System disruptions
We are currently experiencing disruptions on the search portals due to high traffic. We are working to resolve the issue, you may temporarily encounter an error message.
Change search
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
Correlation-based feature extraction from computer-aided design, case study on curtain airbags design
Jönköping University, School of Engineering, JTH, Industrial Product Development, Production and Design, JTH, Product design and development (PDD).ORCID iD: 0000-0002-7894-7734
Department of Mechanical Engineering, School of Engineering Science, University of Skövde, Skövde, Sweden.
Jönköping University, School of Engineering, JTH, Industrial Product Development, Production and Design, JTH, Produktionsutveckling.
Autoliv AB, Vårgårda, Sweden.
Show others and affiliations
2022 (English)In: Computers in industry (Print), ISSN 0166-3615, E-ISSN 1872-6194, Vol. 138, article id 103634Article in journal (Refereed) Published
Abstract [en]

Many high-level technical products are associated with changing requirements, drastic design changes, lack of design information, and uncertainties in input variables which makes their design process iterative and simulation-driven. Regression models have been proven to be useful tools during design, altering the resource-intensive finite element simulation models. However, building regression models from computer-aided design (CAD) parameters is associated with challenges such as dealing with too many parameters and their low or coupled impact on studied outputs which ultimately requires a large training dataset. As a solution, extraction of hidden features from CAD is presented on the application of volume simulation of curtain airbags concerning geometric changes in design loops. After creating a prototype that covers all aspects of a real curtain airbag, its CAD parameters have been analyzed to find out the correlation between design parameters and volume as output. Next, using the design of the experiment latin hypercube sampling method, 100 design samples are generated and the corresponding volume for each design sample was assessed. It was shown that selected CAD parameters are not highly correlated with the volume which consequently lowers the accuracy of prediction models. Various geometric entities, such as the medial axis, are used to extract several hidden features (referred to as sleeping parameters). The correlation of the new features and their performance and precision through two regression analyses are studied. The result shows that choosing sleeping parameters as input reduces dimensionality and the need to use advanced regression algorithms, allowing designers to have more accurate predictions (in this case approximately 95%) with a reasonable number of samples. Furthermore, it was concluded that using sleeping parameters in regression-based tools creates real-time prediction ability in the early development stage of the design process which could contribute to lower development lead time by eliminating design iterations.

Place, publisher, year, edition, pages
Elsevier, 2022. Vol. 138, article id 103634
Keywords [en]
CAD/CAE, Curtain Airbag, Design Automation, Feature extraction, Machine Learning, Medial Axis, Parametric models, Regression Analysis, Computer aided design, Computer aided engineering, Extraction, Forecasting, Iterative methods, Large dataset, Sleep research, Computer-aided design, Computer-aided design/CAE, Design automations, Design parameters, Design-process, Features extraction, Machine-learning, Medial axes, Regression modelling
National Category
Vehicle and Aerospace Engineering
Identifiers
URN: urn:nbn:se:hj:diva-55973DOI: 10.1016/j.compind.2022.103634ISI: 000772755800002Scopus ID: 2-s2.0-85124806561Local ID: HOA;;798384OAI: oai:DiVA.org:hj-55973DiVA, id: diva2:1641841
Funder
Knowledge Foundation, 20180189Available from: 2022-03-03 Created: 2022-03-03 Last updated: 2025-02-14Bibliographically approved
In thesis
1. Data-driven and real-time prediction models for iterative and simulation-driven design processes
Open this publication in new window or tab >>Data-driven and real-time prediction models for iterative and simulation-driven design processes
2022 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

The development of more complex products has increased dependency on virtual/digital models and emphasized the role of simulations as a means of validation before production. This level of dependency on digital models and simulation togetherwith the customization level and continuous requirement change leads to a large number of iterations in each stage of the product development process. This research, studies such group of products that have multidisciplinary, highly iterative, and simulation-driven design processes. It is shown that these high-level technical products, which are commonly outsourced to suppliers, commonly suffer from a long development lead time. The literature points to several research tracks including design automation and data-driven design with possible support. After studying the advantages and disadvantages of each track, a data-driven approachis chosen and studied through two case studies leading to two supporting tools that are expected to improve the development lead time in associated design processes. Feature extraction in CAD as a way to facilitate metamodeling is proposed as the first solution. This support uses the concept of the medial axis to find highly correlated features that can be used in regression models. As for the second supporting tool, an automated CAD script is used to produce a library of images associated with design variants. Dynamic relaxation is used to label each variant with its finite element solution output. Finally, the library is used to train a convolutions neural network that maps screenshots of CAD as input to finite element field answers as output. Both supporting tools can be used to create real-time prediction models in the early conceptual phases of the product development process to explore design space faster and reduce lead time and cost.

Abstract [sv]

Utvecklingen av mer komplexa produkter har ökat beroendet av virtuella/digitala modeller och ökat betydelsen av simuleringar för att validera en produkt inför produktion. Ett stort beroende av digitala modeller och simulering tillsammans med den individuella anpassningen och kontinuerliga kravförändringar leder till ett stort antal iterationer i varje steg i produktutvecklingsprocessen. Forskningen som presenteras i denna avhandling studerar denna typ av produkter som har multidisciplinära, mycket iterativa och simuleringsdrivna designprocesser. Det har visat sig att dessa tekniska produkter på hög nivå, som vanligtvis tillhandahålls av underleverantörer, vanligtvis har en lång ledtid för utveckling. Litteraturstudien pekar på flera forskningsspår, exempelvis designautomation och datadriven design, eventuellt med stöd. Efter att ha studerat fördelarna och nackdelarna med varje spår, väljs det datadrivna tillvägagångssättet och studeras genom två fallstudier som leder till att två stödjande verktyg tas fram. De förväntas förbättra utvecklingsledtiden i tillhörande designprocesser. Feature extraktion i CAD som ett sätt att underlätta metamodellering föreslås som det första verktyget. Detta stöd använder medial axis för att hitta korrelerade features som kan användas i regressionsmodeller. När det gäller det andra stödjande verktyget används ett automatiserat CAD-skript för att producera ett stort bibliotek med bilder som är associerade olika designvarianter. Dynamisk relaxation används för att märka varje variant med dess finita elementlösning. Slutligen används detta bibliotek för att träna ett konvolutionerande neuralt nätverk som kartlägger skärmdumpar av CAD som indata till finita elementfältsvar som utdata. Båda stödverktygen kan användas för att skapa modeller för förutsägelser i realtid i de tidiga konceptuella faserna av produktutvecklingsprocessen för att utforska designrymden snabbare och minska ledtid och kostnader.

Place, publisher, year, edition, pages
Jönköping: Jönköping University, School of Engineering, 2022. p. 59
Series
JTH Dissertation Series ; 071
Keywords
Development lead time; Iterative design; Simulation-driven design; Design automation; Data-driven design; Artificial Intelligence
National Category
Computer Sciences
Identifiers
urn:nbn:se:hj:diva-56577 (URN)978-91-87289-77-4 (ISBN)
Presentation
2022-06-14, E1405, Tekniska Högskolan, Jönköping University, Jönköping, 10:00 (Swedish)
Opponent
Supervisors
Funder
Knowledge Foundation
Available from: 2022-05-25 Created: 2022-05-25 Last updated: 2022-05-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Arjomandi Rad, MohammadCenanovic, MirzaRaudberget, DagStolt, Roland

Search in DiVA

By author/editor
Arjomandi Rad, MohammadCenanovic, MirzaRaudberget, DagStolt, Roland
By organisation
JTH, Product design and development (PDD)JTH, Produktionsutveckling
In the same journal
Computers in industry (Print)
Vehicle and Aerospace Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 335 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