To save content items to your account,
please confirm that you agree to abide by our usage policies.
If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account.
Find out more about saving content to .
To save content items to your Kindle, first ensure firstname.lastname@example.org
is added to your Approved Personal Document E-mail List under your Personal Document Settings
on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part
of your Kindle email address below.
Find out more about saving to your Kindle.
Note you can select to save to either the @free.kindle.com or @kindle.com variations.
‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi.
‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.
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.
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.
Seasonal effects can significantly impact the robustness of socio-technical systems (STS) to demand fluctuations. There is an increasing need to develop novel design approaches that can support capacity planning decisions for enhancing the robustness of STS against seasonal effects. This paper proposes a new network motif-based approach to supporting capacity planning in STS for an improved seasonal robustness. Network motifs are underlying nonrandom subgraphs within a complex network. In this approach, we introduce three motif-based metrics for system performance evaluation and capacity planning decision-making. The first one is the imbalance score of a motif (e.g., a local service network), the second one is the measurement of a motif’s seasonal robustness, and the third one is a capacity planning decision criterion. Based on these three metrics, we validate that the sensitivity of STS performance against seasonal effects is highly correlated with the imbalanced capacity between service nodes in an STS. Correspondingly, we formulate a design optimisation problem to improve the robustness of STS by rebalancing the resources at critical service nodes. To demonstrate the utility of the approach, a case study on Divvy bike-sharing system in Chicago is conducted. With a focus on the size-3 motifs (a subgraph consisting three docked stations), we find that there is a significant correlation between the difference of the number of docks among the stations in a motif and the return/rental performance of such a motif against seasonal changes. Guided by this finding, our design approach can successfully balance out the number of docks between those stations that have caused the most severe seasonal perturbations. The results also imply that the network motifs can be an effective local structural representation in support of STS robust design. Our approach can be generally applied in other STS where the system performances are significantly impacted by seasonal changes, for example, supply chain networks, transportation systems and power grids.
There are three approaches to studying designers – through their cognitive profile, design behaviors, and design artifacts (e.g., quality). However, past work has rarely considered all three data domains together. Here we introduce and describe a framework for a comprehensive approach to engineering design, and discuss how the insights may benefit engineering design research and education. To demonstrate the proposed framework, we conducted an empirical study with a solar energy system design problem. Forty-six engineering students engaged in a week-long computer-aided design challenge that assessed their design behavior and artifacts, and completed a set of psychological tests to measure cognitive competencies. Using a machine learning approach consisting of k-means, hierarchical, and spectral clustering, designers were grouped by similarities on the psychological tests. Significant differences were revealed between designer groups in their sequential design behavior, suggesting that a designer's cognitive profile is related to how they engage in the design process.
Computational modeling of the human sequential design process and successful prediction of future design decisions are fundamental to design knowledge extraction, transfer, and the development of artificial design agents. However, it is often difficult to obtain designer-related attributes (static data) in design practices, and the research based on combining static and dynamic data (design action sequences) in engineering design is still underexplored. This paper presents an approach that combines both static and dynamic data for human design decision prediction using two different methods. The first method directly combines the sequential design actions with static data in a recurrent neural network (RNN) model, while the second method integrates a feed-forward neural network that handles static data separately, yet in parallel with RNN. This study contributes to the field from three aspects: (a) we developed a method of utilizing designers’ cluster information as a surrogate static feature to combine with a design action sequence in order to tackle the challenge of obtaining designer-related attributes; (b) we devised a method that integrates the function–behavior–structure design process model with the one-hot vectorization in RNN to transform design action data to design process stages where the insights into design thinking can be drawn; (c) to the best of our knowledge, it is the first time that two methods of combining static and dynamic data in RNN are compared, which provides new knowledge about the utility of different combination methods in studying sequential design decisions. The approach is demonstrated in two case studies on solar energy system design. The results indicate that with appropriate kernel models, the RNN with both static and dynamic data outperforms traditional models that only rely on design action sequences, thereby better supporting design research where static features, such as human characteristics, often play an important role.
Customer preference modeling provides quantitative assessment of the effects of engineering design attributes on customers’ choices. Utility-based approaches, such as discrete choice model (DCM), and network analysis approaches, such as exponential random graph model (ERGM), have been developed for customer preference modeling. However, no studies have compared these two approaches. Our objective is to identify the distinctions and connections between these two approaches based on both the theoretical foundation and the empirical evidence. Using the vehicle preference modeling as an example, our study shows that when network structure effects are not considered, results from ERGM are consistent with DCM in most of the test cases. However, in one case where customers have varying choice set with multiple alternatives, inconsistencies are observed, possibly due to the discrepancies of the two models in taking different information when calculating choice probabilities. The insights will lead to valuable guidance for choosing the technique for customer preference modeling and co- developing the two frameworks to support engineering design.
We propose a data-driven network-based approach to understand the interactions among technologies, products, and customers. Specifically, the approach enables both a qualitative understanding and a quantitative assessment of the impact of technological changes on customers’ co-consideration behaviors (decision of cross-shopping) and as a consequence the product competitions. The uniqueness of the proposed approach is its capability of predicting complex co-consideration relations of products as a network where both descriptive analyses (e.g., network statistics and joint correspondence analysis) and predictive models (e.g., multiple regressions quadratic assignment procedure) are employed. The integrated network analysis approach features three advantages: (1) It provides an effective visual representation of the underlying market structures; (2) It facilitates the evaluation of the correlation between customers’ consideration preferences and product attributes as well as customer demographics; (3) It enables the prediction of market competitions in response to potential technological changes. This paper demonstrates the proposed network-based approach in a vehicle design context. We investigate the impacts of the fuel economy-boosting technologies and the turbocharged engine technology on individual automakers as well as the entire auto industry. The case study provides vehicle engineers with insights into the change of market competitions brought by technological developments and thereby supports attribute decision-making in vehicle design.
Email your librarian or administrator to recommend adding this to your organisation's collection.