CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
From tacit expertise to data-driven knowledge reuse in sheet metal forming tooling design
Jönköping University, School of Engineering, JTH, Product Development, Production and Design, JTH, Product design and development (PDD). Högskolebiblioteket i Jönköping.ORCID iD: 0000-0002-5480-6048
2026 (English)Licentiate thesis, comprehensive summary (Other academic)
Sustainable development
00. Sustainable Development, 09. Industry, innovation and infrastructure
Abstract [en]

Sheet metal forming tooling is a knowledge-intensive and tacit industrial domain in which early design decisions strongly influence lead time, manufacturability, cost, and tooling performance. Despite digital advances, tooling development still relies heavily on expert tacit knowledge, with limited structured reuse of past project knowledge. This thesis investigates how knowledge reuse can be supported in sheet-metal tooling design through a data-driven, case-based reasoning approach. The research work follows a design research methodology framework and comprises four studies, aligned with its phases. The Research Clarification phase aimed at developing an understanding of the current state of sheet metal tooling design and the industrial challenges affecting knowledge reuse. Descriptive Study 1 further investigated current industrial practice and identified challenges related to fragmented data storage and the limited use of digital technologies. These phases were based on literature reviews and interviews with industrial practitioners. The findings show that knowledge reuse is important, but existing engineering data and previous project experience are not systematically used. Based on these findings, the Prescriptive Study developed a data-driven framework for supporting knowledge reuse in sheet metal tooling design. The framework consists of different modules that can assess manufacturing difficulty, retrieve similar cases, and inform the performance of the retrieved tooling. The support was demonstrated through a proof-of-concept prototype, where machine learning classified sheet metal parts according to manufacturing difficulty and retrieved similar cases and corresponding performance indices. Descriptive Study II focused on the initial evaluation of the proposed support through prototype testing and workshops with industrial practitioners. The results indicate that the developed approach can support tooling engineers by structuring, searching, and reusing knowledge from previous projects. The results also show that manufacturing difficulty can serve as a meaningful abstraction for comparing sheet metal parts and support early-stage decision-making. The thesis contributes by showing how tacit tooling expertise can be represented in a reusable decision support approach for systematic early-stage tooling design.

Abstract [sv]

Konstruktion av plåtformningsverktyg är ett kunskapsintensivt område som till stor del är beroende av verktygskonstruktörernas kunskaper och erfarenheter. Konstruktionsfasen är viktig eftersom den i hög grad påverkar ledtid, tillverkningsbarhet, kostnad och verktygsprestanda. Det har på senare tid gjorts framsteg inom digitalisering, men stödet för strukturerad återanvändning av kunskaper och erfarenheter från tidigare projekt inom verktygskonstruktion är fortfarande begränsat. Denna avhandling undersöker hur återanvändning kan stödjas genom att ta fram en datadriven metod för att systematisera och återanvända tidigare fall. Forskningsarbetet följer ett metodologiskt ramverk som omfattar fyra faser. I den inledande förtydligandefasen utvecklades en förståelse för samtida verktygskonstruktion och de industriella utmaningar som finns. I den andra fasen undersöktes industripraxis och utmaningar kopplade till fragmenterad datalagring. Nivån av digitalisering undersöktes. Dessa två faser baserades på litteraturstudier och intervjuer med experter vid flera verktygsföretag. Resultaten visar att återanvändning av kunskap är viktig, men att data och tidigare projekterfarenhet inte samlas in och används på ett systematiskt sätt. Istället förlitar sig experterna på att de kommer ihåg tidigare projekt och kan hitta dokumentationen från dem. För att möta detta, utvecklades ett datadrivet ramverk för att stödja kunskapsåteranvändning. Ramverket består av flera moduler som automatiskt kan få tillgång till information om tillverkningssvårigheter, hämta liknande fall samt information om verktygsprestanda från tidigare projekt. Ramverket har demonstrerats genom en prototyp och har lett till ett ”proof-of-concept”, där maskininlärning klassificerade plåtdelar efter tillverkningssvårighet och hämtade liknande fall. Prototypen indikerade också hur väl de beprövade lösningarna fungerat i verklig produktion. I den sista fasen gjordes en initial utvärdering av det föreslagna stödet genom prototyptester och workshops med de industriella företagen. Resultaten visar att den utvecklade metoden kan stödja verktygsingenjörer i deras arbete. Avhandlingen visar också att graden av tillverkningssvårighet kan användas som grund för att jämföra plåtdelar och stödja tidiga konstruktionsbeslut. Avhandlingen bidrar genom att visa hur expertkunskap kan representeras och återanvändas som en beslutsstödsmetod i tidiga faser av verktygskonstruktion.

Place, publisher, year, edition, pages
Jönköping: Jönköping University, School of Engineering , 2026. , p. 63
Series
JTH Dissertation Series ; 105
Keywords [en]
Sheet Metal Tooling, Engineering Design, Artificial Intelligence, Machine Learning, Knowledge Reuse, Data-Driven Design
National Category
Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:hj:diva-73482ISBN: 9789189785434 (print)ISBN: 9789189785441 (electronic)OAI: oai:DiVA.org:hj-73482DiVA, id: diva2:2090277
Presentation
2026-08-27, E1405 (Gjuterisalen), Tekniska Högskolan, Jönköping, 09:00 (English)
Opponent
Supervisors
Available from: 2026-08-06 Created: 2026-08-06 Last updated: 2026-08-18Bibliographically approved
List of papers
1. Sheet Metal Forming Tooling: State of Art and Practice in Five Manufacturing Companies
Open this publication in new window or tab >>Sheet Metal Forming Tooling: State of Art and Practice in Five Manufacturing Companies
2024 (English)In: Flexible Automation and Intelligent Manufacturing: Manufacturing Innovation and Preparedness for the Changing World Order: Proceedings of FAIM 2024, June 23–26, 2024, Taichung, Taiwan, Volume 2 / [ed] Y-C Wang, S. H. Chan, Z-H Wang, Springer, 2024, Vol. 2, p. 206-214Conference paper, Published paper (Refereed)
Abstract [en]

There are several recent developments in technology and methods for the design, manufacture and operation of tooling for sheet metal forming. Technologies such as electric presses with accurately controlled motions and design tools such as forming simulations and AI technologies for knowledge capture and reuse are actively progressing. Manufacturing processes such as additive manufacturing and materials are advancing. There are advancements in the operation of the tooling via for example sensor technology. In this paper, a structured literature search is presented to understand the state of the art in sheet metal forming tooling. In addition, the paper presents an interview study with staff and management from five different industrial companies that are active in tooling design, manufacture, and operation. The objective is finding the current challenges for the companies and to what extent new technologies and methods are considered or being implemented to meet the current challenges. The interviews show that there are challenges concerning the lead time for tooling design and manufacture as well as the availability of the tooling in production. Although the companies have made recent investments, they are lacking the knowledge to fully exploit the potential of the new technologies. The paper strongly advocates for the utilization of technology to address the challenges within the tooling industry, aiming for enhanced efficiency and improved tooling design processes.

Place, publisher, year, edition, pages
Springer, 2024
Series
Lecture Notes in Mechanical Engineering, ISSN 2195-4356, E-ISSN 2195-4364
Keywords
Design challenges, Manufacturing challenges, Sheet metal forming, State of the art, technology, Metal forming, Process control, Sheet metal, Smart manufacturing, 'current, Controlled motions, Electric press, Manufacturing companies, Tooling design, Investments
National Category
Production Engineering, Human Work Science and Ergonomics
Identifiers
urn:nbn:se:hj:diva-66962 (URN)10.1007/978-3-031-74485-3_23 (DOI)001437172500023 ()2-s2.0-85213362068 (Scopus ID)978-3-031-74484-6 (ISBN)978-3-031-74485-3 (ISBN)
Conference
33rd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2024 Taichung 23 June 2024 through 26 June 2024
Available from: 2025-01-09 Created: 2025-01-09 Last updated: 2026-08-06Bibliographically approved
2. Exploring AI/ML approaches for CBR-enabled Knowledge Reuse in Sheet Metal Tooling Development
Open this publication in new window or tab >>Exploring AI/ML approaches for CBR-enabled Knowledge Reuse in Sheet Metal Tooling Development
2025 (English)In: Procedia CIRP: 35th CIRP Design 2025 / [ed] Dimitris Mourtzis, Elsevier, 2025, Vol. 136, p. 746-751Conference paper, Published paper (Refereed)
Abstract [en]

The sheet metal forming tooling industry is a highly specialized area. However, there seem to be similarities in the tasks executed and in the design solutions. This work has investigated what types of data are involved in the various steps in the design and manufacturing of sheet metal tooling in five different tooling firms. By analyzing these different types of data, the study explores possible avenues for employing AI/ML techniques for CBR-enabled knowledge reuse based on legacy data. The paper concludes that adopting AI/ML in knowledge reuse has the potential to significantly improve efficiency and innovation in tooling design and manufacturing.

Place, publisher, year, edition, pages
Elsevier, 2025
Series
Procedia CIRP, E-ISSN 2212-8271 ; 136
Keywords
Sheet metal forming, Data-driven methods, Design challenges, Knowledge reuse, Artificial Intelligence, Machine Learning
National Category
Production Engineering, Human Work Science and Ergonomics
Identifiers
urn:nbn:se:hj:diva-69657 (URN)10.1016/j.procir.2025.08.127 (DOI)2-s2.0-105015296117 (Scopus ID)
Conference
35th CIRP Design Conference (CIRP Design 2025), 2-4 April 2025, Patras, Greece
Available from: 2025-09-02 Created: 2025-09-02 Last updated: 2026-08-06Bibliographically approved

Open Access in DiVA

Spikblad(92 kB)30 downloads
File information
File name FULLTEXT04.pdfFile size 92 kBChecksum SHA-512
8097883e94f58bd0d228ed95e705efd6ffa2b1cc44a0cf6bd68ab5041cff43092cd7eac21953a7ec7bb959cc23d18b2f22b16c905ac0e03cbffafd74b4899dc4
Type spikbladMimetype application/pdf
Kappa(1644 kB)36 downloads
File information
File name FULLTEXT05.pdfFile size 1644 kBChecksum SHA-512
f3b7b9f639b745c2faf9056816227396f5722aba61610b3f36e02541f3a3d635bc44efb3776d04df1a1784a4f63c344f2cd471562ac4e6b13416f2dc3cae22d4
Type fulltextMimetype application/pdf

Authority records

Menon, Aju Sukumaran

Search in DiVA

By author/editor
Menon, Aju Sukumaran
By organisation
JTH, Product design and development (PDD)
Other Engineering and Technologies

Search outside of DiVA

GoogleGoogle Scholar
Total: 111 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

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 2326 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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