Browsing by Keyword "Artificial intelligence"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Algoritmos de generación de consigna de velocidad angular y ajuste del control de velocidad en aerogeneradores de media potencia(Universidad del País Vasco, 2017-02-17) González-González, A.; Zulueta Guerrero, EkaitzEl presente trabajo de tesis está dirigido a la optimización del algoritmo de consigna de velocidad angular del rotor de un aerogenerador de media potencia (100kW). El cálculo de los parámetros integral y proporcional del controlador PI se realiza mediante la técnica de programación de ganancias para seis aproximaciones del modelo de aerogenerador: Método I, II, III, IV, V y VI. Se muestran cuatro estrategias de ajuste de la consigna de velocidad angular del rotor: Constante, convencional, aprendizaje por refuerzo (RL) y optimización metaheurística por enjambre de partículas (PSO). Los métodos y las estrategias se evalúan en base a múltiples objetivos contrapuestos: maximizar la energía captada del viento, minimizar el error de la velocidad angular, minimizar la aceleración angular del rotor y minimizar la velocidad angular del pitch. Por un lado, comparando los métodos, los mejores resultados se obtienen con usando los métodos IV, V y VI. Por otro lado, comparando las estrategias, la estrategia RL no mejora significativamente los resultados en comparación con la estrategia constante y convencional, mientras que la estrategia PSO obtiene los mejores resultados. (c)2017 ASIER GONZALEZ GONZALEZItem ASINA Project: Towards a Methodological Data-Driven Sustainable and Safe-by-Design Approach for the Development of Nanomaterials: Towards a Methodological Data-Driven Sustainable and Safe-by-Design Approach for the Development of Nanomaterials(2022-01-28) Furxhi, Irini; Perucca, Massimo; Blosi, Magda; Lopez de Ipiña, Jesús; Oliveira, Juliana; Murphy, Finbarr; Costa, Anna Luisa; SMART_MONThe novel chemical strategy for sustainability calls for a Sustainable and Safe-by-Design (SSbD) holistic approach to achieve protection of public health and the environment, industrial relevance, societal empowerment, and regulatory preparedness. Based on it, the ASINA project expands a data-driven Management Methodology (ASINA-SMM) capturing quality, safety, and sustainability criteria across the Nano-Enabled Products’ (NEPs) life cycle. We base the development of this methodology through value chains of highly representative classes of NEPs in the market, namely, (i) self-cleaning/air-purifying/antimicrobial coatings and (ii) nano-structured capsules delivering active phases in cosmetics. These NEPs improve environmental quality and human health/wellness and have innovative competence to industrial sectors such as healthcare, textiles, cosmetics, and medical devices. The purpose of this article is to visually exhibit and explain the ASINA approach, which allows identifying, combining, and addressing the following pillars: environmental impact, techno-economic performance, functionality, and human and environmental safety when developing novel NEPs, at an early stage. A metamodel supports the above by utilizing quality data collected throughout the NEPs’ life cycle, for maximization of functionality (to meet stakeholders needs) and nano-safety (regulatory obligations) and for the minimization of costs (to meet business requirements) and environmental impacts (to achieve sustainability). Furthermore, ASINA explores digitalization opportunities (digital twins) to speed the nano-industry translation into automatic progress towards economic, social, environmental, and governance sustainability.Item Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence(2022-03) Holzinger, Andreas; Dehmer, Matthias; Emmert-Streib, Frank; Cucchiara, Rita; Augenstein, Isabelle; Ser, Javier Del; Samek, Wojciech; Jurisica, Igor; Díaz-Rodríguez, Natalia; IAMedical artificial intelligence (AI) systems have been remarkably successful, even outperforming human performance at certain tasks. There is no doubt that AI is important to improve human health in many ways and will disrupt various medical workflows in the future. Using AI to solve problems in medicine beyond the lab, in routine environments, we need to do more than to just improve the performance of existing AI methods. Robust AI solutions must be able to cope with imprecision, missing and incorrect information, and explain both the result and the process of how it was obtained to a medical expert. Using conceptual knowledge as a guiding model of reality can help to develop more robust, explainable, and less biased machine learning models that can ideally learn from less data. Achieving these goals will require an orchestrated effort that combines three complementary Frontier Research Areas: (1) Complex Networks and their Inference, (2) Graph causal models and counterfactuals, and (3) Verification and Explainability methods. The goal of this paper is to describe these three areas from a unified view and to motivate how information fusion in a comprehensive and integrative manner can not only help bring these three areas together, but also have a transformative role by bridging the gap between research and practical applications in the context of future trustworthy medical AI. This makes it imperative to include ethical and legal aspects as a cross-cutting discipline, because all future solutions must not only be ethically responsible, but also legally compliant.