Cyber-physical Production Systems Research Articles

Deterministic Network–Computation–Manufacturing Interaction Mechanism for AI-Driven Cyber–Physical Production Systems

Deterministic Network–Computation–Manufacturing Interaction Mechanism for AI-Driven Cyber–Physical Production Systems

An Internet of Things-Based Production Scheduling for Distributed Two-Stage Assembly Manufacturing with Mold Sharing

In digital product and ion scheduling centers, order–factory allocation, factory–mold allocation, and mold routing can be performed centrally and efficiently to maximize the utilization of manufacturing resources (molds). Therefore, in this paper, a manufacturing resource (molds)-sharing mechanism based on the Internet of Things (IoT) and a cyber-physical production system (CPPS) is designed to realize the coordinated allocation of molds and production scheduling. A mixed-integer mathematical model is developed to optimize the cost structure and obtain a reasonable profit solution. A heuristic algorithm based on evolutionary reversal is used to solve the problem. The numerical results show that based on the digital coordinated production scheduling method, distributed two-stage assembly manufacturing with shared molds can effectively reduce the order delay time and increase potential benefits for distributed production enterprises.

Autonomous Agent-Based Adaptation of Energy-Optimized Production Schedules Using Extensive-Form Games

Modular cyber-physical production systems are an important paradigm of Industry 4.0 to react flexibly to changes. The flexibility of those systems is further increased with skill-based engineering and can be used to adapt to customer requirements or to adapt manufacturing to disturbances in supply chains. Further potential for application of these systems can be found in the topic of electrical energy supply, which is also characterized by fluctuations. The relevance of energy-optimized production schedules for manufacturing systems in general becomes more important with the increased use of renewable energies. Nevertheless, it is often difficult to adapt when short-term energy price updates or unforeseen events occur. To address these challenges with an autonomous approach, this contribution focuses on extensive-form games to adapt energy-optimized production schedules in an agent-based manner. The paper presents agent-based modeling to transform and monitor energy-optimized production schedules into game trees to respond to changing energy prices and disturbances in production. The game is setup with a scheduler agent and energy agents who are considered players. The implementation of the mechanism is presented in two use cases, realizing decision making for an energy price update in a simulation example and for unforeseen events in a real-world demonstrator.

Leveraging Digital Twin Technology for Enhanced Cybersecurity in Cyber–Physical Production Systems

Leveraging Digital Twin Technology for Enhanced Cybersecurity in Cyber–Physical Production Systems

Exploring hidden pathways to sustainable manufacturing for cyber-physical production systems

Future manufacturing scenarios will likely be built around cyber-physical production systems. To succeed, this new manufacturing paradigm will also have to comply with the golden rule of sustainability. However, the concept of sustainability as defined in a number of high-level policy documents and recommendations requires disambiguation. The paper introduces HITECS, a novel, context-independent text analytics methodology for hidden correlation analysis in documents. HITECS is based on the assumption that there is a strong link between a concept and the words implicitly chosen to explain it. The analysis is based on the combination of bare words frequency and cosine similarity, excluding trivial, first-level terms (titles, keywords, and definitions). Processing a corpus of generally accepted documents related to various definitions and requirements of sustainability unfolded their hidden correlations and some common key concepts. These results indicate that terms like access, inclusion, global, change, together with others like resource, share, and integration, are among leading concepts in the high-level documents discussing the requirements of sustainability. A similar analysis in the domain of cyber-physical production systems shows strong conceptual overlaps but also gaps indicating pathways for future research and actions.

Monitoring manufacturing systems using AI: A method based on a digital factory twin to train CNNs on synthetic data

Modern cyber–physical production systems provide advanced solutions to enhance factory throughput and efficiency. However, monitoring its behaviour and performance becomes challenging as the complexity of a manufacturing system increases. Artificial Intelligence (AI) provides techniques to manage not only decision-making tasks but also to support monitoring. The integration of AI into a factory can be facilitated by a reliable Digital Twin (DT) that enables knowledge-based and data-driven approaches. While computer vision and convolutional neural networks (CNNs) are crucial for monitoring production systems, the need for extensive training data hinders their adoption in real factories. The proposed methodology leverages the Digital Twin of a factory to generate labelled synthetic data for training CNN-based object detection models. Regarding their position and state, the focus is on monitoring entities in manufacturing systems, such as parts, components, fixtures, and tools. This approach reduces the need for large training datasets and enables training when the actual system is unavailable. The trained CNN model is evaluated in various scenarios, with a real case study involving an industrial pilot plant for repairing and recycling Printed Circuit Boards (PCBs).

Variability modeling of products, processes, and resources in cyber–physical production systems engineering

Cyber-Physical Production Systems (CPPSs), such as automated car manufacturing plants, execute a configurable sequence of production steps to manufacture products from a product portfolio. In CPPS engineering, domain experts start with manually determining feasible production step sequences and resources based on implicit knowledge. This process is hard to reproduce and highly inefficient. In this paper, we present the Extended Iterative Process Sequence Exploration (eIPSE) approach to derive variability models for products, processes, and resources from a domain-specific description. To automate the integrated exploration and configuration process for a CPPS, we provide a toolchain which automatically reduces the configuration space and allows to generate CPPS artifacts, such as control code for resources. We evaluate the approach with four real-world use cases, including the generation of control code artifacts, and an observational user study to collect feedback from engineers with different backgrounds. The results confirm the usefulness of the eIPSE approach and accompanying prototype to straightforwardly configure a desired CPPS.

Model-based Trustworthiness Evaluation of Autonomous Cyber-Physical Production Systems: A Systematic Mapping Study

The fourth industrial revolution, i.e., Industry 4.0, is associated with Cyber-Physical Systems (CPS), which are entities integrating hardware (e.g., smart sensors and actuators connected through the Industrial Internet of Things) together with control and analytics software used to drive and support decisions at several levels. The latest developments in Artificial Intelligence (AI) and Machine Learning (ML) have enabled increased autonomy and closer human-robot cooperation in the production and manufacturing industry, thus leading to Autonomous Cyber-Physical Production Systems (ACPPS) and paving the way to the fifth industrial revolution (i.e., Industry 5.0). ACPPS are increasingly critical due to the possible consequences of their malfunctions on human co-workers, and therefore, evaluating their trustworthiness is essential. This article reviews research trends, relevant attributes, modeling languages, and tools related to the model-based trustworthiness evaluation of ACPPS. As in many other engineering disciplines and domains, model-based approaches, including stochastic and formal analysis tools, are essential to master the increasing complexity and criticality of ACPPS and to prove relevant attributes such as system safety in the presence of intelligent behaviors and uncertainties.

Automated assembly of products by a robot-manipulator with dynamometric control of screw joint tightening

In this work, we develop a conceptual scheme for a robotic complex to perform the installation of parts and their fastening using threaded joints by a robot manipulator. A test bench was created on the basis of a KUKA KR6 R900 industrial robot-manipulator. The robot control software was implemented using the KUKA Robot Language. The proposed actuators are the authors' original development. Two variants of the actuator with screw tightening control are proposed. The first actuating device uses the rotational motion of the robot hand flange to tighten the screws. The second actuating device is equipped, on one side, with a gripper for mounting parts on the product and, on the other side, with a drive tool with a predetermined tightening torque limit. It is shown that both actuating devices ensure a complete cycle of screwing a fastener into a workpiece, from engaging to tightening with the required torque. In the first device, the tightening force is controlled with a strain gauge, the signal from which is processed by an Arduino Mini microcontroller located in a rotating device. The signal is forwarded wirelessly to a stationary controller that sends a stop signal to the robot. It was experimentally established that, due to the presence of the wireless interface, some delay is observed between reaching the torque limit value and stopping the robot rotation during signal transmission. As a result, the value of the actually reached torque may exceed the set value by 60%. In the second device, where torque limitation is based on the current in the drive motor, the absolute error of the torque setting does not exceed 0.8 N·m in the range from 0 to 25 N·m or 3.03% (the error of standard torque wrenches is about 4%). In order to meet the requirements of state-of-the-art cyber-physical production systems, the proposed complex should be complemented with intelligent functions of controlling the process of tightening screw joints on the basis of machine learning methods.

Unsupervised Correlation- and Interaction-Aware Anomaly Detection for Cyber-Physical Production Systems based on Graph Neural Networks

Anomaly detection is essential for realising state-of-the-art and safe cyber-physical production systems. With the early detection of possible anomalies, the rise and the carryover of a failure throughout the entire manufacture can be prevented. Current anomaly detection approaches use sensor data from the live system only. Therefore, many important characteristics, interactions, and correlations within the system are neglected. Graphs open a particular way of modelling cyber-physical production systems, while at the same time, they allow the inclusion of a wider variation and variety of data about the system. In this study, we introduce an unsupervised correlation- and interaction-aware anomaly detection concept for cyber-physical production systems based on graph neural networks. We define a concept that allows modelling the entire system as a graph, including external knowledge. We introduce a reconstruction-based graph neural network to detect and analyse the anomalies in these graph structures. The concept is evaluated in a real industrial cyber-physical production system. The test results confirm that the presented concept can be applied to detect anomalies while concurrently considering the correlations and interactions of the system.

Towards Holistic Interoperability of Cyber-Physical Production Systems within RAMI 4.0

The growing prominence of Industry 4.0 necessitates the increased utilization and complexity of Cyber-Physical Production Systems (CPPS). However, challenges persist in the systematic application of the RAMI 4.0 reference architecture for CPPS and the lack of standardization. To address these issues, we propose a novel process-based methodology leveraging RAMI 4.0 for analyzing, evaluating, and enhancing system interoperability within CPPS. By examining two exemplary CPPS in this study, we demonstrate the significance of minimizing interfaces and adaptations. The results reveal a reduction in required hardware, interfaces, information, and protocols between the systems. Our findings contribute to the advancement of standardized approaches for achieving holistic interoperability among individual systems within the RAMI 4.0 framework.

Towards ultra-flexibility: a framework for evaluating the cyber-physical continuum in flexible production systems

Flexibility is often cited as a desirable key characteristic of modern production systems. In ultra-flexible production, machinery and layouts are in a constant state of adaptation to accommodate changing orders, varying products, or evolving conditions. Cyber-physical integration has been proposed as a potential approach to increasing system flexibility with Cyber-Physical Production Systems (CPPS) and Digital Twins (DT) as central concepts. While numerous architectures, frameworks and approaches have been proposed for CPPS and DT development, further research is motivated regarding the development of a requirement-based framework that links together the high-level system property of flexibility and lower-level system components, enabling the analysis, prescription and comparison of systems. Such a framework could enable manufacturers to continuously evaluate and improve manufacturing systems’ flexibility as well as make informed design decisions. Ultimately enhancing system flexibility and responsiveness to changing production conditions. This study aims to initiate the development and formulation of such a requirements-based framework linking flexibility and lower-level system components. Additionally, it seeks to introduce the concept of a ”cyber-physical continuum,” which the study aims to define as a potential quantifiable indicator reflecting flexibility within production systems. This is achieved by leveraging prior CPPS research based on high-level system requirements. These requirements were expanded by branching each requirement into lower-level components creating a more granular scope and providing a finer lens for analysis and assessment. The framework was then applied to assess a high-mix, low-volume manufacturing scenario. Application of the preliminary framework in the case study indicates its potential utility in providing a useful view of the cyber-physical content of a system. Moreover, it serves as a valuable guide for pinpointing areas for improvement and development. By developing a framework that seamlessly links high-level flexibility requirements with detailed implementation requirements, systems can be comprehensively evaluated, methodically prescribed, and effectively compared. As future work, further refinement and validation of this framework will be crucial to ensuring its validity and applicability across diverse manufacturing contexts.

Digital twin architecture for assembly line performance monitoring

The forthcoming industrial requirements to ensure increasingly flexible and agile production processes will require an ever-increasing ability to recognise, predict and optimise the state of processes with respect to the planned state. Advanced tools such as Digital Twins (DT) and Cyber Physical Systems (CPS) can help manage and address these problems. This paper presents some results of the authors’ research on the adoption of a basic methodology for the design and implementation of Digital Twins aimed at manufacturing applications and subsequent integration into a Cyber Physical Production Systems (CPPS). Reference publications were selected based on the level of detail of DT and CPS architectures. The aim is also to combine methodological development with industrial tools and requirements. The architecture is potentially applicable to different production scenarios. Finally, the first results of application on a scale production line are shown.

In-line parameters optimization of plastic injection molding process in the context of disrupted supply chains

Recent social, healthcare, and geopolitical events have caused major disruptions to global supply chains, leading to significant negative consequences on the availability and cost of raw materials for various industries. The injection molding sector has been significantly impacted, with supply chain disruptions resulting in reduced availability of plastic granules and overall increases in raw material costs. To overcome these challenges, plastic component manufacturers need to optimize their material validation process to make the most efficient use of available materials. This article proposes a fully automatic solution for optimizing plastic component production in the context of disrupted supply chains, leveraging a Cyber-Physical Production Systems (CPPS) composed by a Cobot, an automatic guided vehicle, an injection molding machine, and a test bench for plastic components. The paper details the system architecture, implementation, and experimental results, demonstrating the effectiveness of the proposed approach. The results show that the CPS-enabled manufacturing system can successfully adapt to changes in material availability, increase production efficiency, and reduce waste. The proposed approach offers a promising solution for the challenges posed by disrupted supply chains in various manufacturing contexts and with different granulates and products.

Development of a Human Centric Cyber Physical Production System Framework for Enhanced Social Sustainability

Social sustainability focuses on building a sustainable workplace that prioritizes the occupational health, safety, and overall well-being of workers. It is considered one of the three fundamental pillars of sustainability. Human centric cyber physical production system (CPPS) emphasizes the central role of humans in the smart manufacturing process that has become an essential requirement to enhance social sustainability. This paper proposes a human centric CPPS framework for enhanced social sustainability. The social needs/requirements are identified and categorized into various types. Similarly, functional and design requirements are categorized into different elements and sub-elements of CPPS. The findings are used to create a QFD (Quality Function Deployment) matrix that integrates social requirements with the functional and design requirements of modular CPPS elements. The present work will be significant in enhancing the management capabilities and performance of traditional manufacturing systems, while also meeting diverse social needs and requirements.

Methods and models for substantiating application scenarios for the digitalization of manufacturing and business processes of network enterprises

The process of digital transformation of enterprises is associated with the organization of manufacturing and business processes within the framework of selected types of business models and digital platforms, the distribution and economic substantiation of the roles of participants in network interactions, and ensuring the semantic interoperability of their interaction. Currently, certain experience has been accumulated in the implementation of modern business models for the digital transformation of enterprises which is reflected in the concepts of the Industrie 4.0, the Industrial Internet of Things, the creation of cyber-physical production systems, smart enterprises and intelligent manufacturing. At the same time, the issues of conceptual modeling of the architecture of digital enterprises, which determines the construction of manufacturing and business processes, and its economic substantiation depending on various factors of the external environment and internal economic potential have not yet been sufficiently researched and developed. All of the foregoing determines the relevance of the work presented here. The purpose of the study was to develop ontological and economic methods for substantiating application scenarios for the digitalization of manufacturing and business processes depending on the selected types of business models and digital platforms. To solve the problem, methods of classification, ontological engineering, activity-based costing and analysis of cash flows of income and expenses are used. The article presents an analysis of enterprise digitalization scenarios depending on the types of manufacturing and business processes, the types of business models and digital platforms used. An ontological model of enterprise digital transformation has been constructed, providing a choice of application scenarios for the digitalization of manufacturing and business processes for various types of business models and digital platforms. An economic model is proposed to justify options for constructing application scenarios for the digitalization of production and business processes depending on the distribution of roles of participants in network interaction using methods of activity-based costing and cash flow analysis.

A component-based design approach for energy flexibility in cyber-physical manufacturing systems

AbstractEnergy flexibility of manufacturing systems helps to meet sustainable manufacturing requirements and is getting significant importance with rising energy prices and noticeable climate changes. Considering the need to proactively enable energy flexibility in modern manufacturing systems, this work presents a component-based design approach that aims to embed energy flexibility in the design of cyber-physical production systems. To this end, energy management using Industry 4.0 technologies (e.g., Internet of Things and Cyber-physical Systems) is compared to the literature on energy flexibility in order to evaluate to what extent the energy flexibility practice takes advantage of Industry 4.0 technologies. Another dimension is the coverage of the life cycle of the manufacturing system which guarantees its sustainable design and the ability to achieve energy flexibility by configuring the energy consumption behaviour. A data-based design approach of the energy-flexible components is proposed in the spirit of the Reference Architectural Model Industrie 4.0 (RAMI 4.0), and then it is exemplified using an electric drive (as a component) in order to show the practical applicability of the approach. The energy consumption behaviour of the component is modelled using machine learning techniques. The digital twin of the studied component is developed using Visual Components virtual engineering environment, then its energy consumption behaviour is included in the model allowing the system integrator/decision-maker to configure the component based on the energy availability/price. Finally, external services in terms of an optimisation module and a deep learning module are connected to the digital twin.

Component integration manufacturing middleware for customized production

The cyber-physical production system requires continuous effort to integrate heterogeneous resources and code with frequent changes in components to support customized production for personalized consumer needs. First, we introduce the cloud-native concept to build component integration manufacturing middleware, to realize the unity of software and hardware components, including application, service, model, data, workflow, etc. On the edge and cloud, node services are deployed in containers to form a service mesh; microservices are orchestrated in the middleware; continuous integration and deployment are used at the frontground to design and produce. Second, by elaborating on the specific process of using the middleware for design and production, the improvement of the flexibility of customized production is demonstrated from three aspects: product, process, and resource. Last, the proposed approach is evaluated by building a customized production platform according to the middleware design concept. According to the need for different types of flexibility, corresponding experiments were designed and further verified. Experimental results show that the proposed middleware design approach can provide multiple flexibility for the production system, enabling the cyber-physical production system to support customized production.

Design of Experiments to Compare the Mechanical Properties of Polylactic Acid Using Material Extrusion Three-Dimensional-Printing Thermal Parameters Based on a Cyber-Physical Production System.

The material extrusion 3D printing process known as fused deposition modeling (FDM) has recently gained relevance in the additive manufacturing industry for large-scale part production. However, improving the real-time monitoring of the process in terms of its mechanical properties remains important to extend the lifespan of numerous critical applications. To enhance the monitoring of mechanical properties during printing, it is necessary to understand the relationship between temperature profiles and ultimate tensile strength (UTS). This study uses a cyber-physical production system (CPPS) to analyze the impact of four key thermal parameters on the tensile properties of polylactic acid (PLA). Layer thickness, printing speed, and extrusion temperature are the most influential factors, while bed temperature has less impact. The Taguchi L-9 array and the full factorial design of experiments were implemented along with the deposited line's local fused temperature profile analysis. Furthermore, correlations between temperature profiles with the bonding strength during layer adhesion and part solidification can be stated. The results showed that layer thickness is the most important factor, followed by printing speed and extrusion temperature, with very close influence between each other. The lowest impact is attributed to bed temperature. In the experiments, the UTS values varied from 46.38 MPa to 56.19 MPa. This represents an increase in the UTS of around 17% from the same material and printing design conditions but different temperature profiles. Additionally, it was possible to observe that the influence of the parameter variations was not linear in terms of the UTS value or temperature profiles. For example, the increase in the UTS at the 0.6 mm layer thickness was around four times greater than the increase at 0.4 mm. Finally, even when it was found that an increase in the layer temperature led to an increase in the value of the UTS, for some of the parameters, it could be observed that it was not the main factor that caused the UTS to increase. From the monitoring conditions analyzed, it was concluded that the material requires an optimal thermal transition between deposition, adhesion, and layer solidification in order to result in part components with good mechanical properties. A tracking or monitoring system, such as the one designed, can serve as a potential tool for reducing the anisotropy in part production in 3D printing systems.

Computational-Intelligence-Based Scheduling with Edge Computing in Cyber-Physical Production Systems.

Real-time performance and reliability are two critical indicators in cyber-physical production systems (CPPS). To meet strict requirements in terms of these indicators, it is necessary to solve complex job-shop scheduling problems (JSPs) and reserve considerable redundant resources for unexpected jobs before production. However, traditional job-shop methods are difficult to apply under dynamic conditions due to the uncertain time cost of transmission and computation. Edge computing offers an efficient solution to this issue. By deploying edge servers around the equipment, smart factories can achieve localized decisions based on computational intelligence (CI) methods offloaded from the cloud. Most works on edge computing have studied task offloading and dispatching scheduling based on CI. However, few of the existing methods can be used for behavior-level control due to the corresponding requirements for ultralow latency (10 ms) and ultrahigh reliability (99.9999% in wireless transmission), especially when unexpected computing jobs arise. Therefore, this paper proposes a dynamic resource prediction scheduling (DRPS) method based on CI to achieve real-time localized behavior-level control. The proposed DRPS method primarily focuses on the schedulability of unexpected computing jobs, and its core ideas are (1) to predict job arrival times based on a backpropagation neural network and (2) to perform real-time migration in the form of human-computer interaction based on the results of resource analysis. An experimental comparison with existing schemes shows that our DRPS method improves the acceptance ratio by 25.9% compared to the earliest deadline first scheme.