Search for: All records

Effective coordination of design teams must account for the influence of costs incurred while searching for the best design solutions. This article introduces a cost-aware multi-agent system (MAS), a theoretical model to (1) explain how individuals in a team should search, assuming that they are all rational utility-maximizing decision-makers and (2) study the impact of cost on the search performance of both individual agents and the system. First, we develop a new multi-agent Bayesian optimization framework accounting for information exchange among agents to support their decisions on where to sample in search. Second, we employ a reinforcement learning approach based on the multi-agent deep deterministic policy gradient for training MAS to identify where agents cannot sample due to design constraints. Third, we propose a new cost-aware stopping criterion for each agent to determine when costs outweigh potential gains in search as a criterion to stop. Our results indicate that cost has a more significant impact on MAS communication in complex design problems than in simple ones. For example, when searching in complex design spaces, some agents could initially have low-performance gains, thus stopping prematurely due to negative payoffs, even if those agents could perform better in the later stage of the search. Therefore, global-local communication becomes more critical in such situations for the entire system to converge. The proposed model can serve as a benchmark for empirical studies to quantitatively gauge how humans would rationally make design decisions in a team. 

Computer-aided design (CAD) is a standard design tool used in engineering practice and by students. CAD has become increasingly analytic and inventive in incorporating artificial intelligence (AI) approaches to design, e.g., generative design (GD), to help expand designers' divergent thinking. However, generative design technologies are relatively new, we know little about generative design thinking in students. This research aims to advance our understanding of the relationship between aspects of generative design thinking and traditional design thinking. This study was set in an introductory graphics and design course where student designers used Fusion 360 to optimize a bicycle wheel frame. We collected the following data from the sample: divergent and convergent psychological tests and an open-ended response to a generative design prompt (called the generative design reasoning elicitation problem). A Spearman's rank correlation showed no statistically significant relationship between generative design reasoning and divergent thinking. However, an analysis of variance found a significant difference in generative design reasoning and convergent thinking between groups with moderate GD reasoning and low GD reasoning. This study shows that new computational tools might present the same challenges to beginning designers as conventional tools. Instructors should be aware of informed design practices and encourage students to grow into informed designers by introducing them to new technology, such as generative design.

 

The immense volume of user-generated content on social media provides a rich data source for big data research. Comentioned entities in social media content offer valuable information that can support a broad range of studies, from product market competition to dynamic social network mining and modeling. This paper introduces a new approach that combines named entity recognition (NER) and network modeling to extract and analyze co-mention relationships among entities in the same domain from unstructured social media data. This approach contributes to design for market systems literature because little research has investigated product competition via co-mention networks using large-scale unstructured social media data. In particular, the proposed approach provides designers with a new way to gain insight into market trends and aggregated customer preferences when customer choice data is insufficient. Moreover, our approach can easily support the evolution analysis of co-mention relationships beyond cross-sectional analysis of co-mention networks in a single year due to the abundance of social media data in multiple years. To demonstrate the approach to supporting multi-year product competition analysis, we perform a case study on mining co-mention networks of car models with Twitter data. The result shows that our approach can successfully extract the co-mention relationships of car models in multiple years from 2016 to 2019 from massive Twitter content; and enables us to conduct evolutionary co-mention network analysis with temporal network modeling and descriptive network analysis. The analysis confirmed that the co-mention network is capable of identifying frequently discussed entities and topics, such as car model pairs that often involve in competition and emerging vehicle technologies such as electric vehicles (EV). Furthermore, conducting evolutionary co-mention network analysis provides designers with an efficient way to monitor shifts in customer preferences for car features and to track trends in public discussions such as environmental issues associated with EVs over time. Our approach can be generally applied to other studies on co-mention relationships between entities, such as emerging technologies, cellphones, and political figures. 

Conceptual design is the foundational stage of a design process that translates ill-defined design problems into low-fidelity design concepts and prototypes through design search, creation, and integration. In this stage, product shape design is one of the most paramount aspects. When applying deep learning-based methods to product shape design, two major challenges exist: (1) design data exhibit in multiple modalities and (2) an increasing demand for creativity. With recent advances in deep learning of cross-modal tasks (DLCMTs), which can transfer one design modality to another, we see opportunities to develop artificial intelligence (AI) to assist the design of product shapes in a new paradigm. In this paper, we conduct a systematic review of the retrieval, generation, and manipulation methods for DLCMT that involve three cross-modal types: text-to-3D shape, text-to-sketch, and sketch-to-3D shape. The review identifies 50 articles from a pool of 1341 papers in the fields of computer graphics, computer vision, and engineering design. We review (1) state-of-the-art DLCMT methods that can be applied to product shape design and (2) identify the key challenges, such as lack of consideration of engineering performance in the early design phase that need to be addressed when applying DLCMT methods. In the end, we discuss the potential solutions to these challenges and propose a list of research questions that point to future directions of data-driven conceptual design. 

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.

 

Abstract In this paper, we present a decentralized approach based on a simple set of rules to schedule multi-robot cooperative additive manufacturing (AM). The results obtained using the decentralized approach are compared with those obtained from an optimization-based method, representing the class of centralized approaches for manufacturing scheduling. Two simulated case studies are conducted to evaluate the performance of both approaches in total makespan. In the first case, four rectangular bars of different dimensions from small to large are printed. Each bar is first divided into small subtasks (called chunks), and four robots are then assigned to cooperatively print the resulting chunks. The second case study focuses on testing geometric complexity, where four robots are used to print a mask stencil (an inverse stencil, not face covering). The result shows that the centralized approach provides a better solution (shorter makespan) compared to the decentralized approach for small-scale problems (i.e., a few robots and chunks). However, the gap between the solutions shrinks while the scale increases, and the decentralized approach outperforms the centralized approach for large-scale problems. Additionally, the runtime for the centralized approach increased by 39-fold for the extra-large problem (600 chunks and four robots) compared to the small-scale problem (20 chunks and four robots). In contrast, the runtime for the decentralized approach was not affected by the scale of the problem. Finally, a Monte-Carlo analysis was performed to evaluate the robustness of the centralized approach against uncertainties in AM. The result shows that the variations in the printing time of different robots can lead to a significant discrepancy between the generated plan and the actual implementation, thereby causing collisions between robots that should have not happened if there were no uncertainties. On the other hand, the decentralized approach is more robust because a collision-free schedule is generated in real-time. 

Abstract In this paper, we present a predictive and generative design approach for supporting the conceptual design of product shapes in 3D meshes. We develop a target-embedding variational autoencoder (TEVAE) neural network architecture, which consists of two modules: (1) a training module with two encoders and one decoder (E2D network) and (2) an application module performing the generative design of new 3D shapes and the prediction of a 3D shape from its silhouette. We demonstrate the utility and effectiveness of the proposed approach in the design of 3D car body and mugs. The results show that our approach can generate a large number of novel 3D shapes and successfully predict a 3D shape based on a single silhouette sketch. The resulting 3D shapes are watertight polygon meshes with high-quality surface details, which have better visualization than voxels and point clouds, and are ready for downstream engineering evaluation (e.g., drag coefficient) and prototyping (e.g., 3D printing). 

Abstract Customer preference modelling has been widely used to aid engineering design decisions on the selection and configuration of design attributes. Recently, network analysis approaches, such as the exponential random graph model (ERGM), have been increasingly used in this field. While the ERGM-based approach has the new capability of modelling the effects of interactions and interdependencies (e.g., social relationships among customers) on customers’ decisions via network structures (e.g., using triangles to model peer influence), existing research can only model customers’ consideration decisions, and it cannot predict individual customer’s choices, as what the traditional utility-based discrete choice models (DCMs) do. However, the ability to make choice predictions is essential to predicting market demand, which forms the basis of decision-based design (DBD). This paper fills this gap by developing a novel ERGM-based approach for choice prediction. This is the first time that a network-based model can explicitly compute the probability of an alternative being chosen from a choice set. Using a large-scale customer-revealed choice database, this research studies the customer preferences estimated from the ERGM-based choice models with and without network structures and evaluates their predictive performance of market demand, benchmarking the multinomial logit (MNL) model, a traditional DCM. The results show that the proposed ERGM-based choice modelling achieves higher accuracy in predicting both individual choice behaviours and market share ranking than the MNL model, which is mathematically equivalent to ERGM when no network structures are included. The insights obtained from this study further extend the DBD framework by allowing explicit modelling of interactions among entities (i.e., customers and products) using network representations.