Skip to main content

PROCESAMIENTO DE INCONSISTENCIAS BASADO EN LOGICA PARA SISTEMAS INTELIGENTES EXPLICABLES: APLICACIONES

PID2022-139835NB-C22

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2022
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE LLEIDA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Repositori Obert UdL
Publication Contribución de congreso (ConferenceOutput)

Ús de la intel·ligència artificial per la simulació de dipòsits d’emmagatzematge d’energia tèrmica

  • Rojas Cala, Edgar Felipe
Els tancs d'emmagatzematge d'energia tèrmica (TES en anglès) són com bateries que guarden energia en forma de calor. Durant el seu disseny, els tancs TES poden ser modelats computacionalment per conèixer la serva eficàcia i si es comporten com es desitja; el procés de simulació pot ser costós i requerir moltes hores de treball addicional. Per a això, proposem entrenar una intel·ligència artificial (IA) capaç de fer simulació computacional de tancs TES, reduint els costos i el temps implicat en aquest procés., Aquest treball està parcialment finançat pel Ministerio de Ciencia e Innovación – Agencia Estatal de Investigación (AEI) (PID2021-123511OB-I00 – MCIN/AEI/10.13039/501100011033/FEDER, UE), el Ministerio de Ciencia e Innovación – Agencia Estatal de Investigación (AEI) (PID2022-139835NB-C22 – MCIN/AEI/10.13039/501100011033/FEDER, UE), el Ministerio de Ciencia e Innovación – Agencia Estatal de Investigación (AEI) (PID2023-152814OB-I00 – MCIN/AEI/10.13039/501100011033/FEDER, UE) i el Ministerio de Ciencia e Innovación y Universidades – Agencia Estatal de Investigación (AEI) (RED2024-153629-T). Els autors agraeixen a la Generalitat de Catalunya l’acreditació de qualitat concedida al grup de recerca GREiA (2021 SGR 01615). GREiA és un agent certificat TECNIO en la categoria de desenvolupadors tecnològics de la Generalitat de Catalunya. Aquest treball està parcialment secundat per ICREA dins del programa ICREA Academia. Edgar Freire Rojas també és agraït a: “Convocatòria 2023 d’Ajuts UdL per a la contractació de personal predoctoral en formació. Núm. Expedient: 2023 UdL 12”. Aquest projecte està cofinançat pel programa de recerca i innovació de la Unió Europea Horizon Europe dins del projecte NitRecercat2425 (GA 101162003).
Repositori Obert UdL
Publication Contribución de congreso (ConferenceOutput)

Locally-Minimal Probabilistic Explanations

  • Izza, Yacine
  • Meel, Kuldeep S.
  • Marques-Silva, Joao
Explainable Artificial Intelligence (XAI) is widely regarded as a cornerstone of trustworthy AI. Unfortunately, most work on XAI offers no guarantees of rigor. In high-stakes domains, e.g. uses of AI that impact humans, the lack of rigor of explanations can have disastrous consequences. Formal abductive explanations offer crucial guarantees of rigor and so are of interest in high-stakes uses of machine learning (ML). One drawback of abductive explanations is explanation size, justified by the cognitive limits of human decision-makers. Probabilistic abductive explanations (PAXps) address this limitation, but their theoretical and practical complexity makes their exact computation most often unrealistic. This paper proposes novel efficient algorithms for the computation of locally-minimal PAXps, which offer high-quality approximations of PXAps in practice. The experimental results demonstrate the practical efficiency of the proposed solutions., This work was supported in part by the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme, by the starting funds of ICREA, and by the project PID2022-139835NB-C22 funded by MCIN/AEI/10.13039/501100011033/FEDER, UE.
Repositori Obert UdL
Publication Contribución de congreso (ConferenceOutput)

Physics Informed Neural Networks for a Gasification Reactor

  • Fornieles, Aleix
  • Etxegarai, Maddi
  • Gibert, Daniel
  • Planes Cid, Jordi
Hydrogen arises as an alternative to decarbonize heavy industries, yet its production remains either expensive or environmentally harmful, prompting the exploration of waste-to-hydrogen gasification as a viable solution. This study addresses the challenges in accurately modeling the gasification reactor, a critical step in waste-to-hydrogen conversion, by confronting issues such as the inherent diversity of biomass and the complex interactions among its constituent properties using Artificial Intelligence. To address these challenges, we propose a methodology that integrates Physics-Informed Neural Networks, merging experimental data with physical principles to develop robust and adaptive models to predict syngas composition. Preliminary results indicate improvements in model accuracy over other models, achieving high predictive accuracies with an R2 value of 0.96 for the syngas composition, as well as greater scalability compared to existing approaches in this field., Clean Hydrogen Partnership provided financial support for this study through the Project 101137792 – HYEILD. Aleix Fornieles is a fellow of Eurecat’s ”Vicente Lopez” PhD ´ grant program. This work was supported by the Ramon y Cajal programme RYC2023- 043607-I and was funded by the Spanish Ministry of Science and Innovation (MICIN) under project PID2022-139835NB-C22.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Physics Informed Neural Networks for a Gasification Reactor

  • Fornieles, Aleix
  • Etxegarai, Maddi
  • Gibert, Daniel
  • Planes Cid, Jordi
Hydrogen arises as an alternative to decarbonize heavy industries, yet its production remains either expensive or environmentally harmful, prompting the exploration of waste-to-hydrogen gasification as a viable solution. This study addresses the challenges in accurately modeling the gasification reactor, a critical step in waste-to-hydrogen conversion, by confronting issues such as the inherent diversity of biomass and the complex interactions among its constituent properties using Artificial Intelligence. To address these challenges, we propose a methodology that integrates Physics-Informed Neural Networks, merging experimental data with physical principles to develop robust and adaptive models to predict syngas composition. Preliminary results indicate improvements in model accuracy over other models, achieving high predictive accuracies with an R2 value of 0.96 for the syngas composition, as well as greater scalability compared to existing approaches in this field., Clean Hydrogen Partnership provided financial support for this study through the Project 101137792 – HYEILD. Aleix Fornieles is a fellow of Eurecat’s ”Vicente Lopez” PhD ´ grant program. This work was supported by the Ramon y Cajal programme RYC2023- 043607-I and was funded by the Spanish Ministry of Science and Innovation (MICIN) under project PID2022-139835NB-C22.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Locally-Minimal Probabilistic Explanations

  • Izza, Yacine
  • Meel, Kuldeep S.
  • Marques-Silva, Joao
Explainable Artificial Intelligence (XAI) is widely regarded as a cornerstone of trustworthy AI. Unfortunately, most work on XAI offers no guarantees of rigor. In high-stakes domains, e.g. uses of AI that impact humans, the lack of rigor of explanations can have disastrous consequences. Formal abductive explanations offer crucial guarantees of rigor and so are of interest in high-stakes uses of machine learning (ML). One drawback of abductive explanations is explanation size, justified by the cognitive limits of human decision-makers. Probabilistic abductive explanations (PAXps) address this limitation, but their theoretical and practical complexity makes their exact computation most often unrealistic. This paper proposes novel efficient algorithms for the computation of locally-minimal PAXps, which offer high-quality approximations of PXAps in practice. The experimental results demonstrate the practical efficiency of the proposed solutions., This work was supported in part by the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme, by the starting funds of ICREA, and by the project PID2022-139835NB-C22 funded by MCIN/AEI/10.13039/501100011033/FEDER, UE.