• Energy Research

[Resumen] En la actualidad, en gran medida debido al auge del vehículo eléctrico, los sistemas de almacenamiento energético son cada vez una necesidad mayor siendo tanto las baterías eléctricas como las pilas de combustible, las dos tecnologías en mayor desarrollo en los últimos años. Sin embargo, no es suficiente sólo desarrollar sistemas de almacenamiento de energía, sino que es indispensable maximizar la eficiencia de los mismos, para garantizar el máximo aprovechamiento de la energía almacenada. Para alcanzar dicho objetivo, uno de los aspectos más relevantes es el poder predecir con suficiente exactitud y antelación tanto la generación como el consumo energético que se haría sobre el dispositivo de almacenamiento. Es por ello, que la presente investigación se centra en el desarrollo de un sistema híbrido de modelado de una celda de combustible mediante técnicas de aprendizaje no supervisado para agrupamientos, combinadas con técnicas de regresión para modelado. Finalmente, los modelos generados con conjunto de datos real proveniente de un sistema de generación y almacenamiento de energía mediante una celda de hidrógeno, son validados obteniendo resultados altamente satisfactorios. [Abstract] Currently, largely due to the rise of the electric vehicle, energy storage systems are becoming agreater need, being both electric batteries and fuel cells, the two most developed technologies in recent years. However, it is not enough just to develop energy storage system, but it is essential to maximize the efficiency of them, in order to take the maximum advantage of the stored energy. To reach this goal, one of the most relevant aspects is to predict with enough accuracy and in advance both the generation and consumption of energy that will be made on the storage device. For this reason, the present research focuses on the development of a hybrid system for modeling a fuel cell using unsupervised learning techniques for clustering combined with regression techniques for modeling. Finally, the models generated on a real dataset, coming from an experimental real generation and storage system of energy by means of a hydrogen cell, are validated obtaining highly satisfactory results.

Present research proposes the application of unsupervised and supervised machine‐learning techniques to characterize Android malware families. More precisely, a novel unsupervised neural‐projection method for dimensionality‐reduction, namely, Beta Hebbian Learning (BHL), is applied to visually analyze such malware. Additionally, well‐known supervised Decision Trees (DTs) are also applied for the first time in order to improve characterization of such families and compare the original features that are identified as the most important ones. The proposed techniques are validated when facing real‐life Android malware data by means of the well‐known and publicly available Malgenome dataset. Obtained results support the proposed approach, confirming the validity of BHL and DTs to gain deep knowledge on Android malware.

Energy storage plays a key role in the modern global economy, in which variable renewable energies are growingly acquiring a major part. One option for energy storage is the production of hydrogen through electrolysis of water with renewable electricity, which can later be used again to produce electricity in a fuel cell, internal combustion engine or gas turbine, among other applications. Renewable hydrogen is quickly approaching economic competitiveness and enjoying unprecedented political and business momentum, with the number of favorable policies and projects worldwide expected to increase rapidly in the coming years. The rising interest in this storage alternative is driven by the urgency of greenhouse gas emission mitigation, by the falling costs of renewable power and by systems integration challenges due to rising shares of variable renewable power supply. This book aims at reviewing the different available technologies for hydrogen production, storage and final use as an energy vector.

This paper proposes a methodology for dealing with an issue of crucial practical importance in real engineering systems such as fault detection and recovery of a sensor. The main goal is to define a strategy to identify a malfunctioning sensor and to establish the correct measurement value in those cases. As study case, we use the data collected from a geothermal heat exchanger installed as part of the heat pump installation in a bioclimatic house. The sensor behaviour is modeled by using six different machine learning techniques: Random decision forests, gradient boosting, extremely randomized trees, adaptive boosting, k-nearest neighbors, and shallow neural networks. The achieved results suggest that this methodology is a very satisfactory solution for this kind of systems.

AbstractA large part of technological advances, especially in the field of industry, have been focused on the optimization of productive processes. However, the detection of anomalies has turned out to be a great challenge in fields like industry, medicine or stock markets. The present work addresses anomaly detection on a control level plant. We propose the application of different intelligent techniques, which allow to obtain one-class classifiers using real data taken from the correct plant operation. The performance of each classifier is assessed and validated with real created faults, achieving successful overall results.

Over the last decades, the concept of cybersecurity has been gaining weight in many fields, such as industry or telecommunications, among others. Cybersecurity is defined as a set of processes and technologies designed to protect programs, computers, communication networks and data against attacks and/or unauthorized access, thus ensuring the confidentiality, integrity and availability of systems.

AbstractThe devastating consequences of climate change have resulted in the promotion of clean energies, being the wind energy the one with greater potential. This technology has been developed in recent years following different strategic plans, playing special attention to wind generation. In this sense, the use of bicomponent materials in wind generator blades and housings is a widely spread procedure. However, the great complexity of the process followed to obtain this kind of materials hinders the problem of detecting anomalous situations in the plant, due to sensors or actuators malfunctions. This has a direct impact on the features of the final product, with the corresponding influence in the durability and wind generator performance. In this context, the present work proposes the use of a distributed anomaly detection system to identify the source of the wrong operation. With this aim, five different one-class techniques are considered to detect deviations in three plant components located in a bicomponent mixing machine installation: the flow meter, the pressure sensor and the pump speed.