Scientific research is one of the key building blocks of the knowlEdge project and enables us to (i) utilize state-of-the-art methods and concepts and (ii) report on our key findings and contributions to the scientific community. The following list will eventually grow over the course of its project and reflect the publicly available scientific progress we made. Each publication includes at least one project member.
2024
Anaya, Victor; Alberti, Enrico; Scivoletto, Gabriele
A Manufacturing Digital Twin Framework Book Chapter
In: Soldatos, John (Ed.): Artificial Intelligence in Manufacturing, pp. 181–193, Springer, Cham, 2024, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {A Manufacturing Digital Twin Framework},
author = {Victor Anaya and Enrico Alberti and Gabriele Scivoletto },
editor = {John Soldatos},
url = {https://doi.org/10.1007/978-3-031-46452-2_10},
doi = {10.1007/978-3-031-46452-2_3},
isbn = {978-3-031-46451-5},
year = {2024},
date = {2024-02-09},
urldate = {2024-02-09},
booktitle = {Artificial Intelligence in Manufacturing},
pages = {181–193},
publisher = {Springer, Cham},
abstract = {Digital twin technology has become a driving force in the transformation of the manufacturing industry, playing a crucial role in optimizing processes, increasing productivity, and enhancing product quality. A digital twin (DT) is a digital representation of a physical entity or process, modeled to improve decision-making in a safe and cost-efficient environment. Digital twins (DTs) cover a range of problems in different domains at different phases in the lifecycle of a product or process. DTs have gained momentum due to their seamless integration with technologies such as IoT, machine learning algorithms, and analytics solutions. DTs can have different scopes in the manufacturing domain, including process level, system level, asset level, and component level. This work presents the knowlEdge Digital Twin Framework (DTF), a toolkit that comprises a set of tools to create specific instances of DTs in the manufacturing process. This chapter explains how the DTF relates to other standards, such as ISO 23247. This chapter also presents the implementation done for a dairy company.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Digital twin technology has become a driving force in the transformation of the manufacturing industry, playing a crucial role in optimizing processes, increasing productivity, and enhancing product quality. A digital twin (DT) is a digital representation of a physical entity or process, modeled to improve decision-making in a safe and cost-efficient environment. Digital twins (DTs) cover a range of problems in different domains at different phases in the lifecycle of a product or process. DTs have gained momentum due to their seamless integration with technologies such as IoT, machine learning algorithms, and analytics solutions. DTs can have different scopes in the manufacturing domain, including process level, system level, asset level, and component level. This work presents the knowlEdge Digital Twin Framework (DTF), a toolkit that comprises a set of tools to create specific instances of DTs in the manufacturing process. This chapter explains how the DTF relates to other standards, such as ISO 23247. This chapter also presents the implementation done for a dairy company.
Alberti, Enrico; Alvarez-Napagao, Sergio; Anaya, Victor; Barroso, Marta; Barrué, Cristian; Beecks, Christian; Bergamasco, Letizia; Chala, Sisay Adugna; Gimenez-Abalos, Victor; Graß, Alexander; Hinjos, Daniel; Holtkemper, Maike; Jakubiak, Natalia; Nizamis, Alexandros; Pristeri, Edoardo; Sànchez-Marrè, Miquel; Schlake, Georg; Scholz, Jona; Scivoletto, Gabriele; Walter, Stefan
AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0 Journal Article
In: Systems, vol. 12, iss. 2, no. 48, 2024.
@article{nokey,
title = {AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0},
author = {Alberti, Enrico and Alvarez-Napagao, Sergio and Anaya, Victor and Barroso, Marta and Barrué, Cristian and Beecks, Christian and Bergamasco, Letizia and Chala, Sisay Adugna and Gimenez-Abalos, Victor and Graß, Alexander and Hinjos, Daniel and Holtkemper, Maike and Jakubiak, Natalia and Nizamis, Alexandros and Pristeri, Edoardo and Sànchez-Marrè, Miquel and Schlake, Georg and Scholz, Jona and Scivoletto, Gabriele and Walter, Stefan},
editor = {Academic Editors: Pingyu Jiang, Guozhu Jia, Yuchun Xu, Bernd Kuhlenkötter, Petri Helo and Wei Guo},
url = {https://cris.vtt.fi/ws/files/99602347/systems-12-00048.pdf},
doi = {10.3390/systems12020048},
year = {2024},
date = {2024-02-02},
urldate = {2024-02-02},
journal = {Systems},
volume = {12},
number = {48},
issue = {2},
abstract = {The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a newset of challenges. Our proposed method accomplishes this through the knowlEdge architecture, Academic Editors: Pingyu Jiang, Guozhu Jia, Yuchun Xu, Bernd Kuhlenkötter, Petri Helo and Wei Guo Received: 28 November 2023 Revised: 23 January 2024 Accepted: 24 January 2024 Published: 2 February 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a newset of challenges. Our proposed method accomplishes this through the knowlEdge architecture, Academic Editors: Pingyu Jiang, Guozhu Jia, Yuchun Xu, Bernd Kuhlenkötter, Petri Helo and Wei Guo Received: 28 November 2023 Revised: 23 January 2024 Accepted: 24 January 2024 Published: 2 February 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.
Domenech i Vila, M.; Gnatyshak, D.; Tormos, A.; Gimenez-Abalos, V.; Alvarez-Napagao, S.
Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs Journal Article
In: Electronics, vol. 13, iss. 3, no. 573, 2024.
@article{nokey,
title = {Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs},
author = {Domenech i Vila, M. and Gnatyshak, D. and Tormos, A. and Gimenez-Abalos, V. and Alvarez-Napagao, S.},
editor = {Academic Editor: Cheng He},
url = {https://doi.org/10.3390/electronics13030573},
doi = {10.3390/electronics13030573},
year = {2024},
date = {2024-01-31},
urldate = {2024-01-31},
journal = {Electronics},
volume = {13},
number = {573},
issue = {3},
abstract = {The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last few years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we apply an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first use case of policy graphs in the context of explaining agent behaviour in cooperative multi-agent scenarios and present experimental results that sets this kind of scenario apart from previous implementations in single-agent scenarios: when requiring cooperative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last few years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we apply an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first use case of policy graphs in the context of explaining agent behaviour in cooperative multi-agent scenarios and present experimental results that sets this kind of scenario apart from previous implementations in single-agent scenarios: when requiring cooperative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.
2023
Walter, Stefan
Impacts of AI driven manufacturing processes on supply chains: the contributions of the knowlEdge project Journal Article
In: Transportation Research Procedia, vol. 72, pp. 3443-3449, 2023.
@article{nokey,
title = {Impacts of AI driven manufacturing processes on supply chains: the contributions of the knowlEdge project},
author = {Stefan Walter},
url = {https://doi.org/10.1016/j.trpro.2023.11.773},
doi = {10.1016/j.trpro.2023.11.773},
year = {2023},
date = {2023-12-13},
journal = {Transportation Research Procedia},
volume = {72},
pages = {3443-3449},
abstract = {Integrating cross-company activities to form supply chains (SC) reduces costs, resource waste, and builds relations for mutual improvement. However, with more tiers involved, monitoring and addressing problems becomes more difficult. This puts the continuity of the SC at risk. The EU knowlEdge project addresses monitoring and learning in the SC through artificial intelligence (AI) solutions that are distributed, scalable and collaborative. With algorithms for self-learning and automatic value creation, rigid organisation is replaced by flexible networks, facilitating knowledge sharing. Technologies from different domains, including AI and data analytics, are unified into a software architecture. The architecture constitutes a systemic solution and leapfrogs SC performance, including adaptability and autonomy. This allows to respond to evolving markets and to address deviations better.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Integrating cross-company activities to form supply chains (SC) reduces costs, resource waste, and builds relations for mutual improvement. However, with more tiers involved, monitoring and addressing problems becomes more difficult. This puts the continuity of the SC at risk. The EU knowlEdge project addresses monitoring and learning in the SC through artificial intelligence (AI) solutions that are distributed, scalable and collaborative. With algorithms for self-learning and automatic value creation, rigid organisation is replaced by flexible networks, facilitating knowledge sharing. Technologies from different domains, including AI and data analytics, are unified into a software architecture. The architecture constitutes a systemic solution and leapfrogs SC performance, including adaptability and autonomy. This allows to respond to evolving markets and to address deviations better.
Nizamis, Alexandros; Schlake, Georg; Siachamis, Georgios; Dimitriadis, Vasileios; Patsonakis, Christos; Beecks, Christian; Ioannidis, Dimosthenis; Votis, Konstantinos; Tzovaras, Dimitrios
Designing a Marketplace to Exchange AI Models for Industry 5.0 Book Chapter
In: Soldatos, J. (Ed.): Artificial Intelligence in Manufacturing, pp. 27–41, Springer, Cham., 2023, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {Designing a Marketplace to Exchange AI Models for Industry 5.0},
author = {Nizamis, Alexandros and Schlake, Georg and Siachamis, Georgios and Dimitriadis, Vasileios and Patsonakis, Christos and Beecks, Christian and Ioannidis, Dimosthenis and Votis, Konstantinos and Tzovaras, Dimitrios },
editor = {Soldatos, J.},
url = {https://doi.org/10.1007/978-3-031-46452-2_2},
doi = {10.1007/978-3-031-46452-2_2},
isbn = {978-3-031-46451-5},
year = {2023},
date = {2023-09-28},
urldate = {2023-09-28},
booktitle = {Artificial Intelligence in Manufacturing},
pages = {27–41},
publisher = {Springer, Cham.},
abstract = {Nowadays, the market for AI services is continuously growing and it is expected to exceed 5 trillion euros in the next 5 years. However, the sharing of knowledge is primarily achieved by the sharing of published AI-related papers. The sharing of the trained AI/ML models is still in its infancy stage and in some domains it does not even exist. In this chapter, a marketplace for exchanging AI models related to smart manufacturing and Industry 5.0 domains is introduced. The proposed AI Marketplace consists of a semantic-based repository that manages the AI models, a blockchain-based framework that adds the business logic and web-based user interfaces that enable models’ exploration and sharing, and transactions among the stakeholders. The purpose of this chapter is to present the implementation details of this AI Model Marketplace by highlighting the key concepts and technologies used along with the main supported functionalities. By using such a marketplace, the manufacturing companies are able to capitalize in a large variety of AI models to solve various problems enabling intelligent, flexible, and cost-effective production.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Nowadays, the market for AI services is continuously growing and it is expected to exceed 5 trillion euros in the next 5 years. However, the sharing of knowledge is primarily achieved by the sharing of published AI-related papers. The sharing of the trained AI/ML models is still in its infancy stage and in some domains it does not even exist. In this chapter, a marketplace for exchanging AI models related to smart manufacturing and Industry 5.0 domains is introduced. The proposed AI Marketplace consists of a semantic-based repository that manages the AI models, a blockchain-based framework that adds the business logic and web-based user interfaces that enable models’ exploration and sharing, and transactions among the stakeholders. The purpose of this chapter is to present the implementation details of this AI Model Marketplace by highlighting the key concepts and technologies used along with the main supported functionalities. By using such a marketplace, the manufacturing companies are able to capitalize in a large variety of AI models to solve various problems enabling intelligent, flexible, and cost-effective production.
Chala, Sisay Adugna; Graß, Alexander
Human-AI Interaction for Semantic Knowledge Enrichment of AI Model Output Book Chapter
In: Soldatos, John (Ed.): Artificial Intelligence in Manufacturing, pp. 7–41, Springer, Cham, 2023, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {Human-AI Interaction for Semantic Knowledge Enrichment of AI Model Output},
author = {Chala, Sisay Adugna and Graß, Alexander},
editor = {John Soldatos},
url = {https://doi.org/10.1007/978-3-031-46452-2_3},
doi = {10.1007/978-3-031-46452-2_3},
isbn = {978-3-031-46451-5},
year = {2023},
date = {2023-09-28},
urldate = {2023-09-28},
booktitle = {Artificial Intelligence in Manufacturing},
pages = {7–41},
publisher = {Springer, Cham},
abstract = {Modern manufacturing requires developing a framework of AI solutions that capture and process data from various sources including from human-AI collaboration. This chapter tries to describe the concept of domain knowledge fusion in human-AI collaboration for manufacturing. Human interaction with AI is enabled in such a way that the domain expert not only inspects the output of the AI model but also injects engineered knowledge in order to retrain AI models for iterative improvement. Domain knowledge fusion is a technique that involves combining knowledge from multiple domains or sources to produce a more complete solution by augmenting learned knowledge, i.e., the knowledge generated by the AI model with engineered knowledge, i.e., the knowledge provided by the domain expert. The concept developed in this chapter demonstrates how the domain expert interacts with AI systems to observe and decide the veracity of the learned knowledge with respect to the given context. It enables humans to collaborate with AI systems through intuitive interfaces that help domain experts in interpreting insights, validating the findings, and applying domain knowledge to gain a deeper understanding of the data.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Modern manufacturing requires developing a framework of AI solutions that capture and process data from various sources including from human-AI collaboration. This chapter tries to describe the concept of domain knowledge fusion in human-AI collaboration for manufacturing. Human interaction with AI is enabled in such a way that the domain expert not only inspects the output of the AI model but also injects engineered knowledge in order to retrain AI models for iterative improvement. Domain knowledge fusion is a technique that involves combining knowledge from multiple domains or sources to produce a more complete solution by augmenting learned knowledge, i.e., the knowledge generated by the AI model with engineered knowledge, i.e., the knowledge provided by the domain expert. The concept developed in this chapter demonstrates how the domain expert interacts with AI systems to observe and decide the veracity of the learned knowledge with respect to the given context. It enables humans to collaborate with AI systems through intuitive interfaces that help domain experts in interpreting insights, validating the findings, and applying domain knowledge to gain a deeper understanding of the data.
Walter, Stefan; Mikkola, Markku
Advancing Networked Production Through Decentralised Technical Intelligence Book Chapter
In: Soldatos, John (Ed.): pp. 281–300, 2023, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {Advancing Networked Production Through Decentralised Technical Intelligence},
author = {Walter, Stefan and Mikkola, Markku},
editor = {John Soldatos},
url = {https://doi.org/10.1007/978-3-031-46452-2_16},
doi = {10.1007/978-3-031-46452-2_16},
isbn = {978-3-031-46451-5},
year = {2023},
date = {2023-09-28},
urldate = {2023-09-28},
pages = {281–300},
abstract = {In today’s competitive landscape, networked production plays a crucial role in enabling companies to create value and remain competitive. By integrating advanced logistics and supply chain processes, companies optimise resources through cooperation and dynamic arrangements. However, managing the emerging complexity requires a new and intelligent approach. Decentralised Technical Intelligence (DTI) is a response to this challenge. It refers to the distributed and autonomous intelligence embedded in interconnected systems, devices, and agents—involving both humans and machines. By combining the strengths of humans and artificial intelligence (AI), DTI creates a coordinated environment that enhances the overall system intelligence. This collaboration leads to greater autonomy and enables multiple DTI agents to operate independently within a decentralised network. To achieve advanced networked production with DTI, a roadmap will be established, encompassing building blocks that focus on transparency, cooperation, sustainability, seamless integration and intelligent network control. All building blocks are linked to a vision, value promise and development pathway. As networked production evolves, it gives rise to new business models and demands new skills and expertise. By following this roadmap, DTI unlocks its potential for advancement, creating value and fostering competitiveness.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
In today’s competitive landscape, networked production plays a crucial role in enabling companies to create value and remain competitive. By integrating advanced logistics and supply chain processes, companies optimise resources through cooperation and dynamic arrangements. However, managing the emerging complexity requires a new and intelligent approach. Decentralised Technical Intelligence (DTI) is a response to this challenge. It refers to the distributed and autonomous intelligence embedded in interconnected systems, devices, and agents—involving both humans and machines. By combining the strengths of humans and artificial intelligence (AI), DTI creates a coordinated environment that enhances the overall system intelligence. This collaboration leads to greater autonomy and enables multiple DTI agents to operate independently within a decentralised network. To achieve advanced networked production with DTI, a roadmap will be established, encompassing building blocks that focus on transparency, cooperation, sustainability, seamless integration and intelligent network control. All building blocks are linked to a vision, value promise and development pathway. As networked production evolves, it gives rise to new business models and demands new skills and expertise. By following this roadmap, DTI unlocks its potential for advancement, creating value and fostering competitiveness.
Barroso, M.; Hinjos, D.; Martin, P. A.; Gonzalez-Mallo, M.; Gimenez-Abalos, V.; Alvarez-Napagao, S.
Boosting AutoML and XAI in Manufacturing: AI Model Generation Framework Book Chapter
In: Soldatos, John (Ed.): Artificial Intelligence in Manufacturing , pp. 333–350, 2023, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {Boosting AutoML and XAI in Manufacturing: AI Model Generation Framework},
author = {M. Barroso and D. Hinjos and P. A. Martin and M. Gonzalez-Mallo and V. Gimenez-Abalos and S. Alvarez-Napagao},
editor = {John Soldatos},
url = {https://doi.org/10.1007/978-3-031-46452-2_19},
doi = {10.1007/978-3-031-46452-2_19},
isbn = {978-3-031-46451-5},
year = {2023},
date = {2023-09-28},
urldate = {2023-09-28},
booktitle = {Artificial Intelligence in Manufacturing },
pages = {333–350},
abstract = {The adoption of AI in manufacturing enables numerous benefits that can significantly impact productivity, efficiency, and decision-making processes. AI algorithms can optimize production schedules, inventory management, and supply chain operations by analyzing historical data and producing demand forecasts. In spite of these benefits, some challenges such as integration, lack of data infrastructure and expertise, and resistance to change need to be addressed for the industry to successfully adopt AI. To overcome these issues, we introduce the AI Model Generation framework (AMG), able to automatically generate AI models that adjust to the user’s needs. More precisely, the model development process involves the execution of a whole chain of sub-processes, including data loading, automated data pre-processing, cost computation, automatic model hyperparameter tuning, training, inference, explainability generation, standardization, and containerization. We expect our approach to aid non-expert users into more effectively producing machine and deep learning algorithms and hyperparameter settings that are appropriate to solve their problems without sacrificing privacy and relying on third-party services and infrastructure as few as possible.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
The adoption of AI in manufacturing enables numerous benefits that can significantly impact productivity, efficiency, and decision-making processes. AI algorithms can optimize production schedules, inventory management, and supply chain operations by analyzing historical data and producing demand forecasts. In spite of these benefits, some challenges such as integration, lack of data infrastructure and expertise, and resistance to change need to be addressed for the industry to successfully adopt AI. To overcome these issues, we introduce the AI Model Generation framework (AMG), able to automatically generate AI models that adjust to the user’s needs. More precisely, the model development process involves the execution of a whole chain of sub-processes, including data loading, automated data pre-processing, cost computation, automatic model hyperparameter tuning, training, inference, explainability generation, standardization, and containerization. We expect our approach to aid non-expert users into more effectively producing machine and deep learning algorithms and hyperparameter settings that are appropriate to solve their problems without sacrificing privacy and relying on third-party services and infrastructure as few as possible.
Scholz, Jona; Holtkemper, Maike; Graß, Alexander; Beecks, Christian
Anomaly Detection in Manufacturing Book Chapter
In: Soldatos, John (Ed.): Artificial Intelligence in Manufacturing, pp. 351–360, Springer, Cham, 2023, ISBN: 978-3-031-46451-5.
@inbook{nokey,
title = {Anomaly Detection in Manufacturing},
author = {Jona Scholz and Maike Holtkemper and Alexander Graß and Christian Beecks},
editor = {John Soldatos},
url = {https://doi.org/10.1007/978-3-031-46452-2_20},
doi = {10.1007/978-3-031-46452-2_20},
isbn = {978-3-031-46451-5},
year = {2023},
date = {2023-09-28},
booktitle = {Artificial Intelligence in Manufacturing},
pages = {351–360},
publisher = {Springer, Cham},
abstract = {This chapter provides an introduction to common methods of anomaly detection, which is an important aspect of quality control in manufacturing. We give an overview of widely used statistical methods for detecting anomalies based on k-means, decision trees, and Support Vector Machines. In addition, we examine the more recent deep learning technique of autoencoders. We conclude our chapter with a case study from the EU project knowlEdge, where an autoencoder was utilized in order to detect anomalies in a manufacturing process of fuel tanks. Throughout the chapter, we emphasize the importance of humans-in-the-loop and provide an example of how AI can be used to improve manufacturing processes.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
This chapter provides an introduction to common methods of anomaly detection, which is an important aspect of quality control in manufacturing. We give an overview of widely used statistical methods for detecting anomalies based on k-means, decision trees, and Support Vector Machines. In addition, we examine the more recent deep learning technique of autoencoders. We conclude our chapter with a case study from the EU project knowlEdge, where an autoencoder was utilized in order to detect anomalies in a manufacturing process of fuel tanks. Throughout the chapter, we emphasize the importance of humans-in-the-loop and provide an example of how AI can be used to improve manufacturing processes.
Walter, Stefan
Designing Human and Artificial Intelligence Interactions in Industry X Book Chapter
In: Service Design for Emerging Technologies Product Development, 2023.
@inbook{nokey,
title = {Designing Human and Artificial Intelligence Interactions in Industry X},
author = {Stefan Walter},
url = {https://zenodo.org/doi/10.5281/zenodo.10638264},
doi = {10.1007/978-3-031-29306-1_12},
year = {2023},
date = {2023-07-21},
booktitle = {Service Design for Emerging Technologies Product Development},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Walter, Stefan
AI impacts on supply chain performance : a manufacturing use case study Journal Article
In: Discover Artificial Intelligence, vol. 3, no. 18, 2023.
@article{nokey,
title = {AI impacts on supply chain performance : a manufacturing use case study},
author = {Stefan Walter},
url = {https://doi.org/10.1007/s44163-023-00061-9},
doi = {10.1007/s44163-023-00061-9},
year = {2023},
date = {2023-05-04},
urldate = {2023-05-04},
journal = {Discover Artificial Intelligence},
volume = {3},
number = {18},
abstract = {The integration of cross-company activities to form global supply chains (SC) has several benefits, including reducing costs, minimizing energy and resource waste, and promoting relationships for improving all network actors. However, as the number of tiers of suppliers and customers increases, monitoring processes and identifying problems becomes more challenging, which can threaten the continuity of the SC. To address this issue, the EU knowlEdge project proposes using artificial intelligence (AI) solutions that are distributed, scalable, and collaborative to enable automatic monitoring and learning in the SC. This approach replaces rigid organization with flexible networks that leverage self-learning algorithms and automatic value creation, thereby facilitating knowledge sharing. The project unifies technologies from various domains, including AI, data analytics, edge, and cloud computing, into a software architecture that offers a systemic solution rather than an incremental improvement. This architecture enhances SC performance, including adaptability and autonomy, and enables industry to adopt adaptive strategies. The platform’s functionality is tested in manufacturing, where it will improve production monitoring and planning and enable human intervention and learning. The AI application is expected to increase performance on various business and production indicators, which will also have an impact beyond the factory floor. With this approach, managers can respond quickly to changing customer requirements, while deviations in planned processes can be addressed more effectively. Additionally, the research conducted by the project will provide insights into future management and learning in SC.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The integration of cross-company activities to form global supply chains (SC) has several benefits, including reducing costs, minimizing energy and resource waste, and promoting relationships for improving all network actors. However, as the number of tiers of suppliers and customers increases, monitoring processes and identifying problems becomes more challenging, which can threaten the continuity of the SC. To address this issue, the EU knowlEdge project proposes using artificial intelligence (AI) solutions that are distributed, scalable, and collaborative to enable automatic monitoring and learning in the SC. This approach replaces rigid organization with flexible networks that leverage self-learning algorithms and automatic value creation, thereby facilitating knowledge sharing. The project unifies technologies from various domains, including AI, data analytics, edge, and cloud computing, into a software architecture that offers a systemic solution rather than an incremental improvement. This architecture enhances SC performance, including adaptability and autonomy, and enables industry to adopt adaptive strategies. The platform’s functionality is tested in manufacturing, where it will improve production monitoring and planning and enable human intervention and learning. The AI application is expected to increase performance on various business and production indicators, which will also have an impact beyond the factory floor. With this approach, managers can respond quickly to changing customer requirements, while deviations in planned processes can be addressed more effectively. Additionally, the research conducted by the project will provide insights into future management and learning in SC.
2022
Wajid, U.; Nizamis, A.; & Anaya, V.
Towards Industry 5.0–A Trustworthy AI Framework for Digital Manufacturing with Humans in Control Proceeding
Proceedings of Interoperability for Enterprise Systems and Applications Workshops (I-ESA Workshops 2022), Valencia, Spain, March 23-25, 2022. Published on CEUR-WS: 14-Sep-2022 , 2022, ISSN: 1613-0073.
@proceedings{nokey,
title = {Towards Industry 5.0–A Trustworthy AI Framework for Digital Manufacturing with Humans in Control},
author = {Wajid, U. and Nizamis, A. and & Anaya, V.},
editor = {Martin Zelm, Andrés Boza, Ramona-Diana León, Raul Rodriguez-Rodriguez},
url = {https://ceur-ws.org/Vol-3214/WS5Paper10.pdf},
issn = {1613-0073},
year = {2022},
date = {2022-09-14},
urldate = {2022-09-14},
abstract = {Abstract
Despite the fact that Industry 4.0 concepts and technologies are still being developed and still being adopted, the lessons learned from the last decade have helped shape up the notion of Industry 5.0 - as the next ‘revolution’ in industrial domain. Even though Industry 5.0 shared many concepts with Industry 4.0, it is characterized by three main elements, humancentricity, sustainability and resilience. In this paper, we introduce a digital manufacturing platform architecture that extends Industry 4.0 paradigms to enable AI-based decision support with the necessary trustworthiness and human-centricity elements primed for Industry 5.0. The proposed architecture helps realize the balancing act of getting the perceived benefits from AI-centric digitalization while preserving the role of humans in key decision-making activities.},
howpublished = {Proceedings of Interoperability for Enterprise Systems and Applications Workshops (I-ESA Workshops 2022), Valencia, Spain, March 23-25, 2022. Published on CEUR-WS: 14-Sep-2022 },
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Abstract
Despite the fact that Industry 4.0 concepts and technologies are still being developed and still being adopted, the lessons learned from the last decade have helped shape up the notion of Industry 5.0 - as the next ‘revolution’ in industrial domain. Even though Industry 5.0 shared many concepts with Industry 4.0, it is characterized by three main elements, humancentricity, sustainability and resilience. In this paper, we introduce a digital manufacturing platform architecture that extends Industry 4.0 paradigms to enable AI-based decision support with the necessary trustworthiness and human-centricity elements primed for Industry 5.0. The proposed architecture helps realize the balancing act of getting the perceived benefits from AI-centric digitalization while preserving the role of humans in key decision-making activities.
Despite the fact that Industry 4.0 concepts and technologies are still being developed and still being adopted, the lessons learned from the last decade have helped shape up the notion of Industry 5.0 - as the next ‘revolution’ in industrial domain. Even though Industry 5.0 shared many concepts with Industry 4.0, it is characterized by three main elements, humancentricity, sustainability and resilience. In this paper, we introduce a digital manufacturing platform architecture that extends Industry 4.0 paradigms to enable AI-based decision support with the necessary trustworthiness and human-centricity elements primed for Industry 5.0. The proposed architecture helps realize the balancing act of getting the perceived benefits from AI-centric digitalization while preserving the role of humans in key decision-making activities.
Georgiadis, K.; Nizamis, A.; Vafeiadis, T.; Ioannidis, D.; & Tzovaras, D.
Production Scheduling Optimization enabled by Digital Cognitive Platform Journal Article
In: Procedia Computer Science, vol. 204, pp. 424-431, 2022.
@article{nokey,
title = {Production Scheduling Optimization enabled by Digital Cognitive Platform},
author = {Georgiadis, K. and Nizamis, A. and Vafeiadis, T. and Ioannidis, D. and & Tzovaras, D.},
url = {https://www.sciencedirect.com/science/article/pii/S1877050922007906},
doi = {https://doi.org/10.1016/j.procs.2022.08.052},
year = {2022},
date = {2022-09-08},
urldate = {2022-09-08},
journal = {Procedia Computer Science},
volume = {204},
pages = {424-431},
abstract = {Abstract
Automation and optimization are two key concepts for smart factories in industry 4.0. The production planning and scheduling optimization models are widely used to support the aforementioned key concepts. Due to the wide availability of various Industrial Internet of Things (IIoT) devices and predictive models, the factories of the future would be self-learned and capable to act in monetary situations. To achieve this, the planning optimization, dynamic rescheduling and production line balancing solutions should be available to todays’ production lines. In this paper, we are introducing a real-world example of a solution for production scheduling optimization and production line balancing based on genetic algorithm. The introduced application was developed over an established Cognitive Analytics Platform for Anomaly Detection. The application uses deployment, security and visualization services available by the platform. Therefore, this work presents alongside the optimization solution, the way the platform can be modified for serving other use cases besides the anomaly detection, in order to provide a complete tool for factory automation and optimization.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abstract
Automation and optimization are two key concepts for smart factories in industry 4.0. The production planning and scheduling optimization models are widely used to support the aforementioned key concepts. Due to the wide availability of various Industrial Internet of Things (IIoT) devices and predictive models, the factories of the future would be self-learned and capable to act in monetary situations. To achieve this, the planning optimization, dynamic rescheduling and production line balancing solutions should be available to todays’ production lines. In this paper, we are introducing a real-world example of a solution for production scheduling optimization and production line balancing based on genetic algorithm. The introduced application was developed over an established Cognitive Analytics Platform for Anomaly Detection. The application uses deployment, security and visualization services available by the platform. Therefore, this work presents alongside the optimization solution, the way the platform can be modified for serving other use cases besides the anomaly detection, in order to provide a complete tool for factory automation and optimization.
Automation and optimization are two key concepts for smart factories in industry 4.0. The production planning and scheduling optimization models are widely used to support the aforementioned key concepts. Due to the wide availability of various Industrial Internet of Things (IIoT) devices and predictive models, the factories of the future would be self-learned and capable to act in monetary situations. To achieve this, the planning optimization, dynamic rescheduling and production line balancing solutions should be available to todays’ production lines. In this paper, we are introducing a real-world example of a solution for production scheduling optimization and production line balancing based on genetic algorithm. The introduced application was developed over an established Cognitive Analytics Platform for Anomaly Detection. The application uses deployment, security and visualization services available by the platform. Therefore, this work presents alongside the optimization solution, the way the platform can be modified for serving other use cases besides the anomaly detection, in order to provide a complete tool for factory automation and optimization.
Berns, Fabian; Hüwel, Jan David; Beecks, Christian
Automated Model Inference for Gaussian Processes: An Overview of State-of-the-Art Methods and Algorithms Journal Article
In: SN Computer Science, vol. 3, no. 4, pp. 300, 2022.
@article{DBLP:journals/sncs/BernsHB22,
title = {Automated Model Inference for Gaussian Processes: An Overview of State-of-the-Art Methods and Algorithms},
author = {Fabian Berns and Jan David Hüwel and Christian Beecks},
url = {https://doi.org/10.1007/s42979-022-01186-x},
doi = {10.1007/s42979-022-01186-x},
year = {2022},
date = {2022-05-21},
journal = {SN Computer Science},
volume = {3},
number = {4},
pages = {300},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Schlake, Georg Stefan; Hüwel, Jan David; Berns, Fabian; Beecks, Christian
Evaluating the Lottery Ticket Hypothesis to Sparsify Neural Networks for Time Series Classification Inproceedings
In: IEEE International Conference on Data Engineering (ICDE) Workshops, Kuala Lumpur, Malaysia, May 9, 2022, pp. 70-73, IEEE, 2022.
@inproceedings{SchlakeHBB22,
title = {Evaluating the Lottery Ticket Hypothesis to Sparsify Neural Networks for Time Series Classification},
author = {Georg Stefan Schlake and Jan David Hüwel and Fabian Berns and Christian Beecks},
url = {https://doi.org/10.1109/ICDEW55742.2022.00015},
doi = {10.1109/ICDEW55742.2022.00015},
year = {2022},
date = {2022-05-09},
urldate = {2022-05-09},
booktitle = {IEEE International Conference on Data Engineering (ICDE) Workshops, Kuala Lumpur, Malaysia, May 9, 2022},
pages = {70-73},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
knowlEdge Project,
2022, visited: 06.04.2022.
@online{nokey,
title = {knowlEdge Project -- Concept, Methodology and Innovations for Artificial Intelligence in Industry 4.0},
author = {knowlEdge Project},
url = {https://www.knowledge-project.eu/wp-content/uploads/2022/04/poster_knowledge_v5.pdf},
year = {2022},
date = {2022-04-06},
urldate = {2022-04-06},
keywords = {},
pubstate = {published},
tppubtype = {online}
}
2021
Berns, Fabian; Hüwel, Jan David; Beecks, Christian
LOGIC: Probabilistic Machine Learning for Time Series Classification Inproceedings
In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 1000–1005, IEEE, Auckland, New Zealand, 2021, ISBN: 978-1-66542-398-4.
@inproceedings{bernsLOGICProbabilisticMachine2021,
title = {LOGIC: Probabilistic Machine Learning for Time Series Classification},
author = {Fabian Berns and Jan David Hüwel and Christian Beecks},
doi = {10.1109/ICDM51629.2021.00113},
isbn = {978-1-66542-398-4},
year = {2021},
date = {2021-12-01},
urldate = {2021-12-01},
booktitle = {2021 IEEE International Conference on Data Mining (ICDM)},
pages = {1000--1005},
publisher = {IEEE},
address = {Auckland, New Zealand},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Alvarez-Napagao, Sergio; Ashmore, Boki; Barroso, Marta; Barrué, Cristian; Beecks, Christian; Berns, Fabian; Bosi, Ilaria; Chala, Sisay Adugna; Ciulli, Nicola; Garcia-Gasulla, Marta; Grass, Alexander; Ioannidis, Dimosthenis; Jakubiak, Natalia; Köpke, Karl; Lämsä, Ville; Megias, Pedro; Nizamis, Alexandros; Pastrone, Claudio; Rossini, Rosaria; Sànchez-Marrè, Miquel; Ziliotti, Luca
knowlEdge Project -- Concept, Methodology and Innovations for Artificial Intelligence in Industry 4.0 Inproceedings
In: IEEE 19th International Conference on Industrial Informatics (INDIN), pp. 1-7, IEEE, 2021.
@inproceedings{Alvarez-Napagao2021,
title = {knowlEdge Project -- Concept, Methodology and Innovations for Artificial Intelligence in Industry 4.0},
author = {Sergio Alvarez-Napagao and Boki Ashmore and Marta Barroso and Cristian Barrué and Christian Beecks and Fabian Berns and Ilaria Bosi and Sisay Adugna Chala and Nicola Ciulli and Marta Garcia-Gasulla and Alexander Grass and Dimosthenis Ioannidis and Natalia Jakubiak and Karl Köpke and Ville Lämsä and Pedro Megias and Alexandros Nizamis and Claudio Pastrone and Rosaria Rossini and Miquel Sànchez-Marrè and Luca Ziliotti},
url = {https://ieeexplore.ieee.org/document/9557410},
doi = {10.1109/INDIN45523.2021.9557410},
year = {2021},
date = {2021-10-11},
booktitle = {IEEE 19th International Conference on Industrial Informatics (INDIN)},
pages = {1-7},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Berns, Fabian; Strueber, Joschka Hannes; Beecks, Christian
Local Gaussian Process Model Inference Classification for Time Series Data Inproceedings
In: Zhu, Qiang; Zhu, Xingquan; Tu, Yicheng; Xu, Zichen; Kumar, Anand (Ed.): SSDBM 2021: 33rd International Conference on Scientific and Statistical Database Management, Tampa, FL, USA, July 6-7, 2021, pp. 209–213, ACM, 2021.
@inproceedings{DBLP:conf/ssdbm/BernsSB21,
title = {Local Gaussian Process Model Inference Classification for Time Series
Data},
author = {Fabian Berns and Joschka Hannes Strueber and Christian Beecks},
editor = {Qiang Zhu and Xingquan Zhu and Yicheng Tu and Zichen Xu and Anand Kumar},
url = {https://doi.org/10.1145/3468791.3468839},
doi = {10.1145/3468791.3468839},
year = {2021},
date = {2021-01-01},
booktitle = {SSDBM 2021: 33rd International Conference on Scientific and Statistical
Database Management, Tampa, FL, USA, July 6-7, 2021},
pages = {209--213},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hüwel, Jan David; Berns, Fabian; Beecks, Christian
Automated Kernel Search for Gaussian Processes on Data Streams Inproceedings
In: 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA, December 15-18, 2021, pp. 3584–3588, IEEE, 2021.
@inproceedings{DBLP:conf/bigdataconf/HuwelBB21,
title = {Automated Kernel Search for Gaussian Processes on Data Streams},
author = {Jan David Hüwel and Fabian Berns and Christian Beecks},
url = {https://doi.org/10.1109/BigData52589.2021.9671767},
doi = {10.1109/BigData52589.2021.9671767},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Conference on Big Data (Big Data), Orlando,
FL, USA, December 15-18, 2021},
pages = {3584--3588},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}