Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A System Architecture for Continuous Manufacturing Decision Support Using Knowledge Generated from Multi-Level Simulation-Based Optimization
University of Skövde, School of Engineering Science. University of Skövde, Virtual Engineering Research Environment. Powertrain Production, Volvo Group Trucks Operations, Skövde, Sweden. (Virtual Production Development (VPD))ORCID iD: 0000-0003-1215-152X
University of Skövde, School of Engineering Science. University of Skövde, Virtual Engineering Research Environment. Division of Industrial Engineering and Management, Uppsala University, Sweden. (Virtual Production Development (VPD))ORCID iD: 0000-0003-0111-1776
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. 231-243Conference paper, Published paper (Refereed)
Abstract [en]

Manufacturing is becoming increasingly complex as product life cycles shorten, and new disruptive technologies are introduced. The increased complexity in the manufacturing footprint also complicates industrial decision-making. Proposed improvements to alleviate bottlenecks do not guarantee effective problem resolution. Instead, improvement efforts can become misguided, targeting a bottleneck that affects a single production line rather than the entire site. An effective method for identifying production issues and predicting system performance is discrete-event simulation. When coupled with multi-objective optimization and multi-level modeling, production performance issues can be identified at both the site and workstation levels. However, optimization studies yield vast amounts of data, which can be challenging to extract useful knowledge from. To address this, we employ data-mining methods to assist decision-makers in extracting valuable insights from optimization data. This study presents an architecture for a decision support system that utilizes simulation-based optimization to continuously aid in industrial decision-making. Through a novel model generation method, simulation models are automatically generated and updated using logged data from the manufacturing shop floor and product lifecycle management systems. To reduce the computational complexity of the optimization, model simplification, varying replication numbers, surrogate modeling, and parallel computing in the cloud are also employed within this architecture. The results are presented to a decision-maker in an intelligent decision-support system, allowing for timely and relevant industrial decisions. 

Place, publisher, year, edition, pages
IOS Press, 2024. p. 231-243
Series
Advances in Transdisciplinary Engineering, ISSN 2352-751X, E-ISSN 2352-7528 ; 52
Keywords [en]
decision-support system, discrete-event simulation, industrial case study, knowledge discovery, multi-objective optimization, Architecture, Artificial intelligence, Computer architecture, Decision making, Decision support systems, Discrete event simulation, Information management, Life cycle, Multiobjective optimization, Continuous manufacturing, Decision makers, Decision supports, Decisions makings, Discrete-event simulations, Multi-objectives optimization, Multilevels, Simulation-based optimizations, Systems architecture, Data mining
National Category
Production Engineering, Human Work Science and Ergonomics Computer Sciences
Research subject
Virtual Production Development (VPD)
Identifiers
URN: urn:nbn:se:his:diva-23830DOI: 10.3233/ATDE240168ISI: 001229990300019Scopus ID: 2-s2.0-85191304483ISBN: 978-1-64368-510-6 (print)ISBN: 978-1-64368-511-3 (electronic)OAI: oai:DiVA.org:his-23830DiVA, id: diva2:1857266
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: S. Lidberg; Högskolan i Skövde, Högskolevägen, Skövde, Box 408, Sweden; email: simon.lidberg@his.se

Available from: 2024-05-13 Created: 2024-05-13 Last updated: 2024-09-17Bibliographically approved
In thesis
1. Decision Support Architecture: Improvement Management of Manufacturing Sites Through Multi-Level Simulation-Based Optimization
Open this publication in new window or tab >>Decision Support Architecture: Improvement Management of Manufacturing Sites Through Multi-Level Simulation-Based Optimization
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Manufacturing companies face a complex world with ever-changing demands, globalization, sustainability concerns, and economic challenges. Accurate improvement management and predicting future performance are crucial for staying competitive. Discrete-Event Simulation (DES) helps capture the dynamics of complex production systems, and Simulation-Based Optimization (SBO) can identify improvements with these models. However, past optimization approaches focused on individual production lines, which could lead to sub-optimizations when considering the performance of the manufacturing site. This research proposes a multi-level optimization approach for improvement management focusing on the performance of the manufacturing site.

High computational complexity resulting from combining several detailed models to create the site-level model is an obstacle to presenting decision support in a timeframe suitable for industrial decision-making. The research addresses this by validating a simplification method for DES models which replaces detailed models with simpler ones, sacrificing some detail and accuracy for faster runtime performance, enabling SBO for the site and supply chain level. %This is the first major contribution of this dissertation. 

The second part presents a Decision Support Architecture (DSA) using SBO to optimize site performance. The process starts by identifying the most critical bottleneck line on the entire site, including the specific parameter causing the issue, e.g., processing time or downtime. This approach prioritizes improvements with the highest impact for the least resource expenditure. Following this analysis, individual production lines are further optimized to identify specific equipment and parameters for improvement. Knowledge extraction algorithms then prioritize these improvements, guiding efforts and ensuring they benefit the entire site. Allowing for more efficient resource management, confidence that the proposed improvements are beneficial for the site, and improved decision-making at the site level.

The main novel research outcome of this dissertation lies in the multi-level optimization approach, combined with knowledge extraction and SBO enabled by simplified simulation models. This framework provides valuable insights for optimizing manufacturing sites in a complex and dynamic environment.

Abstract [sv]

Dagens tillverkningsindustrier behöver konkurrera i en omvärld som präglas av föränderliga krav, globalisering, krav på hållbarhet, och ekonomiska utmaningar. Noggrann förbättringshantering och möjligheten att kunna uppskatta framtida prestanda i produktionssystemen är avgörande för att förbli konkurrenskraftiga. Discrete-Event Simulation (DES) och Simulation-Based Optimization (SBO) är kraftfulla verktyg för att modellera och optimera komplexa produktionssystem. SBO har tidigare använts främst för enskilda produktionslinjer, vilket kan leda till suboptimeringar om hänsyn tas till hela systemets prestanda. Detta vetenskapliga bidrag föreslår ett angreppsätt där flernivå-optimering nyttjas för att fokusera på resultatet för hela systemet.

För att övervinna utmaningen med långa beräkningstider för komplexa modeller, utvärderar denna forskning en metod för att förenkla DES-modeller. Genom att minska detaljnoggrannheten kan beräkningstiden reduceras, vilket möjliggör snabbare SBO-analys av hela fabriker och värdeflöden. Denna förenklingsmetod är avgörande för att kunna erbjuda beslutsstöd inom en rimlig tid för industriellt beslutsfattande. Detta bidrag utgör avhandlingens första del.

Avhandlingens andra del presenterar en beslutstödsarkitektur, kallad Decision Support Architecture (DSA), som nyttjar SBO för att optimera fabriksprestanda. Processen inleds med att identifiera den mest kritiska flaskhalsen i produktionssystemet och den specifika parametern som behöver förbättras. Den här metoden prioriterar förbättringar med störst effekt för minsta resursförbrukning. Efter denna analys optimeras varje enskild produktionslinje med detaljerade modeller för att identifiera vilken utrustning och parameter som ger störst effekt på förbättringen. Algoritmer för kunskapsutvinning används sedan för att prioritera dessa förbättringar baserat på deras effekt på hela fabrikens prestanda, vilket leder till effektivare resurshantering och förbättrat beslutsfattande på fabriksnivå.

Det största vetenskapliga bidraget från denna avhandling utgörs av den utvecklade metoden för optimering på flera nivåer i kombination med kunskapsutvinning och SBO som möjliggörs av förenklade simuleringsmodeller. Detta ramverk ger värdefulla insikter för att optimera hela tillverkningssystem i en komplex och dynamisk miljö.

Place, publisher, year, edition, pages
Skövde: University of Skövde, 2024. p. 275
Series
Dissertation Series ; 61
National Category
Computer Systems Production Engineering, Human Work Science and Ergonomics
Research subject
Virtual Production Development (VPD); VF-KDO
Identifiers
urn:nbn:se:his:diva-24455 (URN)978-91-987907-5-7 (ISBN)978-91-987907-6-4 (ISBN)
Public defence
2024-10-18, ASSAR, Kavelbrovägen 2B, 541 36, Skövde, 10:00 (English)
Opponent
Supervisors
Funder
Knowledge Foundation
Note

Smart Industry Sweden research school

In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of University of Skövde's products or services. Internal or personal use of this material is permitted. If interested in reprinting/republishing IEEE copyrighted material for advertising or promotional purposes or for creating new collective works for resale or redistribution, please go to http://www.ieee.org/publications_standards/publications/rights/rights_link.html to learn how to obtain a License from RightsLink.

Två av fyra delarbeten (övriga se rubriken Delarbeten/List of papers):

3. Lidberg, Simon, Frantzén, Marcus, Aslam, Tehseen, and Ng, Amos H. C. (2024). “Model Simplification for Optimized Manufacturing Site Improvement Management”. Manuscript submitted to an international journal.

6. Lidberg, Simon (2024). “Multi-level simulation-based optimization in the cloud for continuous industrial decision support”. In: Ng, Amos H.C. and Bandaru, Sunith. Virtual Factories and Knowledge-Driven Optimization. Under review, pp. 1–20.

Available from: 2024-09-18 Created: 2024-09-17 Last updated: 2024-11-22Bibliographically approved

Open Access in DiVA

fulltext(843 kB)152 downloads
File information
File name FULLTEXT01.pdfFile size 843 kBChecksum SHA-512
6bbedd0738eb3011f7dc0249c6bb8cd0c82f747c94621f4ce224f0e1800c6cc0eb08711721d512a21e991212bcd183ddd94c0124a479faa2599a7fe1fd1d6051
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Lidberg, SimonNg, Amos H. C.

Search in DiVA

By author/editor
Lidberg, SimonNg, Amos H. C.
By organisation
School of Engineering ScienceVirtual Engineering Research Environment
Production Engineering, Human Work Science and ErgonomicsComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 152 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 589 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf