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
Using Dynamic Programming and Reinforcement Learning for Exploring Tradespaces in Changeability Assessment
Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.ORCID iD: 0000-0001-7581-439x
Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.ORCID iD: 0000-0001-5114-4811
Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.ORCID iD: 0000-0002-9662-4576
2025 (English)In: Proceedings of the ASME 2025 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: Volume 2B: 45th Computers and Information in Engineering Conference (CIE), ASME Press, 2025Conference paper, Published paper (Refereed)
Abstract [en]

The construction machinery industry faces many uncertainties stemming from environmental, operational, and market-related factors. To mitigate future risks, development teams often favor more broadly applicable solutions compared to localized performance gains in specific scenarios. This situation highlights the necessity of incorporating changeability in these solutions for developing value-robust systems that can manage future uncertainty. Changeability assessment relies on an effective tradespace exploration that provides a unified view of different system configurations and control policies. To support the design teams in exploring such tradespaces, this paper presents an approach combining Dynamic Programming (DP) and Reinforcement Learning (RL) for evaluating optimal control policies, illustrated through a wheel loader application. The underlying basis is that the overall task can be decomposed into several sub-tasks to be solved by DP or RL selectively. A control policy combined from these sub-tasks is presented along with an illustrative tradespace mapping system attributes. The results show that by combining the strengths of DP and RL, the proposed approach can be beneficial when exploring a wide range of solutions. It allows direct comparisons between configuration and control policy changes, which is crucial for effective changeability assessment. However, several limitations have been acknowledged and will be addressed in future studies.

Place, publisher, year, edition, pages
ASME Press, 2025.
Keywords [en]
Systems Engineering (SE), Simulation-based design, Multiobjective Optimization, Design for changeability.
National Category
Computer Sciences Production Engineering, Human Work Science and Ergonomics
Research subject
Mechanical Engineering
Identifiers
URN: urn:nbn:se:bth-28428DOI: 10.1115/DETC2025-164521Scopus ID: 2-s2.0-105024217404ISBN: 9780791889213 (print)OAI: oai:DiVA.org:bth-28428DiVA, id: diva2:1986136
Conference
ASME 2025 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Anaheim, Aug 17-20, 2025
Part of project
Future Fossil Free Rock Loading Solution, Vinnova
Funder
Vinnova, 2022-00578Available from: 2025-07-30 Created: 2025-07-30 Last updated: 2026-01-02Bibliographically approved
In thesis
1. Changeability Assessment in Complex Systems to Support Early-Stage Design Decisions
Open this publication in new window or tab >>Changeability Assessment in Complex Systems to Support Early-Stage Design Decisions
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The early design phase of complex, capital-intensive systems is critical for shaping their architecture and value proposition. However, such systems face numerous challenges from technological, economic, market, and regulatory domains. In addition, considering system-of-systems introduces new hurdles as the focus shifts from measuring performance to assessing overall effectiveness. Together with the growing trend of servitization, where traditional products are combined with value-added services to deliver functions, a lot of uncertainty is introduced during design decision-making. To handle these uncertainties, systems engineering literature advocates for incorporating lifecycle properties into the system that enable the system to deal with these uncertainties once deployed. Systems that consistently meet evolving stakeholder expectations, despite the changing contexts, are called value-robust systems. Changeability is one such property that allows the system to achieve value robustness by changing internally in response to changes externally. During the design stages, the goal is to identify and integrate options that would enable the system to exercise change and sustain value under all conditions.

In this light, this thesis aims to support the integration of changeability in complex systems by facilitating its assessment during the early design stages. To achieve this goal, it first identifies the existing methods and challenges in changeability assessment for achieving value robustness. To address these challenges, it proposes the Changeability Assessment in Systems during Early Design (CASED) method, which supports development teams in creating value-robust systems in the face of uncertainty. CASED is one of the core contributions of this work, allowing a holistic consideration of identification, quantification, and valuation of changeability during early design stages. It maps the expected mean value and expected standard deviation for each design as a function of changeability level, which serves as a guide for decisions concerning changeability. Additionally, this thesis explores the use of Extended Reality technologies to address perceptual complexity by visualizing operational scenarios and proposes designing for changeability as a mechanism for creating value-robust circular systems.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Tekniska Högskola, 2025. p. 100
Series
Blekinge Institute of Technology Doctoral Dissertation Series, ISSN 1653-2090 ; 2025:09
Keywords
Uncertainty, Changeability assessment, Value robustness, Early design stages, Systems Engineering, Product-Service Systems
National Category
Mechanical Engineering
Research subject
Mechanical Engineering
Identifiers
urn:nbn:se:bth-28429 (URN)978-91-7295-507-3 (ISBN)
Public defence
2025-09-18, J1630, Campus Gräsvik, Karlskrona, 09:15 (English)
Opponent
Supervisors
Available from: 2025-08-11 Created: 2025-07-30 Last updated: 2025-09-30Bibliographically approved

Open Access in DiVA

fulltext(1669 kB)22 downloads
File information
File name FULLTEXT02.pdfFile size 1669 kBChecksum SHA-512
156eb22248d968f02233377c7b7fcedd251f8ee27f34755a2a796e8bee891c67c670796785e047e846866c3a13655cd6f4780d4a70b7c92a9e08573986570af5
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Machchhar, Raj JitenBertoni, AlessandroLarsson, Tobias

Search in DiVA

By author/editor
Machchhar, Raj JitenBertoni, AlessandroLarsson, Tobias
By organisation
Department of Mechanical Engineering
Computer SciencesProduction Engineering, Human Work Science and Ergonomics

Search outside of DiVA

GoogleGoogle Scholar
Total: 23 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: 450 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