Reasoning support for predicting requirement change volatility using complex network metrics

Hein, Phyo Htet; Kames, Elisabeth; Chen, Cheng; Morkos, Beshoy

doi:10.1080/09544828.2022.2154051

Cited by 11 publications

(2 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate unexpected changes, the complexity of design change propagation necessitates the development of a volatility measure to estimate the reactions of engineering changes to the basic change instances Hein et al (2021Hein et al ( , 2022. Further, a topic model approach reduces the risks associated with unexpected change propagation by dividing requirements documents into interpretable groups from which propagation can be estimated Chen et al (2021).…”

Section: Requirements Management In Plmmentioning

confidence: 99%

From Text to Images: Linking System Requirements to Images Using Joint Embedding

Chen¹,

Carroll²,

Morkos³

2023

Proc. Des. Soc.

Self Cite

View full text Add to dashboard Cite

Smart manufacturing enterprises rely on adapting to rapid engineering changes while minimizing the generated risk. Making informed decisions related to engineering changes and managing risks against unexpected costs requires more information to be extracted from limited data. However, limited information in early-stage design can come in many forms, namely text and images. The development of innovative design tools and processes to link multisource data together is essential to assist designers in building model-based engineering (MBE) systems. However, the formal computational linking of multisource data is yet to be realized in MBE. We propose a framework to implement transfer learning and integrate domain specific knowledge to bridge this information gap. A synthetic dataset is created using web scraping techniques based on keywords extracted from the requirements. Requirement-image pairs are used to fine tune a contrastive language-image pretraining model to acquire domain knowledge. The results demonstrate how the content of images can be used to indicate all affected requirements for tracing engineering changes in a complex system.

show abstract

Section: Requirements Management In Plmmentioning

confidence: 99%

From Text to Images: Linking System Requirements to Images Using Joint Embedding

Chen¹,

Carroll²,

Morkos³

2023

Proc. Des. Soc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Much existing commercial software (i.e. IBM DOORS 35 or JAMA ‡ ) and many research tools (i.e., ARCPP 23 , ROM Client 11 ) can manage requirement repositories 36,37,38,39 . An alternative method is the design structure matrix (DSM) (i.e., affinity matrix, A ∈ R n×n ), which represents the relationship between the requirements of a complex system for tracing potential changes propagation 40,41,42,43 .…”

Section: Requirement Managementmentioning

confidence: 99%

Bridging the Knowledge Gap Between Design Requirements and CAD - A Joint Embedding Approach

Chen,

Wei,

Morkos

2023 ASEE Annual Conference &Amp; Exposition Proceedings

View full text Add to dashboard Cite

Cheng holds a Ph.D. in mechanical engineering from the University of Georgia and has published numerous papers on topics such as computational design, geometric modeling, and engineering education. He is always seeking innovative approaches to fill knowledge gaps and to assist in solving complex design issues. He is currently working on several projects to develop various natural language models for requirement management. Cheng is passionate about applying his domain expertise to improve STEM education, with an emphasis on how AI can be incorporated into design practices.

show abstract

A product requirement influence analysis method based on multilayer dynamic heterogeneous networks

Xu,

Dou,

Ouyang

et al. 2024

Advanced Engineering Informatics

View full text Add to dashboard Cite

Reasoning support for predicting requirement change volatility using complex network metrics

Cited by 11 publications

References 79 publications

From Text to Images: Linking System Requirements to Images Using Joint Embedding

From Text to Images: Linking System Requirements to Images Using Joint Embedding

Bridging the Knowledge Gap Between Design Requirements and CAD - A Joint Embedding Approach

A product requirement influence analysis method based on multilayer dynamic heterogeneous networks

Contact Info

Product

Resources

About