An Approach to Develop Digital Twins in Industry.

The industry is currently undergoing a digital revolution driven by the integration of several enabling technologies. These include automation, robotics, cloud computing, industrial cybersecurity, systems integration, digital twins, etc. Of particular note is the increasing use of digital twins, which offer significant added value by providing realistic and fully functional process simulations. This paper proposes an approach for developing digital twins in industrial environments. The novelty lies in not only focusing on obtaining the model of the industrial system and integrating virtual reality and/or augmented reality but also in emphasizing the importance of incorporating other enabled technologies of Industry 4.0, such as system integration, connectivity with standard and specific industrial protocols, cloud services, or new industrial automation systems, to enhance the capabilities of the digital twin. Furthermore, a proposal of the software tools that can be used to achieve this incorporation is made. Unity is chosen as the real-time 3D development tool for its cross-platform capability and streamlined industrial system modeling. The integration of augmented reality is facilitated by the Vuforia SDK. Node-RED is selected as the system integration option, and communications are carried out with MQTT protocol. Finally, cloud-based services are recommended for effective data storage and processing. Furthermore, this approach has been used to develop a digital twin of a robotic electro-pneumatic cell.

Feature Extraction from Building Submetering Networks Using Deep Learning.

The understanding of the nature and structure of energy use in large buildings is vital for defining novel energy and climate change strategies. The advances on metering technology and low-cost devices make it possible to form a submetering network, which measures the main supply and other intermediate points providing information of the behavior of different areas. However, an analysis by means of classical techniques can lead to wrong conclusions if the load is not balanced. This paper proposes the use of a deep convolutional autoencoder to reconstruct the whole consumption measured by the submeters using the learnt features in order to analyze the behavior of different building areas. The display of weights and information of the latent space provided by the autoencoder allows us to obtain precise details of the influence of each area in the whole building consumption and its dependence on external factors such as temperature. A submetering network is deployed in the León University Hospital building in order to test the proposed methodology. The results show different correlations between environmental variables and building areas and indicate that areas can be grouped depending on their function in the building performance. Furthermore, this approach is able to provide discernible results in the presence of large differences with respect to the consumption ranges of the different areas, unlike conventional approaches where the influence of smaller areas is usually hidden.

A Deep Learning Approach for Fusing Sensor Data from Screw Compressors.

Chillers are commonly used for thermal regulation to maintain indoor comfort in medium and large buildings. However, inefficiencies in this process produce significant losses, and optimization tasks are limited because of accessibility to the system. Data analysis techniques transform measurements coming from several sensors into useful information. Recent deep learning approaches have achieved excellent results in many applications. These techniques can be used for computing new data representations that provide comprehensive information from the device. This allows real-time monitoring, where information can be checked with current working operation to detect any type of anomaly in the process. In this work, a model based on a 1D convolutional neural network is proposed for fusing data in order to predict four different control stages of a screw compressor in a chiller. The evaluation of the method was performed using real data from a chiller in a hospital building. Results show a satisfactory performance and acceptable training time in comparison with other recent methods. In addition, the model is capable of predicting control states of other screw compressors different than the one used in the training. Furthermore, two failure cases are simulated, providing an early alarm detection when a continuous wrong classification is performed by the model.

Falla de crecimiento en niños menores de 24 meses / Growth failure in children under 24 months of age

Introducción: los dos primeros años de vida postnatal constituyen un período crítico donde numerosas injurias pueden afectar el crecimiento y desarrollo con secuelas en etapas alejadas que no se pueden reparar. Para mejorar el diagnóstico y tratamiento integral del niño menor de dos años con retardo del crecimiento, se planificó este estudio prospectivo. Objetivo: aplicar un plan de estudio y tratamiento, poniendo en marcha una metodología sencilla con recursos locales accesibles a la población y analizar los factores que incidieron al inicio de la falla de crecimiento. Material y métodos: entre 1999 y 2001 ingresaron al estudio 40 niños de 6 a 24 meses que cumplieron criterios de inclusión. Fueron atendidos por un equipo interdisciplinario que los evaluó según un algoritmo diagnóstico, los trató con el plan terapéutico preestablecido y los siguió con controles adecuados a la severidad en forma personalizada. Resultados: la mediana de edad al ingreso fue de 11,6 meses. Habían sido alimentados con pecho directo exclusivo 3,5 meses en promedio, coincidiendo el enlentecimiento de la velocidad de crecimiento con el destete. La adhesión al tratamiento fue alta. A pesar de que sólo el 55 por ciento lo cumplió totalmente, la mediana de puntaje Z en el peso evolucionó de -2,41 al ingreso a -1,86 en la última evaluación. Conclusiones: la falla de crecimiento en la mayoría de los niños fue de causa nutricional, con mal manejo de los alimentos del destete. Se logró una buena evolución a partir de la captación. La metodología aplicada fue útil, pareciendo imprescindible y posible su aplicación en el primer nivel de atención.