Högskolan i Skövde

his.sePublications
Planned maintenance
A system upgrade is planned for 17/11-2026, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
Link to record
Permanent link

Direct link
Publications (6 of 6) Show all publications
Mittermeier, L., Ng, A. H. C., Senington, R. & Jeusfeld, M. A. (2026). A Graph Database Approach for Supporting Knowledge-Driven and Simulation-Based Optimization in Industry and Academia. SNE Simulation Notes Europe, 36(3), 147-156
Open this publication in new window or tab >>A Graph Database Approach for Supporting Knowledge-Driven and Simulation-Based Optimization in Industry and Academia
2026 (English)In: SNE Simulation Notes Europe, ISSN 2305-9974, Vol. 36, no 3, p. 147-156Article in journal (Refereed) Published
Abstract [en]

With the increase in complexity of industrial systems it becomes more and more challenging to make well-grounded decisions for system design and operation. Following the concept of Virtual Factories with Knowledge-Driven Optimization (VF-KDO), this paper proposes a graph database approach to support knowledge-driven and simulation-based optimization. With the mapping of a VF-KDO ontology to a graph database, competency questions that facilitate traceability, transparency, and group decision making can be answered. This is exemplified with an industrial use case and different student projects from an education course in Industrial Engineering and Management.

Place, publisher, year, edition, pages
Federation of European Simulation Societies, 2026
National Category
Computer Sciences Production Engineering, Human Work Science and Ergonomics
Research subject
Electrical Engineering and Automation (ETA); Information Systems; VF-KDO
Identifiers
urn:nbn:se:his:diva-27207 (URN)10.11128/sne.36.tn.10785 (DOI)
Note

ludwig.mittermeier@his.se

© 2026 EUROSIM / ARGESIM

SNE 36(3), Special Issue SPL: Key Role of Simulation: Shaping Changes, Mastering Challenges, September 2026

Available from: 2026-11-10 Created: 2026-11-10 Last updated: 2026-11-12Bibliographically approved
Senington, R., Mittermeier, L. & Ng, A. H. C. (2026). LLMS, Manufacturing Knowledge Graphs & GraphRAG enabling Intuitive Analytics. In: SPS 2026 - The 12th Swedish Production Symposium 24/03/2026 - 26/03/2026 Luleå, Sweden: . Paper presented at SPS 2026 - The 12th Swedish Production Symposium 24/03/2026 - 26/03/2026 Luleå, Sweden, Leading the transformation towards net zero industry. Institute of Physics Publishing (IOPP), Article ID 012057.
Open this publication in new window or tab >>LLMS, Manufacturing Knowledge Graphs & GraphRAG enabling Intuitive Analytics
2026 (English)In: SPS 2026 - The 12th Swedish Production Symposium 24/03/2026 - 26/03/2026 Luleå, Sweden, Institute of Physics Publishing (IOPP), 2026, article id 012057Conference paper, Published paper (Refereed)
Abstract [en]

As manufacturing systems become increasingly complex and data-rich, there is an opportunity to identify predictive patterns in the data, including deeper patterns and more general, broad principles for effective use of our production infrastructure. Simulation-based multi-objective optimization provides additional options and predictions for industrial decision-makers; however, traditional analytics approaches struggle to provide the necessary insights. More sophisticated methods, such as data mining, provide greater insight; however, they require technically proficient users to achieve results. This paper will examine an example application in which data mining methods were applied to the results of multi-objective optimization and modeled as a knowledge graph. Our study presents the development and evaluation of an LLM-based Graph Retrieval-Augmented Generation (GraphRAG) tool that can translate natural language queries into Neo4j graph database queries for manufacturing data analysis. We present both successful query generations and identify failure modes, providing insights into the current capabilities and limitations of this approach. The paper includes a detailed use case description, documenting specific manufacturing analytics requirements and the corresponding graph query patterns needed to extract meaningful insights.

Place, publisher, year, edition, pages
Institute of Physics Publishing (IOPP), 2026
Series
IOP Conference Series: Materials Science and Engineering, ISSN 1757-8981, E-ISSN 1757-899X ; 1342
National Category
Computer Sciences Computer Systems Production Engineering, Human Work Science and Ergonomics
Research subject
Virtual Production Development (VPD); VF-KDO
Identifiers
urn:nbn:se:his:diva-26796 (URN)10.1088/1757-899x/1342/1/012057 (DOI)001803535300057 ()
Conference
SPS 2026 - The 12th Swedish Production Symposium 24/03/2026 - 26/03/2026 Luleå, Sweden, Leading the transformation towards net zero industry
Note

CC BY 4.0

E-mail: richard.james.senington@his.se

Available from: 2026-07-01 Created: 2026-07-01 Last updated: 2026-08-11Bibliographically approved
Mittermeier, L., Ng, A. H. C., Senington, R. & Jeusfeld, M. A. (2025). A Graph Database Approach for Supporting Knowledge-Driven and Simulation-Based Optimization in Industry and Academia. In: Sebastian Rank; Mathias Kühn; Thorsten Schmidt (Ed.), Simulation in Produktion und Logistik 2025: . Paper presented at 21. ASIM-Fachtagung Simulation in Produktion und Logistik, Dresden, Germany, 24–26 September 2025. Dresden: Technische Universität Dresden, Article ID 43.
Open this publication in new window or tab >>A Graph Database Approach for Supporting Knowledge-Driven and Simulation-Based Optimization in Industry and Academia
2025 (English)In: Simulation in Produktion und Logistik 2025 / [ed] Sebastian Rank; Mathias Kühn; Thorsten Schmidt, Dresden: Technische Universität Dresden , 2025, article id 43Conference paper, Published paper (Refereed)
Abstract [en]

With the increase in complexity of industrial systems it becomes more and more challenging to make well-grounded decisions for system design and operation. Following the concept of Virtual Factories with Knowledge-Driven Optimization (VF-KDO), this paper proposes a graph database approach to support knowledge-driven and simulation-based optimization. With the mapping of a VF-KDO ontology to a graph database, competency questions that facilitate traceability, transparency, and group decision making can be answered. This is exemplified with an industrial use case and a scenario form academic education.

Place, publisher, year, edition, pages
Dresden: Technische Universität Dresden, 2025
Series
ASIM Mitteilungen
Keywords
Graph Database, Knowledge-Driven Optimization, Simulation-Based Optimization, Knowledge graph, Optimization, Decision support, Heterogeneous data, Industrial use case, Academic use case, Supporting knowledge, Database systems, Knowledge retrieval, Virtual Manufacturing
National Category
Computer Sciences Production Engineering, Human Work Science and Ergonomics
Research subject
VF-KDO; Virtual Production Development (VPD); Information Systems
Identifiers
urn:nbn:se:his:diva-25970 (URN)10.25368/2025.276 (DOI)978-3-86780-806-4 (ISBN)978-3-86780-809-5 (ISBN)
Conference
21. ASIM-Fachtagung Simulation in Produktion und Logistik, Dresden, Germany, 24–26 September 2025
Funder
Knowledge Foundation
Note

CC BY-NC 4.0

The authors would like to acknowledge the Knowledge Foundation (KKS), Sweden, for providing funding to the VF-KDO profile (2018-2026) and FlexLink AB for its active partnership within the LINK subject area of VF-KDO. 

Available from: 2025-10-28 Created: 2025-10-28 Last updated: 2026-05-22Bibliographically approved
Senington, R., Ng, A. H. C., Mittermeier, L. & Bandaru, S. (2025). Graph Databases for Group Decision Making in Industry: A Comprehensive Literature Review. IEEE Access, 13, Article ID 3596632.
Open this publication in new window or tab >>Graph Databases for Group Decision Making in Industry: A Comprehensive Literature Review
2025 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 13, article id 3596632Article, review/survey (Refereed) Published
Abstract [en]

Virtual manufacturing, simulation, and optimization provide a wealth of knowledge about the possibilities of future production systems so as to support decision makers. However, this knowledge usually remains with a handful of domain experts, is not captured and is hard to share even within the same team. At the same time, simulations can benefit from the incorporation of linked data from real factories once a process is running. Graph databases provide a possible approach to storing and managing this form of interrelated heterogeneous data, with powerful querying capabilities that can identify important or interesting patterns that might otherwise remain hidden. Current research focuses on one or two aspects of this problem but does not address all at once, despite the potential benefits of the combination. This paper provides a broad literature review of the current directions within research with a special focus on how graphs can support finding knowledge within Virtual Factories, used by larger teams for industrial planning and optimization.

Place, publisher, year, edition, pages
IEEE, 2025
Keywords
Graph database, Industry 4.0, Knowledge graphs, Optimization, Simulation, Database systems, Decision making, Graph theory, Industrial plants, Industrial research, Knowledge graph, Query processing, Reviews, Virtual corporation, Virtual reality, Group Decision Making, Literature reviews, Manufacturing simulation, Optimisations, Production system, Simulation and optimization, Virtual manufacturing
National Category
Production Engineering, Human Work Science and Ergonomics Computer Sciences Computer Systems
Research subject
Virtual Production Development (VPD); VF-KDO
Identifiers
urn:nbn:se:his:diva-25767 (URN)10.1109/ACCESS.2025.3596632 (DOI)001565196100022 ()2-s2.0-105013130528 (Scopus ID)
Funder
Knowledge Foundation, 20180011
Note

CC BY 4.0

Received 27 May 2025, accepted 7 July 2025, date of publication 7 August 2025, date of current version 28 August 2025.

Correspondence Address: R. Senington; University of Skövde, School of Engineering Science, Skövde, 541 28, Sweden; email: richard.james.senington@his.se

This work was supported in part by the Virtual Factories with Knowledge-Driven Optimization (VF-KDO) Research Project under Grant 20180011, and in part by the Knowledge Foundation (KK-Stiftelsen).

Available from: 2025-08-28 Created: 2025-08-28 Last updated: 2026-05-21Bibliographically approved
Mittermeier, L., Ng, A. H. C., Senington, R., Fässberg, T. & Johansson, D. (2025). Supporting Knowledge-Driven Optimization and Decision Support with a Graph Database: An Industrial Use Case. In: Anna Syberfeldt; Amos Ng; Philippe Geril (Ed.), 23rd International Industrial Simulation Conference, ISC 2025: . Paper presented at 23rd International Industrial Simulation Conference, ISC 2025, June 3-5, 2025, University of Skövde, Sweden (pp. 71-78). EUROSIS
Open this publication in new window or tab >>Supporting Knowledge-Driven Optimization and Decision Support with a Graph Database: An Industrial Use Case
Show others...
2025 (English)In: 23rd International Industrial Simulation Conference, ISC 2025 / [ed] Anna Syberfeldt; Amos Ng; Philippe Geril, EUROSIS , 2025, p. 71-78Conference paper, Published paper (Refereed)
Abstract [en]

In recent years graph databases (GDBs) have become popular for managing large amounts of data. Especially the capability to integrate and link heterogeneous data is a driving factor for its success. This makes it a promising tool to support knowledge driven optimization (KDO), which involves various types of data, information, and artifacts. In particular, the link between simulation model, optimization algorithms with their parameters, results, and preferences of the stakeholders is interesting for investigation and traceability. In this paper, we propose a simple ontology as a schema for a KDO graph database and demonstrate how it can be used with an industrial use case. Furthermore, we highlight the ability to add lower level model information from an industrial use case to the GDB. 

Place, publisher, year, edition, pages
EUROSIS, 2025
Keywords
Graph Database, Knowledge-Driven Optimization, Simulation-Based Optimization, Knowledge graph, Optimization, Decision supports, Driving factors, Heterogeneous data, Industrial use case, Large amounts of data, Optimisations, Simulation-based optimizations, Supporting knowledge, Database systems
National Category
Computer Sciences Computer Systems
Research subject
Virtual Production Development (VPD); VF-KDO
Identifiers
urn:nbn:se:his:diva-25715 (URN)2-s2.0-105011590838 (Scopus ID)978-94-92859-35-8 (ISBN)
Conference
23rd International Industrial Simulation Conference, ISC 2025, June 3-5, 2025, University of Skövde, Sweden
Note

© 2025 EUROSIS-ETI

Available from: 2025-08-11 Created: 2025-08-11 Last updated: 2026-07-07Bibliographically approved
Mittermeier, L., Senington, R., Bandaru, S. & Ng, A. H. C. (2024). Knowledge Graphs for Supporting Group Decision Making in Manufacturing Industries. In: Joel Andersson; Shrikant Joshi; Lennart Malmsköld; Fabian Hanning (Ed.), Sustainable Production through Advanced Manufacturing, Intelligent Automation and Work Integrated Learning: Proceedings of the 11th Swedish Production Symposium (SPS2024). Paper presented at 11th Swedish Production Symposium, SPS 2024 Trollhättan 23 April 2024 through 26 April 2024 (pp. 464-475). IOS Press
Open this publication in new window or tab >>Knowledge Graphs for Supporting Group Decision Making in Manufacturing Industries
2024 (English)In: Sustainable Production through Advanced Manufacturing, Intelligent Automation and Work Integrated Learning: Proceedings of the 11th Swedish Production Symposium (SPS2024) / [ed] Joel Andersson; Shrikant Joshi; Lennart Malmsköld; Fabian Hanning, IOS Press, 2024, p. 464-475Conference paper, Published paper (Refereed)
Abstract [en]

Group decision making is traditionally a human-centered process, where communication, synchronization and agreement are driven by the stakeholders involved. In the area of multi-objective optimization (MOO), this becomes a challenge, because MOO usually produces a large amount of trade-off solutions that need to be analyzed and discussed by the stakeholders. Moreover, for transparent group decision making, it is important that each decision maker is able to trace the entire decision process – from associated data and models to problem formulation and solution generation, as well as to the preferences and analyses of other decision makers. A graph database is capable of capturing such diverse information in the form of a knowledge graph. It can be used to store and query all dependencies and hence can support complex decision-making tasks. Further advantages are the inherent suitability for visualization and the possibilities for pattern matching, graph analytics and, if semantically enriched, to infer new connections in the graph. In this paper, we show how such a knowledge graph can be used to support more transparent and traceable decision-making activities, particularly when multiple stakeholders with differing preferences or perspectives are involved. 

Place, publisher, year, edition, pages
IOS Press, 2024
Series
Advances in Transdisciplinary Engineering, ISSN 2352-751X, E-ISSN 2352-7528 ; 52
Keywords
group decision making, knowledge graph, multi-objective optimization, Decision making, Economic and social effects, Pattern matching, Query processing, Decision makers, Decision process, Decisions makings, Knowledge graphs, Large amounts, Manufacturing industries, Multi-objectives optimization, Problem solutions, Tradeoff solution, Multiobjective optimization
National Category
Computer Sciences Production Engineering, Human Work Science and Ergonomics
Research subject
Virtual Production Development (VPD); VF-KDO
Identifiers
urn:nbn:se:his:diva-23822 (URN)10.3233/ATDE240189 (DOI)001229990300039 ()2-s2.0-85191354828 (Scopus ID)978-1-64368-510-6 (ISBN)978-1-64368-511-3 (ISBN)
Conference
11th Swedish Production Symposium, SPS 2024 Trollhättan 23 April 2024 through 26 April 2024
Note

CC BY-NC 4.0 DEED

© 2024 The Authors

Correspondence Address: L. Mittermeier; University of Skövde, School of Engineering Science, Sweden; email: ludwig.mittermeier@his.se

Available from: 2024-05-13 Created: 2024-05-13 Last updated: 2026-07-01Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0009-0006-6208-4790

Search in DiVA

Show all publications