https://www.mdu.se/

mdu.sePublikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
Publikationer (10 of 39) Visa alla publikationer
Leberruyer, N., Ahlskog, M., Bruch, J. & Backhans, E. (2027). Empowering the Manufacturing Workforce to Integrate AI Coding Assistants. In: IFIP Advances in Information and Communication Technology: . Paper presented at 45th IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2026, Bergamo, Italy, 13-17 September, 2026 (pp. 65-80). Springer Science and Business Media Deutschland GmbH
Öppna denna publikation i ny flik eller fönster >>Empowering the Manufacturing Workforce to Integrate AI Coding Assistants
2027 (Engelska)Ingår i: IFIP Advances in Information and Communication Technology, Springer Science and Business Media Deutschland GmbH , 2027, s. 65-80Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Despite the interest in Artificial Intelligence (AI) within manufacturing, many companies struggle to move beyond experimental pilot projects toward successful operational integration. A significant gap remains between the acquisition of technical tools and the development of the organizational capability to use them effectively in a production environment. This study investigates how AI coding assistants can bridge this gap by empowering non-programming domain experts, such as process engineers and quality technicians, to achieve analytical autonomy. A case study with an interactive approach was applied at a heavy-duty automotive manufacturing site. The researchers and practitioners engaged in a joint learning process for six months. The findings are analyzed through the lens of dynamic capabilities theory, specifically the capacities for Sensing, Seizing, and Reconfiguring. Results reveal a trust-adoption paradox, where participants overcome skepticism of AI-generated outputs by leveraging their domain expertise for verification. The study documents six real-world cases where participants independently used AI tools to identify bottlenecks, optimize cycle times, and improve data quality. Our findings suggest that AI coding assistants act as a capability multiplier, reducing cross-functional friction and initiating a virtuous cycle of data integrity. For management, the study implies that the AI integration hurdle can be overcome not by hiring external specialists, but by providing the autonomy and technical support for the existing workforce to translate their domain knowledge into executable digital solutions.

Ort, förlag, år, upplaga, sidor
Springer Science and Business Media Deutschland GmbH, 2027
Serie
IFIP Advances in Information and Communication Technology, ISSN 1868-4238
Nyckelord
Digital transformation, Human-AI collaboration, Industrial AI, Industrial systems, Industry 5.0, Computer programming, Engineering education, Personnel, Human-artificial intelligence collaboration, Industrial artificial intelligence, Manufacturing workforce, Operational integration, Organizational capabilities, Pilot programs, Technical tools, Codes (symbols)
Nationell ämneskategori
Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:mdh:diva-79317 (URN)10.1007/978-3-032-38618-2_5 (DOI)2-s2.0-105053530696 (Scopus ID)9783032386175 (ISBN)
Konferens
45th IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2026, Bergamo, Italy, 13-17 September, 2026
Tillgänglig från: 2026-10-27 Skapad: 2026-10-27 Senast uppdaterad: 2026-10-27Bibliografiskt granskad
Sauter, B., Ahlskog, M., Granlund, A. & Bruch, J. (2026). Achieving adoption of virtual reality in the new product development process: key decisions and implementation activities.
Öppna denna publikation i ny flik eller fönster >>Achieving adoption of virtual reality in the new product development process: key decisions and implementation activities
2026 (Engelska)Artikel i tidskrift (Refereegranskat) Submitted
Abstract [en]

Virtual Reality (VR) within manufacturing industry has continued to be of large interest, especially when seeking to reduce time-to-market for development of new products. To reduce time-to-market (TTM), VR technology must be implemented and used in the development process in a way that enables increased performance. Therefore, the purpose of this study is to identify key decisions and implementation activities that impact VR adoption in NPD processes. This paper explores the VR adoption and usage to shed light on key decisions and implementation activities. A retrospective multiple case study has been conducted. One case has successfully implemented and used VR while two other cases have not. The results describe the decisions and implementation activities performed. Based on the results a framework for VR adoption is proposed. The framework identifies attributes which are key to VR adoption and describes them among three adoption stages.

Nyckelord
Virtual reality, implementation, NPD, adoption, maturity, production system, smart production, case study, concurrent engineering, manufacturing industry, virtual prototyping, validation, management, teams
Nationell ämneskategori
Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:mdh:diva-75214 (URN)
Tillgänglig från: 2025-12-17 Skapad: 2025-12-17 Senast uppdaterad: 2026-01-22Bibliografiskt granskad
Jackson, M., Klöckner, M., Govindaraj, A., Ahlskog, M. & Bruch, J. (2026). Cloneable Automation Systems - Industrial Needs and Development Areas. In: : . Paper presented at The 12th Swedish Production Symposium 24-26, 2026, Luleå, Sweden (pp. 012019-012019). IOP Publishing, 1342(1)
Öppna denna publikation i ny flik eller fönster >>Cloneable Automation Systems - Industrial Needs and Development Areas
Visa övriga...
2026 (Engelska)Konferensbidrag, Publicerat paper (Övrigt vetenskapligt)
Abstract [en]

In today’s competitive industrial environment, characterized by diversecustomer demands and an increasing need for rapid adaptation, the ability toquickly and efficiently relocate manufacturing capacity to different locations hasbecome crucial. This paper introduces the concept of Cloneable AutomationSystems which are automation systems specifically designed for easy and efficientduplication of both functionality and physical structure. These systems aredistinguished by their capability to swiftly embed and relocate automationcapacity within a corporation, with minimal undesirable effects in terms of time,effort, cost, or performance. The research presented in this paper has beenconducted within the framework of the Mälardalen University AutomationResearch Center (MARC), which is committed to advancing digitalization andautomation in industry through a comprehensive, multidisciplinary approach andstrong industrial partnerships. The expected scientific contributions of theresearch include the development of innovative solutions in smart and portableautomation, robotics and control, as well as digital infrastructure. The maincontribution of this paper is the framing of a Cloneable Automation Systemconcept based on a case study within a global manufacturing company. The paperidentifies industrial needs and development areas related to enhancing thepossibilities for reusability and relocation of automation systems.

Ort, förlag, år, upplaga, sidor
IOP Publishing, 2026
Serie
IOP Conference Series: Materials Science and Engineering, ISSN 1757-8981, E-ISSN 1757-899X ; 1342
Nationell ämneskategori
Robotik och automation
Identifikatorer
urn:nbn:se:mdh:diva-76916 (URN)10.1088/1757-899x/1342/1/012019 (DOI)
Konferens
The 12th Swedish Production Symposium 24-26, 2026, Luleå, Sweden
Tillgänglig från: 2026-05-26 Skapad: 2026-05-26 Senast uppdaterad: 2026-05-26Bibliografiskt granskad
Ahlskog, M., Klöckner, M., Govindaraj, A., Jackson, M. & Bruch, J. (2026). Introducing the concept of smart and portable automation systems. In: : . Paper presented at The 12th Swedish Production Symposium 24 - 26, 2026 Luleå, Sweden (pp. 012020-012020). IOP Publishing, 1342(1)
Öppna denna publikation i ny flik eller fönster >>Introducing the concept of smart and portable automation systems
Visa övriga...
2026 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Traditional industrial robot automation is often fixed, and they have enabled increased competitiveness, but often lack the agility required for dynamic manufacturing environments. Building on research projects such as Factory-in-a-Box and Lean robotics, the purpose of the paper is to introduce the concept of smart and portable automation systems, a vision for modern manufacturing that emphasizes the need for scalable, movable, and reconfigurable automation solutions. The concept of smart and portable automation systems refers to advanced robotic systems that combine intelligent, data-driven capabilities with enhanced mobility and adaptability, allowing for flexible and reconfigurable operations. A collaborative and interactive research approach has been applied in a research project with three participating manufacturing companies. Based on the manufacturing companies’ automation challenges and proposed use cases for smart and portable automation the goal with the research project is to develop demonstrators that show cases smart and portable automation. In this paper a smart and portable automation system refers to “an automation system with a low degree of perceived complexity that can be easily moved and easily meet dynamic manufacturing needs.

Ort, förlag, år, upplaga, sidor
IOP Publishing, 2026
Serie
IOP Conference Series: Materials Science and Engineering, ISSN 1757-8981, E-ISSN 1757-899X ; 1342
Nationell ämneskategori
Robotik och automation
Identifikatorer
urn:nbn:se:mdh:diva-76915 (URN)10.1088/1757-899x/1342/1/012020 (DOI)
Konferens
The 12th Swedish Production Symposium 24 - 26, 2026 Luleå, Sweden
Tillgänglig från: 2026-05-26 Skapad: 2026-05-26 Senast uppdaterad: 2026-05-26Bibliografiskt granskad
Agerskans, N., Ahlskog, M., Badasjane, V., Granlund, A. & Sauter, B. (2025). Coordination of Digital Transformation. Eskilstuna: Mälardalens universitet
Öppna denna publikation i ny flik eller fönster >>Coordination of Digital Transformation
Visa övriga...
2025 (Engelska)Rapport (Övrigt vetenskapligt)
Ort, förlag, år, upplaga, sidor
Eskilstuna: Mälardalens universitet, 2025. s. 35
Nationell ämneskategori
Annan teknik
Forskningsämne
industriella system
Identifikatorer
urn:nbn:se:mdh:diva-72375 (URN)978-91-7485-712-2 (ISBN)
Projekt
KODITXPRES
Forskningsfinansiär
Vinnova, 2020-02991XPRES - Initiative for excellence in production research
Tillgänglig från: 2025-06-24 Skapad: 2025-06-24 Senast uppdaterad: 2025-10-10Bibliografiskt granskad
Leberruyer, N., Ahlskog, M. & Bruch, J. (2024). Addressing challenges when adopting AI-driven Zero Defect Manufacturing: Insights from industry. In: IFAC-PapersOnLine: . Paper presented at 18th IFAC Workshop on Time Delay Systems, TDS 2024, Udine, Italy, 2-5 October, 2023 (pp. 112-119). Elsevier BV, 58
Öppna denna publikation i ny flik eller fönster >>Addressing challenges when adopting AI-driven Zero Defect Manufacturing: Insights from industry
2024 (Engelska)Ingår i: IFAC-PapersOnLine, Elsevier BV , 2024, Vol. 58, s. 112-119Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Zero Defect Manufacturing (ZDM), driven by Artificial Intelligence (AI), has the potential to transform industry in the digital age, utilizing data from various production stages to achieve zero defects and minimize waste, resulting in superior customer value. However, extensive empirical studies are required to validate its effectiveness across various production settings and enhance its implementation by improving technological components, seamlessly integrating with existing processes, and clearly defining human roles. The purpose of this paper is to investigate how to facilitate the adoption of AI-driven ZDM in production systems. This research highlights challenges and recommendations associated when implementing AI-driven ZDM within a production system and suggests a framework to facilitate this process. Using a longitudinal case study in the heavy-duty automotive industry, four AI-driven ZDM applications were examined to determine adoption dynamics. Leveraging the Technology-Organization-Environment (TOE) theory, we identified ten application challenges and made recommendations for how to address them. The analysis highlights the importance of adhering to agile principles with continuous adaptation during AI implementation, stressing the need for feedback collection from stakeholders to assess adoption factors. This study underscores the significance of explainable AI in empowering operators and emphasizes the necessity of human-centered design principles and feedback loops to ensure AI systems truly serve their users. Building on these findings, a framework is proposed aiming for incremental value creation, continuous learning, and adaptation while considering human feedback through various channels, similar to the Plan-Do-Check-Act cycle in lean management. This iterative approach, encompassing continuous improvement loops, aims to ensure successful adoption and maximize the potential of AI-driven ZDM in order to achieve operational excellence. This study contributes to the existing literature on AI adoption in production systems by offering a comprehensive understanding of the challenges and recommendations associated with implementing AI-driven ZDM. Additionally, the proposed framework provides a practical roadmap for organizations seeking to leverage the power of AI to achieve zero-defect manufacturing and enhance their competitive advantage.

Ort, förlag, år, upplaga, sidor
Elsevier BV, 2024
Serie
IFAC-PapersOnLine, ISSN 1474-6670, E-ISSN 2405-8973
Nyckelord
Industrial Artificial Intelligence, Industry 5.0, Quality, Smart production
Nationell ämneskategori
Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:mdh:diva-75787 (URN)2-s2.0-85213018238 (Scopus ID)9783902661869 (ISBN)9788374810357 (ISBN)
Konferens
18th IFAC Workshop on Time Delay Systems, TDS 2024, Udine, Italy, 2-5 October, 2023
Forskningsfinansiär
KK-stiftelsenMälardalens universitet
Tillgänglig från: 2026-02-06 Skapad: 2026-02-06 Senast uppdaterad: 2026-06-29Bibliografiskt granskad
Leberruyer, N., Ahlskog, M. & Bruch, J. (2024). Addressing challenges when adopting AI-driven Zero Defect Manufacturing: Insights from industry. In: Procedia CIRP: . Paper presented at 57th CIRP Conference on Manufacturing Systems 2024 (CMS 2024), 29 - 31 May, 2024, Povoa de Varzim, Portugal (pp. 112-119). Elsevier BV, 130
Öppna denna publikation i ny flik eller fönster >>Addressing challenges when adopting AI-driven Zero Defect Manufacturing: Insights from industry
2024 (Engelska)Ingår i: Procedia CIRP, Elsevier BV , 2024, Vol. 130, s. 112-119Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Zero Defect Manufacturing (ZDM), driven by Artificial Intelligence (AI), has the potential to transform industry in the digital age, utilizing data from various production stages to achieve zero defects and minimize waste, resulting in superior customer value. However, extensive empirical studies are required to validate its effectiveness across various production settings and enhance its implementation by improving technological components, seamlessly integrating with existing processes, and clearly defining human roles. The purpose of this paper is to investigate how to facilitate the adoption of AI-driven ZDM in production systems. This research highlights challenges and recommendations associated when implementing AI-driven ZDM within a production system and suggests a framework to facilitate this process.Using a longitudinal case study in the heavy-duty automotive industry, four AI-driven ZDM applications were examined to determine adoption dynamics. Leveraging the Technology-Organization-Environment (TOE) theory, we identified ten application challenges and made recommendations for how to address them. The analysis highlights the importance of adhering to agile principles with continuous adaptation during AI implementation, stressing the need for feedback collection from stakeholders to assess adoption factors. This study underscores the significance of explainable AI in empowering operators and emphasizes the necessity of human-centered design principles and feedback loops to ensure AI systems truly serve their users. Building on these findings, a framework is proposed aiming for incremental value creation, continuous learning, and adaptation while considering human feedback through various channels, similar to the Plan-Do-Check-Act cycle in lean management. This iterative approach, encompassing continuous improvement loops, aims to ensure successful adoption and maximize the potential of AI-driven ZDM in order to achieve operational excellence.This study contributes to the existing literature on AI adoption in production systems by offering a comprehensive understanding of the challenges and recommendations associated with implementing AI-driven ZDM. Additionally, the proposed framework provides a practical roadmap for organizations seeking to leverage the power of AI to achieve zero-defect manufacturing and enhance their competitive advantage.

Ort, förlag, år, upplaga, sidor
Elsevier BV, 2024
Serie
Procedia CIRP, ISSN 2212-8271
Nationell ämneskategori
Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:mdh:diva-69297 (URN)10.1016/j.procir.2024.10.064 (DOI)2-s2.0-85214992324 (Scopus ID)9781510875692 (ISBN)
Konferens
57th CIRP Conference on Manufacturing Systems 2024 (CMS 2024), 29 - 31 May, 2024, Povoa de Varzim, Portugal
Tillgänglig från: 2024-12-05 Skapad: 2024-12-05 Senast uppdaterad: 2026-07-30Bibliografiskt granskad
Badasjane, V., Granlund, A., Ahlskog, M., Bruch, J. & Sauter, B. (2024). Coordinating Digital Transformation: Exploring IT Organizational Adaptations in International Manufacturing Networks. In: IFIP Advances in Information and Communication Technology: . Paper presented at IFIP Advances in Information and Communication Technology (pp. 120-134). Springer Nature
Öppna denna publikation i ny flik eller fönster >>Coordinating Digital Transformation: Exploring IT Organizational Adaptations in International Manufacturing Networks
Visa övriga...
2024 (Engelska)Ingår i: IFIP Advances in Information and Communication Technology, Springer Nature , 2024, s. 120-134Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Digital transformation is complicated in International Manufacturing Networks (IMNs), where factories are spread globally, and actions are interdependent. Adapting organizational structures is one way to handle the demands and expectations posed by digital transformation. However, research covering the adaptations to the IT organization is limited, and this paper's purpose is to explore adaptations of IT organizations within IMNs during digital transformation. A multiple case study was performed, studying two manufacturing companies’ adaptations of the IT organization. The result reveals three phases of adaptations of the IT organization: the foundation phase, the mapping phase, and the coordinating phase. The phases are accompanied by the setup of a new operational IT function that works with digital transformation in the IMNs. Also, the interfaces and collaboration between the operational IT function and the factories in the IMNs are identified. Lastly, it highlights remaining challenges with the adaptations of the IT organization that need further research. 

Ort, förlag, år, upplaga, sidor
Springer Nature, 2024
Serie
IFIP Advances in Information and Communication Technology, ISSN 1868-4238, E-ISSN 1868-422X
Nyckelord
Digitalization, Global Manufacturing, Smart Production, Digital transformation, IT organizations, Manufacturing companies, Manufacturing networks, Multiple-case study, Organizational adaptation, Organizational structures, Smart manufacturing
Nationell ämneskategori
Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:mdh:diva-68583 (URN)10.1007/978-3-031-71633-1_9 (DOI)001356136900009 ()2-s2.0-85204545247 (Scopus ID)9783031716324 (ISBN)
Konferens
IFIP Advances in Information and Communication Technology
Tillgänglig från: 2024-10-02 Skapad: 2024-10-02 Senast uppdaterad: 2026-02-25Bibliografiskt granskad
Andersson, T., Bohlin, M., Ahlskog, M. & Olsson, T. (2024). Interpretable ML Model for Quality Control of Locks Using Counterfactual Explanations. In: Proc. - Int. Conf. Innov. Dev. Inf. Technol. Robot., IDITR: . Paper presented at Proceedings - 2024 3rd International Conference on Innovations and Development of Information Technologies and Robotics, IDITR 2024 (pp. 161-166). Institute of Electrical and Electronics Engineers Inc.
Öppna denna publikation i ny flik eller fönster >>Interpretable ML Model for Quality Control of Locks Using Counterfactual Explanations
2024 (Engelska)Ingår i: Proc. - Int. Conf. Innov. Dev. Inf. Technol. Robot., IDITR, Institute of Electrical and Electronics Engineers Inc. , 2024, s. 161-166Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper presents an interpretable machine-learning model for anomaly detection in door locks using torque data. The model aims to replace the human tactile sense in the quality control process, reducing repetitive tasks and improving reliability. The model achieved an accuracy of 96%, however, to gain social acceptance and operators' trust, interpretability of the model is crucial. The purpose of this study was to evaluate an approach that can improve interpretability of anomalous classifications obtained from an anomaly detection model. We evaluate four instance-based counterfactual explanators, three of which, employ optimization techniques and one uses, a less complex, weighted nearest neighbor approach, which serve as our baseline. The former approaches, leverage a latent representation of the data, using a weighted principal component analysis, improving plausibility of the counter factual explanations and reduces computational cost. The explanations are presented together with the 5-50-95th percentile range of the training data, acting as a frame of reference to improve interpretability. All approaches successfully presented valid and plausible counterfactual explanations. However, instance-based approaches employing optimization techniques yielded explanations with greater similarity to the observations and was therefore concluded to be preferable despite the higher execution times (4-16s) compared to the baseline approach (0.1s). The findings of this study hold significant value for the lock industry and can potentially be extended to other industrial settings using timeseries data, serving as a valuable point of departure for further research.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers Inc., 2024
Nyckelord
Anomaly detection, Counterfactual explanation, Explainable artificial intelligence, Principal component analysis, Artificial intelligence, Industrial research, Locks (fasteners), Quality control, Counterfactuals, Interpretability, Machine learning models, Optimization techniques, Principal-component analysis, Tactile sense, Torque data
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
urn:nbn:se:mdh:diva-69541 (URN)10.1109/IDITR62018.2024.10554297 (DOI)2-s2.0-85197291244 (Scopus ID)9798350385694 (ISBN)
Konferens
Proceedings - 2024 3rd International Conference on Innovations and Development of Information Technologies and Robotics, IDITR 2024
Tillgänglig från: 2024-12-12 Skapad: 2024-12-12 Senast uppdaterad: 2025-10-10Bibliografiskt granskad
Andersson, T., Bohlin, M., Ahlskog, M. & Olsson, T. (2024). Interpretable ML model for quality control of locks using counterfactual explanations. In: : . Paper presented at 2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024). , Article ID 7.
Öppna denna publikation i ny flik eller fönster >>Interpretable ML model for quality control of locks using counterfactual explanations
2024 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper presents an interpretable machinelearning model for anomaly detection in door locks using torque data. The model aims to replace the human tactile sense in the quality control process, reducing repetitive tasks and improving reliability. The model achieved an accuracy of 96%, however, to gain social acceptance and operators' trust, interpretability of the model is crucial. The purpose of this study was to evaluate anapproach that can improve interpretability of anomalousclassifications obtained from an anomaly detection model. Weevaluate four instance-based counterfactual explanators, three of which, employ optimization techniques and one uses, a less complex, weighted nearest neighbor approach, which serve as ourbaseline. The former approaches, leverage a latent representation of the data, using a weighted principal component analysis, improving plausibility of the counter factual explanations andreduces computational cost. The explanations are presentedtogether with the 5-50-95th percentile range of the training data, acting as a frame of reference to improve interpretability. All approaches successfully presented valid and plausible counterfactual explanations. However, instance-based approachesemploying optimization techniques yielded explanations withgreater similarity to the observations and was therefore concluded to be preferable despite the higher execution times (4-16s) compared to the baseline approach (0.1s). The findings of this study hold significant value for the lock industry and can potentially be extended to other industrial settings using timeseries data, serving as a valuable point of departure for further research.

Nyckelord
—Explainable artificial intelligence, Counterfactual explanation, Anomaly detection, Principal component analysis
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
datavetenskap
Identifikatorer
urn:nbn:se:mdh:diva-66504 (URN)
Konferens
2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024)
Forskningsfinansiär
KK-stiftelsen, No 20200132 01 H
Anmärkning

In press

Tillgänglig från: 2024-04-24 Skapad: 2024-04-24 Senast uppdaterad: 2025-10-10Bibliografiskt granskad
Organisationer
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0002-9933-8532

Sök vidare i DiVA

Visa alla publikationer