Mark Fuge

Last Name

Fuge

First Name

Mark

ORCID

0000-0003-3819-8895

Organisational unit

09828 - Fuge, Mark / Fuge, Mark

Show all metadata

Search Results

Publications 1 - 10 of 68

Design manifolds capture the intrinsic complexity and dimension of design spaces
Chen, Wei; Fuge, Mark; Chazan, Jonah (2017)
Journal of Mechanical Design
This paper shows how to measure the intrinsic complexity and dimensionality of a design space. It assumes that high-dimensional design parameters actually lie in a much lower-dimensional space that represents semantic attributes—a design manifold. Past work has shown how to embed designs using techniques like autoencoders; in contrast, the method proposed in this paper first captures the inherent properties of a design space and then chooses appropriate embeddings based on the captured properties. We demonstrate this with both synthetic shapes of controllable complexity (using a generalization of the ellipse called the superformula) and real-world designs (glassware and airfoils). We evaluate multiple embeddings by measuring shape reconstruction error, pairwise distance preservation, and captured semantic attributes. By generating fundamental knowledge about the inherent complexity of a design space and how designs differ from one another, our approach allows us to improve design optimization, consumer preference learning, geometric modeling, and other design applications that rely on navigating complex design spaces. Ultimately, this deepens our understanding of design complexity in general.
Design creativity
Fu, Katherine; Fuge, Mark; Brown, David C. (2018)
AI EDAM
Using Semantic Fluency Models Improves Network Reconstruction Accuracy of Tacit Engineering Knowledge
Sexton, Thurston; Fuge, Mark (2019)
Proceedings of the ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 2A: 45th Design Automation Conference
Human- or expert-generated records that describe the behavior of engineered systems over a period of time can be useful for statistical learning techniques like pattern detection or output prediction. However, such data often assumes familiarity of a reader with the relationships between entities within the system — that is, knowledge of the system’s structure. This required, but unrecorded “tacit” knowledge makes it difficult to reliably learn patterns of system behavior using statistical modeling techniques on these written records. Part of this difficulty stems from a lack of good models for how engineers generate written records of a system, given their expertise, since they often create such records under time pressure using shorthand notation or internal jargon. In this paper, we model the process of maintenance work order creation as a modified semantic fluency task, to build a probabilistic generative model that can uncover underlying relationships between entities referenced within a complex system. Compared to more traditional similarity-metric-based methods for structure recovery, we directly model a possible cognitive process by which technicians may record work-orders. Mathematically, we represent this as a censored local random walk over a latent network structure representing tacit engineering knowledge. This allows us to recover implied engineering knowledge about system structure by processing written records. Additionally, we show that our model leads to improved generative capabilities for synthesizing plausible data.
Synthesizing designs with interpart dependencies using hierarchical generative adversarial networks
Chen, Wei; Fuge, Mark (2019)
Journal of Mechanical Design
Real-world designs usually consist of parts with interpart dependencies, i.e., the geometry of one part is dependent on one or multiple other parts. We can represent such dependency in a part dependency graph. This paper presents a method for synthesizing these types of hierarchical designs using generative models learned from examples. It decomposes the problem of synthesizing the whole design into synthesizing each part separately but keeping the interpart dependencies satisfied. Specifically, this method constructs multiple generative models, the interaction of which is based on the part dependency graph. We then use the trained generative models to synthesize or explore each part design separately via a low-dimensional latent representation, conditioned on the corresponding parent part(s). We verify our model on multiple design examples with different interpart dependencies. We evaluate our model by analyzing the constraint satisfaction performance, the synthesis quality, the latent space quality, and the effects of part dependency depth and branching factor. This paper’s techniques for capturing dependencies among parts lay the foundation for learned generative models to extend to more realistic engineering systems where such relationships are widespread.
Measuring and Optimizing Design Variety Using Herfindahl Index
Ahmed, Faez; Ramachandran, Sharath Kumar; Fuge, Mark; et al. (2019)
Proceedings of the ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 7: 31st International Conference on Design Theory and Methodology
In this paper, we propose a new design variety metric based on the Herfindahl index. We also propose a practical procedure for comparing variety metrics via the construction of ground truth datasets from pairwise comparisons by experts. Using two new datasets, we show that this new variety measure aligns with human ratings more than some existing and commonly used tree-based metrics. This metric also has three main advantages over existing metrics: a) It is a super-modular function, which enables us to optimize design variety using a polynomial time greedy algorithm. b) The parametric nature of this metric allows us to fit the metric to better represent variety for new domains. c) It has higher sensitivity in distinguishing between variety of sets of randomly selected designs than existing methods. Overall, our results shed light on some qualities that good design variety metrics should possess and the non-trivial challenges associated with collecting the data needed to measure those qualities.
Structuring Online Dyads: Explanations Improve Creativity, Chats Lead to Convergence
Ahmed, Faez; Chandra, Nischal Reddy; Fuge, Mark; et al. (2019)
C&C '19: Proceedings of the 2019 Conference on Creativity and Cognition
Exposing people to concepts created by others can inspire novel combinations of concepts, or conversely, lead people to simply emulate others. But how does the type of exposure affect creative outcomes in online collaboration where dyads interact for short tasks? In this paper, we study the creative outcomes of dyads working together online on a slogan writing task under different types of interactions: providing both the partner's idea and their explanation for that idea, enabling synchronous chat, and only exposing a person to their partner's idea without any explanation. We measure the creative outcome and define text-similarity-based metrics (e.g., mimicry, convergence, and fixation) to disentangle the interactions. The results show that having partners explain their ideas leads to largest improvement in creative outcome. In contrast, participants who chatted were more likely to reach convergence on their final slogans. Our work sheds lights on how different online interactions may create trade-offs in creative collaborations.
Automatic Laplacian-based shape optimization for patient-specific vascular grafts
Habibi, Milad; Aslan, Seda; Liu, Xiaolong; et al. (2025)
Computers in Biology and Medicine
Cognitional heart disease is one of the leading causes of mortality among newborns. Tissue-engineered vascular grafts offer the potential to help treat cognitional heart disease through patient-specific vascular grafts. However, current methods often rely on non-personalized designs or involve significant human intervention. This paper presents a computational framework for the automatic shape optimization of patient-specific tissue-engineered vascular grafts for repairing the aortic arch, aimed at reducing the need for manual input and improving current treatment outcomes, which either use non-patient-specific geometry or require extensive human intervention to design the vascular graft. The paper’s core innovation lies in an automatic shape optimization pipeline that combines Bayesian optimization techniques with the open-source finite volume solver, OpenFOAM, and a novel graft deformation algorithm. Specifically, our framework begins with Laplacian mode computation and the approximation of a computationally low-cost Gaussian process surrogate model to capture the minimum weighted combination of inlet-outlet pressure drop (PD) and maximum wall shear stress (WSS). Bayesian Optimization then performs a limited number of OpenFOAM simulations to identify the optimal patient-specific shape. We use imaging and flow data obtained from six patients diagnosed with cognitional heart disease to evaluate our approach. Our results showcase the potential of online training and hemodynamic surrogate model optimization for providing optimal graft shapes. These results show how our framework successfully reduces inlet-outlet PD and maximum WSS compared to pre-lofted models that include both the native geometry and human-designed grafts. Furthermore, we compare how the performance of each design optimized under steady-state simulation compares to that design’s performance under transient simulation, and to what extent the optimal design remains similar under both conditions. Our findings underscore that the automated designs achieve at least a 16% reduction in blood flow pressure drop in comparison to geometries optimized by humans.
Active expansion sampling for learning feasible domains in an unbounded input space
Chen, Wei; Fuge, Mark (2018)
Structural and Multidisciplinary Optimization
Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body styling designs based on constraints like aesthetics and functionality. Current active-learning based methods learn feasible domains for bounded input spaces. However, we usually lack prior knowledge about how to set those input variable bounds. Bounds that are too small will fail to cover all feasible domains; while bounds that are too large will waste query budget. To avoid this problem, we introduce Active Expansion Sampling (AES), a method that identifies (possibly disconnected) feasible domains over an unbounded input space. AES progressively expands our knowledge of the input space, and uses successive exploitation and exploration stages to switch between learning the decision boundary and searching for new feasible domains. We show that AES has a misclassification loss guarantee within the explored region, independent of the number of iterations or labeled samples. Thus it can be used for real-time prediction of samples’ feasibility within the explored region. We evaluate AES on three test examples and compare AES with two adaptive sampling methods — the Neighborhood-Voronoi algorithm and the straddle heuristic — that operate over fixed input variable bounds.
Adaptive Expansion Bayesian Optimization for Unbounded Global Optimization
Chen, Wei; Fuge, Mark (2020)
arXiv
Bayesian optimization is normally performed within fixed variable bounds. In cases like hyperparameter tuning for machine learning algorithms, setting the variable bounds is not trivial. It is hard to guarantee that any fixed bounds will include the true global optimum. We propose a Bayesian optimization approach that only needs to specify an initial search space that does not necessarily include the global optimum, and expands the search space when necessary. However, over-exploration may occur during the search space expansion. Our method can adaptively balance exploration and exploitation in an expanding space. Results on a range of synthetic test functions and an MLP hyperparameter optimization task show that the proposed method out-performs or at least as good as the current state-of-the-art methods.
IH-GAN: A conditional generative model for implicit surface-based inverse design of cellular structures
Wang, Jun; Chen, Wei (Wayne); Da, Daicong; et al. (2022)
Computer Methods in Applied Mechanics and Engineering
Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically optimized structures, particularly those represented as discrete density maps. However, the optimization of such cellular structures is challenging due to the multiscale design problem. Past work addressing this problem generally either only optimizes the volume fraction of single-type unit cells but ignoring the effects of unit cell geometry on properties, or considers the geometry–property relation but builds this relation via heuristics. In contrast, we propose a simple yet more principled way to accurately model the property to geometry mapping using a conditional deep generative model, named Inverse Homogenization Generative Adversarial Network (IH-GAN). It learns the conditional distribution of unit cell geometries given properties and can realize the one-to-many mapping from properties to geometries. We further reduce the complexity of IH-GAN by using the implicit function parameterization to represent unit cell geometries. Results show that our method can 1) generate various unit cells that satisfy given material properties with high accuracy (R2-scores between target properties and properties of generated unit cells >98%) and 2) improve the optimized structural performance over the conventional variable-density single-type structure. In the minimum compliance example, our IH-GAN generated structure achieves a 79.7% reduction in concentrated stress and an extra 3.03% reduction in displacement. In the target deformation examples, our IH-GAN generated structure reduces the target matching error by 86.4% and 79.6% for two test cases, respectively. We also demonstrated that the connectivity issue for multi-type unit cells can be solved by transition layer blending.

Publications 1 - 10 of 68

Mark Fuge

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results