The aim of this study is to explore how large language models (LLMs) integrated with structured versus unstructured concept generation techniques (CGTs) influence designers’ creative thinking processes and outputs. Using human–human collaboration (HHC) as a baseline, a 2 × 2 mixed factorial design was adopted to investigate the effects of collaborator type (between-subjects: LLM-based agents vs. experienced designers) and CGT type (within-subjects: brainstorming vs. TRIZ). Two LLM-based agents, IntelliStorm and EvoluTRIZ, were developed for the study, with 32 participants randomly assigned to either the HHC or human–agent collaboration (HAC) groups. Brain activity was measured using functional near-infrared spectroscopy, while outputs were assessed through expert evaluations. Results showed that designers exhibited lower cognitive load, better cognitive resource coordination, and enhanced fluency and flexibility in thinking in HAC than in HHC. Moreover, distinct patterns were revealed in different CGTs: brainstorming activated the right dorsolateral prefrontal cortex (PFC) as the core connectivity region, enhancing ideational fluency, whereas TRIZ activated the left dorsolateral PFC, facilitating refined thinking. Although HAC demonstrated stronger overall performance, HHC retained unique advantages in originality. This research offers novel neuroscientific insights and provides evidence-based guidance for developing more effective LLM-based design agents.

The emergence of large language models (LLMs) provides an opportunity for AI to operate as a co-ideation partner during the creative processes. However, designers currently lack a comprehensive methodology for engaging in co-ideation with LLMs, and there is a limited framework that describes the process of co-ideation between a designer and ChatGPT. This research thus aimed to explore how LLMs can act as codesigners and influence creative ideation processes of industrial designers and whether the ideation performance of a designer could be improved by employing the proposed framework for co-ideation with custom GPT. A survey was first conducted to detect how LLMs influenced the creative ideation processes of industrial designers and to understand the problems that designers face when using ChatGPT to ideate. Then, a framework which based on mapping content to guide the co-ideation between humans and custom GPT (named as Co-Ideator) was promoted. Finally, a design case study followed by a survey and an interview was conducted to evaluate the ideation performance of the custom GPT and framework compared with traditional ideation methods. Also, the effect of custom GPT on co-ideation was compared with a non-artificial intelligence (AI)-used condition. The findings indicated that if users employed co-ideation with custom GPT, the novelty and quality of ideation outperformed by using traditional ideation.

Digital Tools are reshaping how Engineering Design data and information are produced, processed, used, reused, shared, and stored. The Digital Thread prioritizes the flow of design data and information, promoting effective collaboration and process efficiency. While literature showcases the immense application and capability of taking a Digital Thread approach to Product Design, best practices, key features, and benefits of successful implementations remain scarce. Reviewing and understanding successful implementations can assist researchers and practitioners in making informed decisions to effectively implement Digital Threads in their product design processes. This article addresses this gap by reporting a post hoc review of a collaborative Research & Development project that developed and implemented a Digital Thread approach to the design of hydrogen composite pressure vessels. A thematic analysis of the project’s reports and interviews with members of the project team was performed to identify the key features that expedite and improve the design process through an effective Digital Thread implementation. The post hoc review offers valuable insights – in the form of six feature benefits, four potential implementation challenges, three possible extensions, and four best practice recommendations – for companies looking to adopt and implement a Digital Thread approach to their design process.

Vibration control in structures is essential to mitigate undesired dynamic responses, thereby enhancing stability, safety, and performance under varying loading conditions. Mechanical metamaterials have emerged as effective solutions, enabling tailored dynamic properties for vibration attenuation. This study introduces a convolutional autoencoder framework for the inverse design of local resonators embedded in mechanical metamaterials. The model learns from the dynamic behaviour of primary structures coupled with ideal absorbers to predict the geometric parameters of resonators that achieve desired vibration control performance. Unlike conventional approaches requiring full numerical models, the proposed method operates as a data-driven tool, where the target frequency to be mitigated is provided as input, and the model directly outputs the resonator geometry. A large dataset, generated through physics-informed simulations of ideal absorber dynamics, supports training while incorporating both spectral and geometric variability. Within the architecture, the encoder maps input receptance spectra to resonator geometries, while the decoder reconstructs the target receptance response, ensuring dynamic consistency. Once trained, the framework predicts resonator configurations that satisfy predefined frequency targets with high accuracy, enabling efficient design of passive controllers of the syntonized mass type. This study specifically demonstrates the application of the methodology to resonators embedded in wind turbine metastructures, a critical context for mitigating structural vibrations and improving operational efficiency. Results confirm strong agreement between predicted and target responses, underscoring the potential of deep learning techniques to support on-demand inverse design of mechanical metamaterials for smart vibration control in wind energy and related engineering applications.

Design Neurocognition, a field bridging Design Research and Cognitive Neuroscience, offers new insights into the cognitive processes underlying creative ideation. This study adopts a micro-perspective on design ideation by examining convergent and divergent thinking as its core components. Using 32-channel EEG recordings, it investigates how educational background (Industrial Design Engineering vs. Engineering Design) influences designers’neural activity (alpha, beta, and gamma frequency bands), behavioral responses, and perceived stress during ideation tasks. Data from forty participants reveal a consistent and meaningful interaction between brain activity, behavior, and self-reported stress, highlighting that educational background significantly modulates cognitive and neural patterns during ideation. Importantly, perceived stress shows strong negative correlations with neural power across all frequency bands, suggesting a close alignment between subjective experience and physiological measures. By integrating neural, behavioral, and psychological data, this study advances the understanding of the neurocognitive mechanisms driving design ideation and establishes a methodological foundation for bridging Design and Cognitive Neuroscience. These findings contribute to building a unified evidence base for future human-centred and neuro-informed design research.

Model-based systems engineering (MBSE) is increasingly used across industries for the integrated modeling of complex systems to support model-based development and provide enhanced traceability between requirements and verification and validation of the system. This paper seeks to strengthen the function modeling methodology in MBSE by introducing an approach based on flow heuristics guided by the System State Flow Diagram schema. This provides integrated function architectures with an enhanced integrity in MBSE. The approach is illustrated with a case study of an electric bicycle implemented in the MathWorks System Composer environment.

Generative artificial intelligence (GenAI) applications in job scheduling are expected to help schedulers embed their requirements into scheduling models in a more user-friendly way to generate customized scheduling results. However, there are still very few such applications, while using existing general-purpose GenAI services is inconvenient and prone to data leakage risks. To solve these problems, this study established a GenAI job scheduling system. By hosting the GenAI job scheduling system locally, schedulers can avoid the leakage of order- or recipe-related information that may occur when uploading to the cloud-based GenAI service. In the GenAI job scheduling system, a user interface is designed for users to enter queries in natural language. The user’s query is then analyzed to extract his/her requirements related to the scheduling task, thereby building an extended three-field notation (ETFN) of the scheduling problem. A customized genetic algorithm (GA) is generated to help solve the mathematical programming (MP) model corresponding to the ETFN, thereby updating invalid code or adding new code to the basic GA application. The effectiveness of the GenAI job scheduling system has been tested in a flexible job shop case.

Fault analysis at the early design stages of an engineering system is crucial for ensuring reliability and safety during operation. Given the limited information on system components and configurations available at this stage, such analysis heavily relies on historical data and expert knowledge. Traditional methods like Fault Tree, Bayesian networks, and Markov chains depend on manually established causality models for system failures. In complex systems with numerous components, creating these causality models becomes increasingly time-consuming and susceptible to human-error in identifying potential causal relationships. One of the major reasons for the modeling errors is that the causality models lack the support of physics. To address these limitations, this article introduces a novel approach for formally establishing causal relations between faults and system failures and calculating the probabilities of each cause. Even at conceptual design stage, the proposed method can automatically deduce all possible causes and fault propagation paths for each system failure corresponding to the physics modeled by the analyst. The entire approach is divided into two major steps: the first step identifies the system trajectories for a known condition using qualitative physics and symbolic AI, and the second step calculates the conditional probabilities of the causes outlined in the first step for a given initial condition. Knowledge about the probabilistically weighted causes of system failures allows designers to identify potential issues that have a relatively high likelihood of occurrence and severe consequences. The article demonstrates the method’s application by analyzing a simplified secondary loop of a nuclear power plant.