Artificial Intelligence (AI) is gaining importance in the field of education (Chen et al., 2020). Despite its widespread use to assist teachers (Pratama et al., 2023; Baidoo-Anu Ansah, 2023), there’s a gap in literature on AI’s role in instructional design, particularly for students with disabilities. This study explores the perceptions of 114 support teachers on using ChatGPT and the CONALI Ontology (Maffei et al., 2016) for creating Individualized Education Plans (IEPs). In the first phase of the study, teachers were trained on how to identify objectives, teaching and learning activities and assessment methods within the IEP, following the CONALI ontological framework and constructive alignment (CA) (Maffei et al., 2022). After verifying their perceptions of the experience through an initial validated questionnaire, a second exercise was conducted, in which the experimental group applied the CONALI framework in combination with ChatGPT to fill in the IEP. At the end of the exercise, a second questionnaire was handed out to collect participants’ perceptions of the experience and to assess the effectiveness of ChatGPT and CONALI in designing the IEP. Descriptive analysis revealed that the combination of ChatGPT and CONALI was perceived as useful in IEP design. Ontology was confirmed as a useful tool for identifying SMART training objectives and aligning them with intervention strategies and assessment methods in the IEP. AI, supported by CONALI, was seen as an effective tool for instructional design, speeding up IEP completion and promoting engagement, motivation, and learning quality.

There is a widespread fear that large language models (LLMs) produce content that is indistinguishable from an original human work. Can students use LLM-based tools for their exam essays without being spotted? We performed experiments on a publicly available dataset that we produced, containing thirty answers provided by ChatGPT and thirty-six answers from university students, for each of six anonymized exam essay traces from a scientific methodology course for engineers. We applied term frequency-inverse document frequency (TF-IDF), a state-of-the-art machine learning algorithm for natural language processing, and the cosine similarity metric, in order to produce two LLM detectors. One is based on one-class support vector machine anomaly detection, and the other is based on multi-class random forest classification. The results show that it is possible to spot when LLMs are involved, provided that the source LLM is known. Education institutions can follow our guidelines to prevent cheating and improve education.

Modern manufacturing processes' increasing complexity and variability demand advanced systems capable of real-time monitoring, adaptability, and data-driven decision-making. This paper introduces a novel runtime condition model to enhance interoperability, data integration, and decision support within intelligent manufacturing environments. The model encapsulates key manufacturing elements, including asset management, relationships, key performance indicators (KPIs), capabilities, data structures, constraints, and configurations. A key innovation is the integration of a knowledge graph enriched with embedding techniques, enabling the inference of missing relationships, dynamic reasoning, and predictive analytics. The proposed model was validated through a case study conducted in collaboration with TQC Automation Ltd., using their MicroApplication Leak Test System (MALT). A dataset of over 9,000 unique test configurations demonstrated the model's capabilities in representing runtime conditions, managing operational parameters, and optimising test configurations. The enriched knowledge graph facilitated advanced analyses, providing actionable insights into test outcomes and enabling proactive decision-making. Empirical results showcase the model's ability to harmonise diverse data sources, infer missing connections, and improve runtime adaptability. This study highlights the potential of combining runtime modelling with knowledge graphs to address the challenges of modern manufacturing. Future research will explore the model's application to additional domains, integration with larger datasets, and the use of machine learning for enhanced predictive capabilities.

Configure-to-Order (CTO) assembly systems are becoming pivotal in meeting the rising demand for mass customization. However, enabling rapid and cost-effective system reconfiguration remains a major challenge in manufacturing. Despite the flexibility of general-purpose machines, fixture design introduces significant bottlenecks, often requiring extensive manual effort to access, organize, and interpret fragmented or incomplete data. This leads to inefficient design pipelines that can compromise product functionality and result in costly redesign iterations, even when using advanced Computer-Aided Fixture Design (CAFD) tools. Although the Model-Based Definition (MBD) paradigm offers a promising response to these information-related challenges, its adoption within the CAFD domain remains limited. This work aims to support the broader adoption of MBD in this field through a multi-level contribution. First, a structured literature review identifies the essential semantic information required in an MBD dataset tailored to CAFD. Second, this content is structured in a machine-readable form using the ISO standard STEP AP242. Third, an MBD-driven CAFD framework is proposed. Finally, a proof-of-concept CAFD tool is developed by integrating established methodologies with commercial software to automate non-value-added tasks, such as configuring Computer-Aided Technologies (CAx). The results demonstrate the potential of this approach to streamline CAFD processes and establish a fully connected digital thread.

The paper discusses the design and implementation of a cognitive digital twin (CDT) to enhance the capabilities of autonomous industrial mobile manipulator (AIMM) in industrial settings. The integration of data in CDT facilitates enhanced positioning, even in the presence of obstacles, and optimized recharging schedules. The use of external sensors significantly improves the robot’s accuracy. The implementation of ML models facilitates intelligent planning of charging stops and minimizing downtime. This enhancement is achieved by creating a virtual representation of the physical system that incorporates cognitive capabilities, such as reasoning, learning, and planning. The study demonstrates the potential of CDTs to serve as advanced tools for decision-making, optimization, and predictive maintenance in industrial settings. The results also highlight the challenges in developing CDTs, particularly the need for high fidelity in replicating the physical system and the environment.

Multidisciplinary collaboration is key to product development; however, integrating multiple perspectives and design intent within the outcome of this process remains challenging. Although 3D product models are widely employed, they still lack relevant production details. A previous work established a coherent framework for enriching CAD files with assembly process information. This work offers the industrial perception and alignment of such a system through a preliminary impact assessment survey. Insights from experts and practitioners confirmed the solution's suitability to address these gaps, revealing organizational connotations and offering recommendations for improvement. These findings provide a user-centred perspective to guide the future implementation of the approach into established product development processes.

This study examines barriers to integrating design for assembly (DFA) principles into modular product architectures using the modular function deployment (MFD) method–a critical step for enabling cost-efficient mass customisation. Despite the known benefits of DFA, its adoption in early design stages remains limited. Drawing on qualitative insights from a focus group involving industry practitioners and advanced engineering students, as well as a prior systematic literature review, the study identifies key challenges. Results are classified into primary–closely aligned with research gaps–and secondary themes, emerging during practice-based discussions. These findings are synthesised into a conceptual framework structured around technological, economic, regulatory, and organisational (TERO) barriers. The framework provides guidance for integrating DFA earlier in modularisation, supporting more efficient, adaptable, and high-quality designs. It also outlines actionable areas for future research, including early-stage evaluation methods, AI-augmented design practices, and strategies for structuring knowledge repositories and promoting cross-functional collaboration.

This paper presents an innovative approach to integrating data-driven strategies into intelligent manufacturing systems, specifically targeting the challenges of configuration management in modular production environments. To address the distinct and evolving requirements of customized products, we propose a dynamic configuration management methodology that automatically adjusts system settings in real-time. This approach utilizes operational semantics to formalize the interactions between production modules, capturing essential operational information for intelligent decision-making. A novel control mechanism is developed, using knowledge graphs to semantically represent and manage the relationships between production system components and settings. By mapping these, the system can determine optimal configurations based on real-time data and specific operational requirements. The interaction between the control mechanism and the knowledge graph ensures continuous adaptability, enabling the system to reconfigure dynamically in response to changes. This method was validated in an industrial dry-air leak testing scenario, demonstrating its effectiveness in adaptability.

Over the past decades, significant developments have occurred in the manufacturing domain, culminating in the contemporary landscape of Industry 5.0 (I5.0). This era is defined by three primary dimensions: technical aspects, sustainability concerns, and human-centricity. Although the broader manufacturing field features a dispersed array of scientific literature reviews amidst this multidisciplinary transition, a focused examination of Visual Inspection Systems (VIS) within this context appears absent. This study aims to provide a comprehensive mapping study that navigates this complex and emerging area of research for VIS, incorporating both scientific publications and Intellectual Property (IP). Employing a systematic methodology for mapping review, an initial exploratory search was conducted, retrieving 264 documents. Following a systematic screening process, 46 documents were identified as relevant, underscoring the preliminary findings and prevailing trends in the field. Results shows that three main clusters emerged with rising interest in technological solutions. Additionally, this study offers a procedural approach to further investigate these promising exploratory findings and expand upon the current review.

In the evolving landscape of modern manufacturing, a novel concept known as Feeding-as-a-Service (FaaS) is emerging, part of the larger Automationas-a-Service (AaaS) framework. FaaS aims to optimize feeding systems in cloud manufacturing environments to meet the demands of mass customization and allow for quick responses to production changes. Therefore, it fits into the Manufacturing as-a-Service (MaaS) system as well. As the manufacturing industry undergoes significant transformations through automation and service-oriented models, understanding how FaaS fits into the other frameworks is essential.This study presents a systematic literature review with two primary objectives: first, to contextualize FaaS within AaaS and MaaS, highlighting similarities, differences,and distinctive characteristics; second, to identify and clarify the essential Key Performance Indicators (KPIs) crucial for its strategic implementation.KPIs are pivotal metrics guiding organizations toward manufacturing excellence.In this context, common KPIs focus on efficiency and quality, such as resource utilization, and error rates. Other KPIs are also crucial, such as the ones related tocost reduction and customer satisfaction. For FaaS, the most relevant include also data security, data management, and network speed.This research provides a valuable KPI framework for FaaS developers, aidingin strategic decision making and deployment in industrial settings. It also contributes to a broader understanding of KPIs in manufacturing, which benefits both researchers and industrial practitioners.The results of the review, though, fail to address other crucial indicators for ‘asa-Service’ business, such as Churn Rate and Total Contract Value. Future research will address these limitations through methods ranging from questionnaires to practitioner interviews, with the aim of gathering the knowledge needed for real-world implementations.