It is essential to consider the vibration behaviour of a technical system as early as possible in the product development process. While quantitative product modelling approaches can provide detailed analyses on vibration behaviour, their early applicability is limited due to necessary information. In contrast, early applicable qualitative product modelling approaches in embodiment design fall short in considering the vibration behaviour. Therefore, this publication’s objective is to investigate whether a qualitative product modelling approach focused on embodiment function relations can be linked with a product modelling approach considering the vibration behaviour. This investigation was carried out by intending to link the Contact Channel Approach (C C²-A) and Single Degree of Freedom (SDOF) system approach as exemplary product modelling approaches, and subsequently evaluating whether they provide an accurate insight into a design problem in comparison to experimental findings. The results show that a link from the SDOF system approach to the C C²-A is possible and that this linking possibility can enable accurate qualitative insights into the vibration behaviour for a targeted manipulation of design parameters. Thus, the linked product modelling approaches are more capable together than the previous individual ones and represents a first step towards an early applicable consideration of vibration behaviour in embodiment design.
With the rapid development of generative intelligent design technologies, engineers are increasingly confronted with large numbers of candidate solutions, amplifying the need for controllable generation and efficient evaluation of mechanical performance. To address common challenges in data-driven structural design, this study proposes an integrated framework that combines heterogeneous dataset construction with deep learning to improve generalization and robustness in performance prediction. A heterogeneous structural dataset is constructed for training and evaluation by integrating two parameterized design schemes and a topology-optimization approach. The parameterized datasets are employed for surrogate-model training and meta-learning, while the topology-optimized dataset is reserved for independent evaluation of cross-design-space generalization. Based on this dataset, a multi-scale feature-fusion deep residual network (MS-Res-Net) is developed and further improved using a model-agnostic meta-learning (MAML) strategy to strengthen predictive accuracy and accelerate adaptation to new design distributions. Results show that the proposed method achieves high prediction accuracy for maximum displacement and von Mises stress across diverse parameter configurations. Furthermore, the incorporation of MAML consistently improves prediction performance on unseen topology-optimized structures, with the most notable gains observed in stress-related responses. These findings demonstrate the potential of the proposed framework as a computationally efficient tool for cross-design-space structural performance prediction, supporting intelligent design evaluation, rapid scheme screening, and data-driven decision-making in engineering design workflows.
As robotic technologies become more integrated into society, there is a growing demand for systems that are not only technically robust, but also socially accepted, safe, and designed for long-term use. Biologically-Inspired Design (BID), Human-Centered Design (HCD), and Human-Robot Interaction (HRI) each offer valuable theories, methodologies, and tools to support the design and evaluation of such systems. Despite their complementary goals, these fields have largely developed in isolation. The lack of integration across BID, HCD, and HRI presents significant barriers for researchers and designers seeking to create biologically-informed, human-centered robots that facilitate meaningful interactions. In this work, an integrative literature review was conducted to examine the fields of BID, HCD, and HRI. An analytic categorization approach was used to categorize 63 papers into one or more of the three fields: 20 in BID, 27 in HCD, and 21 in HRI, with some papers categorized into multiple categories. Within each field, an inductive, interpretive coding and thematic analysis were used to identify key terminology, tools, methods, and conceptual frameworks, helping establish a shared vocabulary and summarize the state of the art. This was followed by a synthesis of limitations and field-specific gaps. Cross-field analysis revealed only four papers demonstrating overlap within the reviewed corpus: three showing implicit connections between HCD and HRI, and one showing implicit overlap between BID and HRI with indirect ties to HCD. This review lays the groundwork for more integrated design research by identifying opportunities for collaboration across BID, HCD, and HRI, highlighting the potential for more biologically-informed, user-centered, and socially responsive robotic systems.
This paper proposes an integrative and flexible categorisation framework for early-stage material exploration in design-oriented contexts. The framework responds to the growing complexity of contemporary material landscapes, where conventional taxonomies and material databases often fail to adequately represent emerging, non-conventional, and sustainability-oriented materials. To develop the proposal, the authors conducted a critical review of 35 international material libraries, both physical and digital, and identified significant heterogeneity in categorisation criteria, as well as major gaps in the treatment of life-cycle-related information, aesthetic and sensorial characteristics, and less conventional material classes. The framework was then iteratively drafted, tested, refined, and consolidated through collaborative discussion among the authors and a pilot application involving 110 material case studies, with particular attention to recent and innovative materials. The resulting structure is designed to guide the organised and consistent comparison of material case studies in the early stages of the design process and, eventually, support the organisation of repositories of knowledge and material references. To do so, the framework integrates general information, material classification, technical data, aesthetic-sensorial characteristics, composition, life-cycle-related aspects, certifications, and links to the Sustainable Development Goals. Unlike late-stage selection tools focused mainly on engineering performance, the proposed framework is intended to support holistic exploration when uncertainty is high and information is often incomplete. Its modular and adaptable structure makes it suitable for use in design education, academic research, professional practice, and corporate R D. By promoting clearer terminology, greater comparability, and more comprehensive material descriptions, the framework aims to become a practical tool for navigating the rapidly evolving field of materials and for supporting more organised case studies exploration and categorisation.
Generative Artificial Intelligence (AI) and Large Language Models are increasingly considered for integration into engineering design workflows, yet their actual capabilities on the analytical and optimization tasks that arise in engineering design remain poorly understood. In this study, we examine Large Language Model-generated answers to 86 text-based questions covering three task categories chosen for their direct correspondence to typical engineering design activities: 50 problem-solving tasks from the Kangaroo Math Competition, 20 structural engineering design tasks involving stress analysis and cross-section selection, and 16 engineering optimization tasks involving conflicting constraints and trade-offs. Across the evaluated models, we observe that performance is consistently higher on the general Kangaroo problem-solving questions than on the engineering geometry and optimization tasks, even though these draw on a comparable set of underlying skills. The study further exposes systematic failure modes across the examined task types, including geometric reasoning, multi-step numerical computation, and optimization under conflicting constraints. These findings characterize the specific capabilities that AI-enabled design systems must develop to be reliable in practice, and establish an empirical baseline for evaluating future augmentation strategies such as tool integration and structured design workflows.
