Emmanouil Bakopoulos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Emmanouil Bakopoulos has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Kosmas Alexopoulos
University of Patras
8 shared publications - Panagiotis Mavrothalassitis
University of Patras
5 shared publications - Nikolaos Nikolakis
Laboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, Greece
4 shared publications - Vasilis Siatras
Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece
4 shared publications Adrian Jacob
Digital Production Twin, Fraunhofer Institute for Machine Tools and Forming Technology IWU, Dresden, Saxony, 01187, Germany
1 shared publication- Alexander Dementjev
Digital Production Twin, Fraunhofer Institute for Machine Tools and Forming Technology IWU, Dresden, Saxony, 01187, Germany
1 shared publication
Latest Publications
- Open Access
- 19 November 2026
- Published by Springer Nature
- p. 206-214
Large Language Models in Production Planning and Scheduling: A System Architecture for Query Handling and Model Comparison
- 19 November 2026
- Published by Springer Nature
- p. 206-214
Open AccessLarge Language Models in Production Planning and Scheduling: A System Architecture for Query Handling and Model Comparison
- Open Access
- 7 August 2026
- Published by CERN in Open Research Europe
Achieving resilience through reconfigurability: The role of digitisation for improved strategy and decision-making for EU manufacturing industries
This article examines how digitization can support resilience in European Union manufacturing by enabling reconfigurability at the levels of the supply chain, factories, systems, and workstations. In light of recent disruptions, such as the Coronavirus Disease 2019 (COVID-19) pandemic, geopolitical instability, energy price volatility, and material shortages, the paper conceptualizes resilience as a staged capability that encompasses shock absorption, adaptation, and transformation. The paper argues that manufacturing resilience depends not only on robust planning, but also on the ability to rapidly reconfigure processes, resources, and decision pathways in volatile, uncertain, complex, and ambiguous conditions. Using evidence from three Horizon Europe projects, the study presents a practice-oriented analysis of how digital tools can strengthen resilience in diverse industrial settings. The paper reviews pilot and demonstration cases in sectors including steel, textiles, plastics, automotive, medical products, and precision manufacturing. It also maps disturbances according to their likelihood, severity, and operational level. The paper highlights a portfolio of digital solutions, including digital twins, AAS-based integration, federated data spaces, resilience assessment services, production scheduling tools, supply chain digital twins, human assistance systems, and an AI-based early detection tool for identifying weak signals. The article shows how these tools can support a workflow for building digital resilience that includes identifying risks, anticipating them, assessing scenarios, and reconfiguring operations. The findings across the cases indicate that the effectiveness of digital resilience strategies depends on connecting data and decisions across organizational layers, improving interoperability, and addressing persistent barriers, such as legacy systems, fragmented data environments, and limited digital maturity — especially among small and medium-sized enterprises. Overall, the paper provides a practical framework for understanding how digitization can improve preparedness and responsiveness in manufacturing. It emphasizes that resilience is context-dependent, resource-intensive, and influenced by organizational and technical capabilities.
- 7 August 2026
- Published by CERN in Open Research Europe
Open AccessAchieving resilience through reconfigurability: The role of digitisation for improved strategy and decision-making for EU manufacturing industries
This article examines how digitization can support resilience in European Union manufacturing by enabling reconfigurability at the levels of the supply chain, factories, systems, and workstations. In light of recent disruptions, such as the Coronavirus Disease 2019 (COVID-19) pandemic, geopolitical instability, energy price volatility, and material shortages, the paper conceptualizes resilience as a staged capability that encompasses shock absorption, adaptation, and transformation. The paper argues that manufacturing resilience depends not only on robust planning, but also on the ability to rapidly reconfigure processes, resources, and decision pathways in volatile, uncertain, complex, and ambiguous conditions. Using evidence from three Horizon Europe projects, the study presents a practice-oriented analysis of how digital tools can strengthen resilience in diverse industrial settings. The paper reviews pilot and demonstration cases in sectors including steel, textiles, plastics, automotive, medical products, and precision manufacturing. It also maps disturbances according to their likelihood, severity, and operational level. The paper highlights a portfolio of digital solutions, including digital twins, AAS-based integration, federated data spaces, resilience assessment services, production scheduling tools, supply chain digital twins, human assistance systems, and an AI-based early detection tool for identifying weak signals. The article shows how these tools can support a workflow for building digital resilience that includes identifying risks, anticipating them, assessing scenarios, and reconfiguring operations. The findings across the cases indicate that the effectiveness of digital resilience strategies depends on connecting data and decisions across organizational layers, improving interoperability, and addressing persistent barriers, such as legacy systems, fragmented data environments, and limited digital maturity — especially among small and medium-sized enterprises. Overall, the paper provides a practical framework for understanding how digitization can improve preparedness and responsiveness in manufacturing. It emphasizes that resilience is context-dependent, resource-intensive, and influenced by organizational and technical capabilities.
- Open Access
- 26 May 2026
- Published by Springer Nature
- p. 67-76
Resilient Manufacturing Through Data Spaces: Leveraging IDS and Gaia-X in a Compute-on-Demand Environment
Resilience is increasingly critical in modern manufacturing, especially within complex supply chains. Information sharing based on data sovereignty principles enables informed, timely decisions, improving supply chain resilience. Data space technologies, like International Data Spaces (IDS) and Gaia-X, support secure, multi-stakeholder data sharing. This work integrates IDS and Gaia-X data spaces into a data spaces framework for resilience (DSF4R). The framework facilitates secure data exchange using a compute on demand environment, ensuring data remains secure within the provider’s system while enabling external services to process it. This eliminates the need for data transfer, ensuring privacy and compliance. Applied in a real-world industrial use case from the steel industry sector, it demonstrates enhanced resilience and broader applicability.
- 26 May 2026
- Published by Springer Nature
- p. 67-76
Open AccessResilient Manufacturing Through Data Spaces: Leveraging IDS and Gaia-X in a Compute-on-Demand Environment
Resilience is increasingly critical in modern manufacturing, especially within complex supply chains. Information sharing based on data sovereignty principles enables informed, timely decisions, improving supply chain resilience. Data space technologies, like International Data Spaces (IDS) and Gaia-X, support secure, multi-stakeholder data sharing. This work integrates IDS and Gaia-X data spaces into a data spaces framework for resilience (DSF4R). The framework facilitates secure data exchange using a compute on demand environment, ensuring data remains secure within the provider’s system while enabling external services to process it. This eliminates the need for data transfer, ensuring privacy and compliance. Applied in a real-world industrial use case from the steel industry sector, it demonstrates enhanced resilience and broader applicability.
- Open Access
- 26 May 2026
- Published by Springer Nature
- p. 57-66
Enhancing Resilience in Smart Manufacturing: A Method for Connected Machine Networks
Resilience in production environments is defined as the system’s ability to avoid, adapt, and rapidly recover from disruptive events, attaining normal operational conditions with minimal time and financial investment. Current methods lack the capability to quantify risks based on real-time data from production devices, creating a critical gap. This article presents a novel method aimed at enhancing resilience by integrating data from micro and meso levels within precision machining production plants. By utilizing real-time monitoring data, from machines and production processes, the proposed approach is based on the assessment of risks of failure of machines and early detection of anomalies in machining processes, to support decision-making. Leveraging the Industrial Internet of Things (IIoT), the method collects and analyses real-time machines and machining process data for risk assessment and early anomaly detection. The proposed method minimizes the impact of unexpected failures by incorporating failure risk calculations into plant-level decision-making. Validation of the method was conducted using a milling machine in a controlled laboratory setting, demonstrating the significance of real-time data and health assessment in developing resilient industrial systems. Preliminary results indicate strong potential for industrial application, with the next step being implemented in a production plant.
- 26 May 2026
- Published by Springer Nature
- p. 57-66
Open AccessEnhancing Resilience in Smart Manufacturing: A Method for Connected Machine Networks
Resilience in production environments is defined as the system’s ability to avoid, adapt, and rapidly recover from disruptive events, attaining normal operational conditions with minimal time and financial investment. Current methods lack the capability to quantify risks based on real-time data from production devices, creating a critical gap. This article presents a novel method aimed at enhancing resilience by integrating data from micro and meso levels within precision machining production plants. By utilizing real-time monitoring data, from machines and production processes, the proposed approach is based on the assessment of risks of failure of machines and early detection of anomalies in machining processes, to support decision-making. Leveraging the Industrial Internet of Things (IIoT), the method collects and analyses real-time machines and machining process data for risk assessment and early anomaly detection. The proposed method minimizes the impact of unexpected failures by incorporating failure risk calculations into plant-level decision-making. Validation of the method was conducted using a milling machine in a controlled laboratory setting, demonstrating the significance of real-time data and health assessment in developing resilient industrial systems. Preliminary results indicate strong potential for industrial application, with the next step being implemented in a production plant.
- Open Access
- 26 May 2026
- Published by Springer Nature
- p. 47-56
Resilience Assessment in Steel Manufacturing: Evaluating Disruption Scenarios Using the Penalty of Change Methodology
As manufacturing systems have become more complex, uncertainties and disruptions have increased, where resilience has become essential for manufacturers, in order to ensure production continuity and quick adaptations to disruptions such as equipment failures, supply chain issues, or the introduction of new products. This work presents an approach of assessing resilience in steel manufacturing, using the Penalty of Change (PoC) methodology. Combining PoC with a heuristic scheduling algorithm, the goal is to simulate and evaluate the impact of disruption. Resilience is quantified by measuring the degree of production deviation caused by disruptions such as machinery breakdowns and unplanned orders with high priority. Through a case study of a steel manufacturing plant, the proposed framework offers a clear methodology for assessing resilience and identifying areas for improvement. This study emphasizes the importance of resilience in manufacturing, offering a practical tool for decision-makers to optimize production planning and enhance operational robustness under certain conditions.
- 26 May 2026
- Published by Springer Nature
- p. 47-56
Open AccessResilience Assessment in Steel Manufacturing: Evaluating Disruption Scenarios Using the Penalty of Change Methodology
As manufacturing systems have become more complex, uncertainties and disruptions have increased, where resilience has become essential for manufacturers, in order to ensure production continuity and quick adaptations to disruptions such as equipment failures, supply chain issues, or the introduction of new products. This work presents an approach of assessing resilience in steel manufacturing, using the Penalty of Change (PoC) methodology. Combining PoC with a heuristic scheduling algorithm, the goal is to simulate and evaluate the impact of disruption. Resilience is quantified by measuring the degree of production deviation caused by disruptions such as machinery breakdowns and unplanned orders with high priority. Through a case study of a steel manufacturing plant, the proposed framework offers a clear methodology for assessing resilience and identifying areas for improvement. This study emphasizes the importance of resilience in manufacturing, offering a practical tool for decision-makers to optimize production planning and enhance operational robustness under certain conditions.
- Open Access
- 30 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 232
Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems
Production scheduling is a critical task in the management of manufacturing systems. It is difficult to derive an optimal schedule due to the problem complexity. Computationally expensive and time-consuming solutions have created major issues for companies trying to respect their customers’ demands. Simple dispatching rules have typically been applied in manufacturing practice and serve as a good scheduling option, especially for small and midsize enterprises (SMEs). However, in recent years, the progress in smart systems enabled by artificial intelligence (AI) and machine learning (ML) solutions has revolutionized the scheduling approach. Under different production circumstances, one dispatch rule may perform better than others, and expert knowledge is required to determine which rule to choose. The objective of this work is to design and implement a framework for the modeling and deployment of a deep reinforcement learning (DRL) agent to support short-term production scheduling. The DRL agent selects a dispatching rule to assign jobs to manufacturing resources. The model is trained, tested and evaluated using a discrete event simulation (DES) model that simulates a pilot case from the bicycle production industry. The DRL agent can learn the best dispatching policy, resulting in schedules with the best possible production makespan.
- 30 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 232
Open AccessDeep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems
Production scheduling is a critical task in the management of manufacturing systems. It is difficult to derive an optimal schedule due to the problem complexity. Computationally expensive and time-consuming solutions have created major issues for companies trying to respect their customers’ demands. Simple dispatching rules have typically been applied in manufacturing practice and serve as a good scheduling option, especially for small and midsize enterprises (SMEs). However, in recent years, the progress in smart systems enabled by artificial intelligence (AI) and machine learning (ML) solutions has revolutionized the scheduling approach. Under different production circumstances, one dispatch rule may perform better than others, and expert knowledge is required to determine which rule to choose. The objective of this work is to design and implement a framework for the modeling and deployment of a deep reinforcement learning (DRL) agent to support short-term production scheduling. The DRL agent selects a dispatching rule to assign jobs to manufacturing resources. The model is trained, tested and evaluated using a discrete event simulation (DES) model that simulates a pilot case from the bicycle production industry. The DRL agent can learn the best dispatching policy, resulting in schedules with the best possible production makespan.
- Open Access
- 6 June 2024
- Published by MDPI AG in Information
- Vol. 15 (6) , 337
Production Scheduling Based on a Multi-Agent System and Digital Twin: A Bicycle Industry Case
The emerging digitalization in today’s industrial environments allows manufacturers to store online knowledge about production and use it to make better informed management decisions. This paper proposes a multi-agent framework enhanced with digital twin (DT) for production scheduling and optimization. Decentralized scheduling agents interact to efficiently manage the work allocation in different segments of production. A DT is used to evaluate the performance of different scheduling decisions and to avoid potential risks and bottlenecks. Production managers can supervise the system’s decision-making processes and manually regulate them online. The multi-agent system (MAS) uses asset administration shells (AASs) for data modelling and communication, enabling interoperability and scalability. The framework was deployed and tested in an industrial pilot coming from the bicycle production industry, optimizing and controlling the short-term production schedule of the different departments. The evaluation resulted in a higher production rate, thus achieving higher production volume in a shorter time span. Managers were also able to coordinate schedules from different departments in a dynamic way and achieve early bottleneck detection.
- 6 June 2024
- Published by MDPI AG in Information
- Vol. 15 (6) , 337
Open AccessProduction Scheduling Based on a Multi-Agent System and Digital Twin: A Bicycle Industry Case
The emerging digitalization in today’s industrial environments allows manufacturers to store online knowledge about production and use it to make better informed management decisions. This paper proposes a multi-agent framework enhanced with digital twin (DT) for production scheduling and optimization. Decentralized scheduling agents interact to efficiently manage the work allocation in different segments of production. A DT is used to evaluate the performance of different scheduling decisions and to avoid potential risks and bottlenecks. Production managers can supervise the system’s decision-making processes and manually regulate them online. The multi-agent system (MAS) uses asset administration shells (AASs) for data modelling and communication, enabling interoperability and scalability. The framework was deployed and tested in an industrial pilot coming from the bicycle production industry, optimizing and controlling the short-term production schedule of the different departments. The evaluation resulted in a higher production rate, thus achieving higher production volume in a shorter time span. Managers were also able to coordinate schedules from different departments in a dynamic way and achieve early bottleneck detection.
- Open Access
- 9 February 2024
- Published by Springer Nature
- p. 147-179
Digital-Twin-Enabled Framework for Training and Deploying AI Agents for Production Scheduling
Digital manufacturing tools aim to provide intelligent solutions that will help manufacturing industry adapt to the volatile work environment. Modern technologies such as artificial intelligence (AI) and digital twins (DT) are primarily exploited in a way to simulate and select efficient solutions from a broad range of alternative decisions. This work aims to couple DT and AI technologies in a framework where training, testing, and deployment of AI agents is made more efficient in production scheduling applications. A set of different AI agents were developed, utilizing key optimization technologies such as mathematical programming, deep learning, heuristic algorithms, and deep reinforcement learning are developed to address hard production schedule optimization problems. DT is the pilar technology, which is used to simulate accurately the production environment and allow the agents to reach higher efficiency. On top of that, Asset Administration Shell (AAS) technology, being the pilar components of Industry 4.0 (I4.0), was used for transferring data in a standardized format in order to provide interoperability within the multi-agent system (MAS) and compatibility with the rest of I4.0 ecosystem. The system validation was provided in the manufacturing system of the bicycle industry by improving the business performance.
- 9 February 2024
- Published by Springer Nature
- p. 147-179
Open AccessDigital-Twin-Enabled Framework for Training and Deploying AI Agents for Production Scheduling
Digital manufacturing tools aim to provide intelligent solutions that will help manufacturing industry adapt to the volatile work environment. Modern technologies such as artificial intelligence (AI) and digital twins (DT) are primarily exploited in a way to simulate and select efficient solutions from a broad range of alternative decisions. This work aims to couple DT and AI technologies in a framework where training, testing, and deployment of AI agents is made more efficient in production scheduling applications. A set of different AI agents were developed, utilizing key optimization technologies such as mathematical programming, deep learning, heuristic algorithms, and deep reinforcement learning are developed to address hard production schedule optimization problems. DT is the pilar technology, which is used to simulate accurately the production environment and allow the agents to reach higher efficiency. On top of that, Asset Administration Shell (AAS) technology, being the pilar components of Industry 4.0 (I4.0), was used for transferring data in a standardized format in order to provide interoperability within the multi-agent system (MAS) and compatibility with the rest of I4.0 ecosystem. The system validation was provided in the manufacturing system of the bicycle industry by improving the business performance.
- Open Access
- 9 February 2024
- Published by Springer Nature
- p. 251-263
A Multi-intelligent Agent Solution in the Automotive Component–Manufacturing Industry
The manufacturing industry is an ecosystem full of changes and variations where production conditions are never the same. As an example, the raw materials received from suppliers differ from one another, though within tolerances. And similar variations appear in all areas of manufacturing, such as tool wearing, the statuses of production machines, and even operator decisions.Improvements to production must factor in technical considerations and economic ones. Several points of view must be included to determine the best solution. Even when applying artificial intelligence (AI) in the manufacturing process, the situation should be similar: Several agents with different goals should interact to determine the most holistic solution.This paper presents the ontology, semantics, and architecture that facilitates multiagent interaction. The Reference Architecture Model Industry 4.0, or RAMI 4.0 (RAMI4.0 – 2018 – DE (plattform-i40.de)), has been selected as the basis for this approach.Given that most of the time, the operator’s decision is based on intuition and experience, not based on data analysis, this paper also analyses which data architecture will permit the data analysis of raw materials, finished products, tooling characteristics and statuses, machine parameters, and external conditions, to minimize the influence of intuition and personal bias on decision-making in manufacturing.
- 9 February 2024
- Published by Springer Nature
- p. 251-263
Open AccessA Multi-intelligent Agent Solution in the Automotive Component–Manufacturing Industry
The manufacturing industry is an ecosystem full of changes and variations where production conditions are never the same. As an example, the raw materials received from suppliers differ from one another, though within tolerances. And similar variations appear in all areas of manufacturing, such as tool wearing, the statuses of production machines, and even operator decisions.Improvements to production must factor in technical considerations and economic ones. Several points of view must be included to determine the best solution. Even when applying artificial intelligence (AI) in the manufacturing process, the situation should be similar: Several agents with different goals should interact to determine the most holistic solution.This paper presents the ontology, semantics, and architecture that facilitates multiagent interaction. The Reference Architecture Model Industry 4.0, or RAMI 4.0 (RAMI4.0 – 2018 – DE (plattform-i40.de)), has been selected as the basis for this approach.Given that most of the time, the operator’s decision is based on intuition and experience, not based on data analysis, this paper also analyses which data architecture will permit the data analysis of raw materials, finished products, tooling characteristics and statuses, machine parameters, and external conditions, to minimize the influence of intuition and personal bias on decision-making in manufacturing.
- Open Access
- 23 August 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (17) , 9540
On the Use of Asset Administration Shell for Modeling and Deploying Production Scheduling Agents within a Multi-Agent System
Industry 4.0 (I4.0) aims at achieving the interconnectivity of multiple industrial assets from different hierarchical layers within a manufacturing environment. The Asset Administration Shell (AAS) is a pilar component of I4.0 for the digital representation of assets and can be applied in both physical and digital assets, such as enterprise software, artificial intelligence (AI) agents, and databases. Multi-agent systems (MASs), in particular, are useful in the decentralized optimization of complex problems and applicable in various planning or scheduling scenarios that require the system’s ability to adapt to any given problem by using different optimization methods. In order to achieve this, a universal model for the agent’s information, communication, and behaviors should be provided in a way that is interoperable with the rest of the I4.0 assets and agents. To address these challenges, this work proposes an AAS-based information model for the description of scheduling agents. It allows multiple AI methods for scheduling, such as heuristics, mathematical programming, and deep reinforcement learning, to be encapsulated within a single agent, making it adjustable to different production scenarios. The software implementation of the proposed architecture aims to provide granularity in the deployment of scheduling agents which utilize the underlying AAS metamodel. The agent was implemented using the SARL agent-oriented programming (AOP) language and deployed in an open-source MAS platform. The system evaluation in a real-life bicycle production scenario indicated the agent’s ability to adapt and provide fast and accurate scheduling results.
- 23 August 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (17) , 9540
Open AccessOn the Use of Asset Administration Shell for Modeling and Deploying Production Scheduling Agents within a Multi-Agent System
Industry 4.0 (I4.0) aims at achieving the interconnectivity of multiple industrial assets from different hierarchical layers within a manufacturing environment. The Asset Administration Shell (AAS) is a pilar component of I4.0 for the digital representation of assets and can be applied in both physical and digital assets, such as enterprise software, artificial intelligence (AI) agents, and databases. Multi-agent systems (MASs), in particular, are useful in the decentralized optimization of complex problems and applicable in various planning or scheduling scenarios that require the system’s ability to adapt to any given problem by using different optimization methods. In order to achieve this, a universal model for the agent’s information, communication, and behaviors should be provided in a way that is interoperable with the rest of the I4.0 assets and agents. To address these challenges, this work proposes an AAS-based information model for the description of scheduling agents. It allows multiple AI methods for scheduling, such as heuristics, mathematical programming, and deep reinforcement learning, to be encapsulated within a single agent, making it adjustable to different production scenarios. The software implementation of the proposed architecture aims to provide granularity in the deployment of scheduling agents which utilize the underlying AAS metamodel. The agent was implemented using the SARL agent-oriented programming (AOP) language and deployed in an open-source MAS platform. The system evaluation in a real-life bicycle production scenario indicated the agent’s ability to adapt and provide fast and accurate scheduling results.