More Like this

1. MODELLING THE DESIGN OF MODELS: AN EXAMPLE USING CRISP-DM

   https://doi.org/10.1017/pds.2023.271  

   Kannengiesser, Udo; Gero, John S (July 2023, Proceedings of the Design Society)

   Editor, A (Ed.)

   Abstract Design is widely understood as a domain-independent notion, comprising any activity concerned with creating artefacts. This paper shows that models can be viewed as artefacts, and that the design of models resembles the design of artefacts in other domains. The function-behaviour-structure (FBS) ontology of design is applied to models, mapping generic characteristics of models derived from literature on modelling onto basic, design-ontological categories. An example of model design, namely the CRISP-DM model for designing data mining models, is analysed and compared with models of designing in other domains (systems engineering, mechanical engineering, software engineering, and service design). The results show that there are fundamental commonalities but also differences, revealing the need for further research in developing a theory of model design. 

   more » « less
2. Predicting Sequential Design Decisions Using the Function-Behavior-Structure Design Process Model and Recurrent Neural Networks

   https://doi.org/10.1115/1.4049971  

   Rahman, Molla Hafizur; Xie, Charles; Sha, Zhenghui (August 2021, Journal of Mechanical Design)

   null (Ed.)

   Abstract In engineering systems design, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are essential to the development of new algorithms embedded with human intelligence to augment the computational design. In this paper, we develop a deep learning-based approach to model and predict designers’ sequential decisions in the systems design context. The core of this approach is an integration of the function-behavior-structure (FBS) model for design process characterization and the long short-term memory unit (LSTM) model for deep leaning. This approach is demonstrated in two case studies on solar energy system design, and its prediction accuracy is evaluated benchmarking on several commonly used models for sequential design decisions, such as the Markov Chain model, the Hidden Markov Chain model, and the random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to rely on both short-term and long-term memory of past design decisions in guiding their future decision-making in the design process. Our approach can support human–computer interactions in design and is general to be applied in other design contexts as long as the sequential data of design actions are available. 

   more » « less
3. Design representation for performance evaluation of 3D shapes in structure-aware generative design

   https://doi.org/10.1017/dsj.2023.25  

   Li, Xingang; Xie, Charles; Sha, Zhenghui (January 2023, Design Science)

   Abstract Data-driven generative design (DDGD) methods utilize deep neural networks to create novel designs based on existing data. The structure-aware DDGD method can handle complex geometries and automate the assembly of separate components into systems, showing promise in facilitating creative designs. However, determining the appropriate vectorized design representation (VDR) to evaluate 3D shapes generated from the structure-aware DDGD model remains largely unexplored. To that end, we conducted a comparative analysis of surrogate models’ performance in predicting the engineering performance of 3D shapes using VDRs from two sources: the trained latent space of structure-aware DDGD models encoding structural and geometric information and an embedding method encoding only geometric information. We conducted two case studies: one involving 3D car models focusing on drag coefficients and the other involving 3D aircraft models considering both drag and lift coefficients. Our results demonstrate that using latent vectors as VDRs can significantly deteriorate surrogate models’ predictions. Moreover, increasing the dimensionality of the VDRs in the embedding method may not necessarily improve the prediction, especially when the VDRs contain more information irrelevant to the engineering performance. Therefore, when selecting VDRs for surrogate modeling, the latent vectors obtained from training structure-aware DDGD models must be used with caution, although they are more accessible once training is complete. The underlying physics associated with the engineering performance should be paid attention. This paper provides empirical evidence for the effectiveness of different types of VDRs of structure-aware DDGD for surrogate modeling, thus facilitating the construction of better surrogate models for AI-generated designs. 

   more » « less
4. A Foreshock Bubble Driven by an IMF Tangential Discontinuity: 3D Global Hybrid Simulation

   https://doi.org/10.1029/2021GL093068  

   Wang, Chih‐Ping; Wang, Xueyi; Liu, Terry Z.; Lin, Yu (May 2021, Geophysical Research Letters)

   Abstract Foreshock bubbles (FBs) have been observed upstream of solar wind tangential discontinuities (TDs). A hypothesized mechanism is that foreshock ions with gyroradii larger than the TD thickness may move to upstream side of TDs and generate FBs. In this study, we present the very first three‐dimensional global hybrid simulation of an FB driven by a TD. After the TD encounters the ion foreshock, plasma and magnetic field perturbations are generated upstream of the TD. These perturbations are characteristically consistent with the observed TD‐driven FBs, confirming that TDs can form FBs. We further analyze the initial perpendicular temperature increase initiating the FB and compare the temperature structure with that from tracing test‐particles in static TD electric and magnetic fields. The structure can be explained by the perpendicular velocity change of foreshock ions with large gyroradii as they encounter the magnetic field direction change across the TD, which supports the hypothesized mechanism. 

   more » « less
5. Developmental lineage of human pluripotent stem cell‐derived cardiac fibroblasts affects their functional phenotype

   https://doi.org/10.1096/fj.202100523R  

   Floy, Martha_E; Givens, Sophie_E; Matthys, Oriane_B; Mateyka, Taylor_D; Kerr, Charles_M; Steinberg, Alexandra_B; Silva, Ana_C; Zhang, Jianhua; Mei, Ying; Ogle, Brenda_M; et al (August 2021, The FASEB Journal)

   Abstract Cardiac fibroblasts (CFBs) support heart function by secreting extracellular matrix (ECM) and paracrine factors, respond to stress associated with injury and disease, and therefore are an increasingly important therapeutic target. We describe how developmental lineage of human pluripotent stem cell‐derived CFBs, epicardial (EpiC‐FB), and second heart field (SHF‐FB) impacts transcriptional and functional properties. Both EpiC‐FBs and SHF‐FBs exhibited CFB transcriptional programs and improved calcium handling in human pluripotent stem cell‐derived cardiac tissues. We identified differences including in composition of ECM synthesized, secretion of growth and differentiation factors, and myofibroblast activation potential, with EpiC‐FBs exhibiting higher stress‐induced activation potential akin to myofibroblasts and SHF‐FBs demonstrating higher calcification and mineralization potential. These phenotypic differences suggest that EpiC‐FBs have utility in modeling fibrotic diseases while SHF‐FBs are a promising source of cells for regenerative therapies. This work directly contrasts regional and developmental specificity of CFBs and informs CFB in vitro model selection. 

   more » « less