining sector is the Digital Twin. Digital Twin encompasses digital models of the production models enabling a virtual representation of a physical system and ensuring a continuous real time interaction, correction, control and optimisation. Consequently, the Digital Twin could afford an alleviation of the mineral processing variability in terms of mineralogy, final product’s grades, mechanical setting and processing configuration. This topic is a part of the Moroccan national project “Smart Connected Mine” that arose after the consortium of industrials and researchers for the digital transformation of the mining industry. In this paper, the background of the Digital Twin, its types and the major misconceptions about it are presented. The values, challenges of the implementation of such concept and its key enablers technologies are highlighted. Also an architectural framework for the Digital Twin implementation in a mineral processing plant is proposed and the modeling approaches are discussed.KeywordsDigital twinDisruptive technologySmart control and supervisionDigital transformationMineral processingInnovationIndustry 4.0

In the face of ever-increasing complexity and global uncertainty, today’s industries are under immense pressure to develop adaptive and resilient production models. The ability to effectively manage and respond to disruptions has become not only a competitive advantage but an operational necessity. Digital Twins enables the creation of a virtual, real-time model of physical assets and processes. Through continuous data collection, a Digital Twins accurately mirrors the state and behaviour of machines, workflows, and supply chains, allowing companies to monitor, analyse, and predict operational conditions as they evolve. This research centres on a case study within the fashion industry, exploring the practical application of Digital Twins to manage and mitigate disruptions in mixed-model production environments. This work contributes to the growing body of knowledge on Digital Twin technology, emphasizing its potential as a tool for immediate operational resilience.