Persona: Dormido Canto, Sebastián
Cargando...
Dirección de correo electrónico
ORCID
0000-0001-7652-5338
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Dormido Canto
Nombre de pila
Sebastián
Nombre
4 resultados
Resultados de la búsqueda
Mostrando 1 - 4 de 4
Publicación Disruption prediction with artificial intelligence techniques in tokamak plasmas(Springer Nature, 2022-06-06) Vega, J.; Murari, A.; Rattá, Giuseppe A.; Gelfusa, Michela; Contributors, JET.; Dormido Canto, SebastiánIn nuclear fusion reactors, plasmas are heated to very high temperatures of more than 100 million kelvin and, in so-called tokamaks, they are confined by magnetic fields in the shape of a torus. Light nuclei, such as deuterium and tritium, undergo a fusion reaction that releases energy, making fusion a promising option for a sustainable and clean energy source. Tokamak plasmas, however, are prone to disruptions as a result of a sudden collapse of the system terminating the fusion reactions. As disruptions lead to an abrupt loss of confinement, they can cause irreversible damage to present-day fusion devices and are expected to have a more devastating effect in future devices. Disruptions expected in the next-generation tokamak, ITER, for example, could cause electromagnetic forces larger than the weight of an Airbus A380. Furthermore, the thermal loads in such an event could exceed the melting threshold of the most resistant state-of-the-art materials by more than an order of magnitude. To prevent disruptions or at least mitigate their detrimental effects, empirical models obtained with artificial intelligence methods, of which an overview is given here, are commonly employed to predict their occurrence—and ideally give enough time to introduce counteracting measures.Publicación A novel feature engineering approach for high-frequency financial data(Elsevier, 2023-10) Mantilla, Pablo; Dormido Canto, SebastiánFeature engineering for high-frequency financial data based on constructing dynamic data subsets, defined by time intervals in which high-frequency trends occur, is proposed. These intervals are obtained through time series segmentation. This methodology allows us to extract and analyze variables by intraday trends as well as to feed artificial intelligence models to forecast response variables in future trends. Furthermore, to show how to use this feature engineering, this methodology is applied to estimate high-frequency volatility, duration and direction linked to future intraday trends, developing multiclass classification models based on the machine learning method extreme gradient boosting. Experimentation was conducted using high-frequency financial data from the Brazil Stock Exchange, corresponding to 206 trading days related to 20 listed assets from this financial market.Publicación An event-based adaptation of the relay feedback experiment for frequency response identification of stable processes(Elsevier, 2023-04-13) Sánchez Moreno, José; Torre Cubillo, Luis de la; Chacón Sombría, Jesús; Dormido Canto, Sebastián; Elsevier; https://orcid.org/0000-0003-0898-3462An event-based modification of the classical relay feedback experiment without the inclusion of additional elements (integrator, time delay, . . . ) for identification of the spectrum of stable processes between zero and the phase cross-over frequency is presented. By inserting an event-based sampler in the control loop, the natural behaviour of a classical relay is simulated and the system is forced to work in two modes. The event-based sampler activates the first mode by sending control actions to the process every time the error signal crosses zero; this mode is to discover the approximated value of the cross-over frequency ω180◦ . During the second mode, the event-based sampler sends samples to the process simulating that the error signal crosses zero at ω180◦ /N where N is the number of points to identify in the range 0 ≤ ω ≤ ω180◦ . One advantage of this procedure is that the logic used in an already existing relay feedback experiment to fit a transfer function model or tune a controller could be maintained just replacing the relay block by the event-based sampler block presented in the paper. Simulations and experiments with different processes and in presence of noise demonstrate the effectivity of the procedure.Publicación Obtaining high preventive and resilience capacities in critical infrastructure by industrial automation cells(Elsevier, 2020-06) González, Santiago G.; Dormido Canto, Sebastián; Sánchez Moreno, JoséThe advances in Information Technologies (ITs) are providing Industrial Control Systems (ICS) with a great capacity for interconnection and adaptability. However, the use of communication networks makes ICS highly vulnerable. Consequently, it is essential to develop methodologies for the identification and subsequent classification of the ICS that intervene in critical infrastructure assets with any level of complexity, scalability and heterogeneity. The System and Infrastructure of Knowledge for Real Experimentation by means of Cells of Industrial Automation (SIKRECIA), described in this work, provides new capabilities for research, development, simulation and testing of the functioning of these systems, and the ability to foresee the behavior of a specific system in industrial production. The scenarios recreated through SIKRECIA have the ability to anticipate new threats that affect the ICS of critical infrastructures. Using SIKRECIA, a specific vulnerability of a PLC has been verified through the engineering programmed for the management of a traffic light control system. The results obtained demonstrate the high dependence between IT and OT (Operation Technologies) systems and therefore the importance of being able to recreate those environments before entering into operation. As SIKRECIA is an open system, it can use components from different industrial manufacturers to cover the existing architectures in the process industry.