In the modern era of industrial digitalization, the convergence of the Internet of Things (IoT), advanced data analysis, augmented reality (AR) and virtual reality (VR) is significantly transforming various industrial sectors. This research aimed to study and develop a proposal for an integrated system that combines IoT, data analysis, AR and VR for the monitoring and maintenance of industrial equipment. The importance of this research lies in its potential to contribute to the implementation of predictive maintenance solutions, which can significantly reduce machine downtime in an industrial environment and thus reduce or prevent operational failures. The central research question of this work was the following: how can the integration of IoT, data analysis and augmented and virtual reality contribute to optimizing industrial maintenance? We tested the combination of technologies to enable the creation of an effective predictive maintenance system, capable of alerting operators to anomalous conditions and providing detailed visual instructions for maintenance tasks. As a result, a prototype system was developed and tested, and it has shown the potential to evolve into a real system in an industrial environment.

This article presents an integrated approach that combines Virtual Reality (VR), Augmented Reality (AR), and an Intelligent Virtual Assistant (IVA) to support training, on-the-job assistance, and maintenance in a textile manufacturing environment. The solution spans three systems: RioRV, a Unity-based VR platform for immersive, step-by-step procedure rehearsal, instructional videos, and simplified 3D animations; RiAR, a mobile AR application for assisted maintenance and access to real-time and historical machine data using marker-based (VuMark) identification; and Ria, a web-based IVA that delivers document-grounded answers, operational queries over a secure plant API, short-horizon forecasting, and a narrow set of guarded remote actions. The architecture prioritizes human-centered Industry 5.0 principles—safety, usability, and resilience—by enabling operators to learn procedures in VR, execute tasks with AR overlays and maintenance media at the workstation, and obtain concise, source-cited guidance via the IVA without leaving immersion. In the case study with a spinning section at RIOPELE, the convergence of VR, AR, and IVA reduced reliance on bulky manuals, shortened time-to-information for machine status, and established a feedback loop in which training and operational experience continuously enrich the knowledge base.

The increasing digitalization of industrial environments has led to the emergence of new paradigms such as Digital Twins (DTs), which enable real-time connections between physical assets and their virtual counterparts. In this context, the Coffee Twin system was developed as a modular and controlled demonstrator to explore, present, and validate the integration of DT technology with Augmented Reality (AR), Virtual Reality (VR), and voice-based interaction. A coffee machine was selected as the case study due to its manageable complexity, low-risk operation, and potential to illustrate concepts that can later be extended to more complex industrial systems. The system architecture is centered on a Raspberry Pi, which supports local data acquisition from temperature and humidity sensors, mechanical actuation through a servo motor, and remote control via a smart switch. To interact with the system, three software applications were developed: a Web application, an AR application for contextual visualization and remote interaction, and a VR application that recreates the operation of the machine within an immersive 3D environment. Beyond the technical implementation, the prototype was evaluated in demonstration and user-testing sessions in which 80 participants, mostly secondary-school pupils and university students, completed a coffee-making task across the three applications and then answered a System Usability Scale (SUS) questionnaire. The analysis of the 80 valid responses yielded a mean SUS score of 69.2 (standard deviation 15.9; 95% confidence interval [65.7, 72.8]), which corresponds to acceptable, slightly above-average usability and indicates that combining real-time sensing, remote actuation, and multimodal interaction in a single low-cost platform is perceived as usable across a heterogeneous, predominantly non-expert audience. The main contribution of this work is therefore not a new Digital Twin algorithm, but an accessible, modular, and reproducible integration of Web, AR, VR, and voice interaction around a physical asset, supported by usability evidence. Overall, Coffee Twin shows how a low-cost and multimodal DT demonstrator can support the communication, experimentation, and early exploration of Industry 4.0 concepts in educational and pre-industrial settings.