Using Decision Trees Supported by Data Mining to Improve Function-Based Design

Ferrero, Vincenzo; Alqseer, Naser; Tensa, Melissa; DuPont, Bryony

doi:10.1115/detc2020-22498

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other research, association rules and weighted confidence has been used to determine the function of a component within product configurations [35,36,37]. Decision trees have proved useful in reducing the feasible design space of functional assignment when considering product assembly [38]. Furthermore, deep learning approaches have been used to disambiguate customer reviews based on function, form, and behavior [39].…”

Section: Function-based Product Designmentioning

confidence: 99%

Classifying Component Function in Product Assemblies with Graph Neural Networks

Ferrero¹,

Hassani²,

Grandi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Function is defined as the ensemble of tasks that enable the product to complete the designed purpose. Functional tools, such as functional modeling, offer decision guidance in the early phase of product design, where explicit design decisions are yet to be made. Function-based design data is often sparse and grounded in individual interpretation. As such, function-based design tools can benefit from automatic function classification to increase data fidelity and provide function representation models that enable function-based intelligent design agents. Functionbased design data is commonly stored in manually generated design repositories. These design repositories are a collection of expert knowledge and interpretations of function in product design bounded by function-flow and component taxonomies. In this work, we represent a structured taxonomy-based design repository as assembly-flow graphs, then leverage a graph neural network (GNN) model to perform automatic function classification. We support automated function classification by learning from repository data to establish the ground truth of component function assignment. Experimental results show that our GNN model achieves a micro-average F 1 -score of 0.832 for tier 1 (broad), 0.756 for tier 2, and 0.783 for tier 3 (specific) functions. Given the imbalance of data features, the results are encouraging. Our efforts in this paper can be a starting point for more sophisticated applications in knowledge-based CAD systems and Design-for-X consideration in function-based design.

show abstract

Section: Function-based Product Designmentioning

confidence: 99%

Classifying Component Function in Product Assemblies with Graph Neural Networks

Ferrero¹,

Hassani²,

Grandi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Evolving to multi-modal knowledge graphs for engineering design: state-of-the-art and future challenges

Pan,

Li,

et al. 2024

Journal of Engineering Design

View full text Add to dashboard Cite

Do Human and Computational Evaluations of Similarity Align? An Empirical Study of Product Function

Nandy

Goucher-Lambert

2022

Journal of Mechanical Design

View full text Add to dashboard Cite

Function drives many early design considerations in product development, highlighting the importance of finding functionally similar examples when searching for sources of inspiration or evaluating designs against existing technology. However, it is difficult to capture what people consider to be functionally similar and therefore, if measures that compare function directly from the products themselves are meaningful. In this work, human evaluations of similarity are compared to computationally determined values, shedding light on how quantitative measures align with human perceptions of functional similarity. Human perception of functional similarity is considered at two levels of abstraction: (1) the high-level purpose of a product, and (2) a detailed view of how the product works. These human evaluations of similarity are quantified by crowdsourcing 1360 triplet ratings at each functional abstraction and creating low-dimensional embeddings from the triplets. The triplets and embeddings are then compared to similarity that is computed between functional models using six representative measures, including matching measures like cosine similarity and network-based measures like spectral distance. The outcomes demonstrate how different levels of abstraction and the fuzzy line between what is considered “highly similar” and “somewhat similar” may impact functional similarity representations by humans and subsequently affect how computed similarity aligns with these representations. The results inform how functional similarity can be leveraged by designers and therefore, applications lie in creativity support tools, such as those used for design-by-analogy, or future computational methods in design that incorporate product function.

show abstract

Using Decision Trees Supported by Data Mining to Improve Function-Based Design

Cited by 6 publications

References 0 publications

Classifying Component Function in Product Assemblies with Graph Neural Networks

Classifying Component Function in Product Assemblies with Graph Neural Networks

Evolving to multi-modal knowledge graphs for engineering design: state-of-the-art and future challenges

Do Human and Computational Evaluations of Similarity Align? An Empirical Study of Product Function

Contact Info

Product

Resources

About