Repository logo
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    or
    New user? Click here to register.
Repository logo

Repositorio Institucional de la Universidad de Murcia

Repository logoRepository logo
  • Communities & Collections
  • All of DSpace
  • Statistics
  • menu.section.collectors
  • menu.section.acerca
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    or
    New user? Click here to register.
  1. Home
  2. Browse by Subject

Browsing by Subject "Industry 4.0"

Now showing 1 - 6 of 6
Results Per Page
Sort Options
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    A supervised ML Biometric Continuous Authentication System for Industry 4.0
    (IEEE, 2022-04-29) Espín López, Juan Manuel; Esquembre, Francisco; Martínez Pérez, Gregorio; Marín-Blázquez, Javier G.; Huertas Celdrán, Alberto; Matemáticas
    Continuous authentication (CA) is a promis- ing approach to authenticate workers and avoid security breaches in the industry, especially in Industry 4.0, where most interaction between workers and devices takes place. However, introducing CA in industries raises unsolved questions regarding machine learning (ML) models: i) its precision and performance, ii) its robustness and iii) the issue about if or when to retrain the models. To answer these questions, this work explores these issues with a proposed supervised vs non-supervised ML-based CA sys- tem that uses sensors, applications statistics, or speaker data collected by the operator’s devices. Experiments show supervised models with Equal Error Rates of 7.28% using sensors data, 9.29% with statistics, and 0.31% with voice, a significant improvement of 71.97%, 62.14%, and 97.08%, respectively, over unsupervised models. Voice is the most robust dimension when adding new workers, with less than 2% of false acceptance rate even if workforce size is doubled.
  • Loading...
    Thumbnail Image
    Publication
    Restricted
    Assessment of functional condition of equipment in industrial plants based on multiple measurements
    (Elsevier, 2020-06-01) Gómez de León Hijes, Félix; Sánchez Robles, J.; Martínez García, F. M.; Alarcón García, Mariano; Rivera, E. Belén; Ingeniería de la Información y las Comunicaciones
    Knowing the functional condition of production equipment at all times, that is, detecting and assessing any possible malfunction of it from the earliest stage of its appearance, is essential to avoid unforeseen interruptions in the production of any industrial plant. This work provides a methodology for the automatic assessment of the functional condition of the machines through joint evaluation of multiple measurements of one or several parameters, such as vibration or temperature, used in the Condition Based Maintenance for plant equipment. In this way, the information of the machinery status can be immediately implemented in the plant's computer system, making it accessible in real-time to all staff. Because of the dependencies that exist between the components of the machine, false alarms often occur when multiple measurements are analyzed separately. To avoid this, based on the limit values of the standard scale used to evaluate each parameter, this work proposes the use of variable limits, which vary according to the number of available measurements for every piece of equipment, in order to take into account the joint effect of all the measurements when evaluating its functional condition. The result is a novel method that calculates a new variable scale to evaluate each set of measurements carried out on a machine, allowing an immediate assessment of its functional condition, avoiding many false alarms and, therefore, helping to improve decision making.
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    CGAPP: A continuous group authentication privacy-preserving platform for industrial scene
    (Elsevier ltd., 2023-10-09) Espín López, Juan Manuel; Esquembre, Francisco; Martínez Pérez, Gregorio; Marín-Blázquez, Javier G.; Huertas Celdrán, Alberto; Matemáticas
    In Industry 4.0, security begins with the workers’ authentication, which can be done individually or in groups. Recently, group authentication is gaining momentum, allowing users to authenticate as group members without the need to specify the particular individual. Continuous authentication and federated learning are promising techniques that might help group authentication by providing privacy, by its own design, and extra security compared to traditional methods based on passwords, tokens, or biometrics. However, these techniques have not previously been combined or evaluated for authenticating workers in Industry 4.0. Thus, this paper proposes a novel continuous group authentication privacy-preserving (CGAPP)platform that is suitable for the industry. The CGAPP platform incorporates statistical data from workers’ smartphones and employs federated learning-based outlier detection for group worker authentication while ensuring the privacy of personal data vectors. A series of experiments were performed to measure the framework’s suitability and address the following research questions: (i) What is the cost of using FL compared to full data access in industrial scenarios? (ii) How robust is federated learning against adversarial attacks, specifically, how much malicious data is required to deceive the model? and (iii) How much noise is required to disrupt the authentication system? The results demonstrate the effectiveness of the CGAPP platform in the industry since it provides factory safety while preserving privacy. This platform achieves an accuracy of 92%, comparable to the 96% obtained by traditional approaches in the literature that do not address privacy concerns. The platform’s robustness is tested against attacks in the second and third experiments, and various countermeasures are evaluated. While the CGAPP platform exhibits certain vulnerabilities to data injection attacks, straightforward countermeasures can alleviate them. Nevertheless, the system’s performance experiences a notable impact in the event of a data perturbation attack, and the countermeasures investigated are ineffective in addressing this issue.
  • Loading...
    Thumbnail Image
    Publication
    Restricted
    Energy and maintenance management systems in the context of industry 4.0. Implementation in a real case
    (Elsevier, 2021-03-01) Alarcón García, Mariano; Martínez García, Fernando Manuel; Gómez de León Hijes, Félix; Ingeniería de la Información y las Comunicaciones
    Industry 4.0 facilities and organization structures are used to improve energy efficiency and maintenance in industry. One of the challenges of Industry 4.0 is the urgent need to lower the consumption of energy, water and raw materials, as well as to ensure the safe and reliable running of a plant and reduce maintenance costs. The work presented herein proposes the low cost integration of Energy Management Systems (EMS) and Maintenance Management Systems (MMS) within the main management systems of a company, formed by organization appliances such as Enterprise Resource Planning (ERP), Distributed Control Systems (DCS) or Manufacturing Execution Systems (MES), The proposal has the virtue of introducing maintenance and energy saving in the company agenda. A central role in such integration is played by the generalized use of network analyzers in electric machinery; the information gained from these network analyzers is not only interesting for ascertaining energy consumption, but also for understanding the real operating conditions of the machinery, identifying premature failures or abnormal behavior. Dramatic reductions (about 50%) in energy consumption and required maintenance inspections, as well as the extension of piece replacement time, are achieved at a reasonable cost. The proposed measures have been implemented by a multinational corporation, owners of a chemical plant located in El Palmar (Murcia-Spain).
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    Exploring skill requirements for the industry 4.0: a worker-oriented approach
    (Universidad de Murcia. Servicio de Publicaciones, 2021) Peña-Jimenez, Marco; Battistelli, Adalgisa; Odoardi, Carlo; Antino, Mirko
    Tecnologías emergentes están dando forma al mundo del trabajo, creando así una industria cada vez más digital, también conocida como "Industria 4.0". Por tanto, examinar el requirimiento de habilidades se vuelve esencial para facilitar la adaptación organizacional a esta revolución tecnológica. El objetivo de este estudio fue explorar la percepción de las habilidades requeridas por los trabajadores de una empresa manufacturera altamente tecnológica. En el Estudio 1 (n = 671), se realizó un análisis factorial exploratorio para identificar grupos relevantes de habilidades. Un año después, en el Estudio 2 (n = 176), confirmamos la estructural factorial a través de un análisis factorial confirmatorio y realizamos un análisis de curva de crecimiento latente para examinar posibles cambios en las habilidades requeridas debido al confinamiento y el trabajo remoto forzado durante la pandemia del COVID-19. Los resultados mostraron que las habilidades cognitivas, funcionales del negocio, estratégicas y de gestión de personas se consideran recursos importantes para la industria 4.0, siendo las habilidades funcionales del negocio más relevantes en el tiempo 2. Además, identificamos diferencias entre gerentes y subordinados con respecto a tales habilidades. Discutimos las implicaciones teóricas y prácticas para el desarrollo de habilidades en la era digital.
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    Realidad aumentada como soporte de asistencia y formación integrada en la Industria 4.0
    (Universidad de Murcia, 2025-07-28) Morales Méndez, Ginés; Cerro Velázquez, Francisco del; Escuela Internacional de Doctorado; Escuela Internacional de Doctorado
    La tesis doctoral tiene como finalidad explorar el papel de la realidad aumentada (RA) como tecnología habilitadora para optimizar la asistencia técnica y la formación en entornos industriales propios de la Industria 4.0. Esta investigación se enmarca en la convergencia entre los procesos de digitalización avanzados, los sistemas ciberfísicos y la transformación del trabajo humano, con el objeto de mejorar la eficiencia operativa, reducir errores y reforzar la seguridad industrial. El objetivo general del estudio es diseñar una arquitectura basada en RA que se adapte dinámicamente a las habilidades del operario, al tipo de tarea y a las condiciones del entorno, proporcionando apoyo operativo y formativo en tiempo real. A partir de este propósito central, se plantean cinco objetivos específicos: (1) identificar factores clave en la implementación de la RA en la industria, (2) cuantificar su impacto frente a métodos tradicionales, (3) desarrollar una arquitectura adaptativa, (4) validar experimentalmente un prototipo funcional y (5) proponer recomendaciones para su integración efectiva. La investigación se ha desarrollado en cinco fases. En primer lugar, se llevó a cabo una revisión sistemática y un análisis bibliométrico de 60 estudios relevantes, lo que permitió identificar las principales áreas de aplicación de la RA (como el mantenimiento, la formación o la seguridad) y detectar vacíos en la estandarización y la validación empírica. En segundo lugar, se realizó un metaanálisis cuantitativo con el fin de sintetizar los efectos de la RA sobre indicadores como la eficiencia, la tasa de errores y la carga cognitiva, donde se evidenció el valor añadido de la RA frente a métodos tradicionales. La tercera fase consistió en el diseño de una arquitectura adaptativa de RA, capaz de modular el contenido visual según el perfil del operario y el contexto del entorno. El diseño contempló variables como la experiencia del usuario, la complejidad de la tarea y los requisitos de seguridad. A continuación, se procedió al desarrollo y validación experimental de un prototipo basado en Microsoft HoloLens 2, Unity 3D y Vuforia, en un entorno industrial simulado, los ensayos demostraron mejoras significativas en la precisión, en los tiempos de ejecución, en el mantenimiento predictivo y em la reducción de la carga cognitiva. Por último, se formularon un conjunto de recomendaciones orientadas a facilitar la adopción de la RA en entornos reales, abarcando aspectos técnicos, formativos, organizativos y normativos. La tesis demuestra que la RA tiene un impacto significativo en la mejora de procesos industriales, al facilitar la toma de decisiones, incrementar la seguridad y proporcionar formación contextualizada en tiempo real. Los resultados avalan la viabilidad de una arquitectura adaptativa que optimiza la interacción humano-máquina y refuerza la transferencia de conocimiento operativo. No obstante, el estudio también identifica limitaciones, como las carencias estructurales en la digitalización de la industria española, la volatilidad de los dispositivos aumentados y la escasa madurez tecnológica de algunos sectores. Estas barreras justifican la necesidad de seguir investigando en contextos reales, fomentar la interoperabilidad de sistemas y avanzar hacia modelos más escalables e integrables

DSpace software copyright © 2002-2026 LYRASIS

  • Cookie settings
  • Accessibility
  • Send Feedback