000150666 001__ 150666
000150666 005__ 20251017144638.0
000150666 0247_ $$2doi$$a10.1007/s00521-024-10732-y
000150666 0248_ $$2sideral$$a142454
000150666 037__ $$aART-2025-142454
000150666 041__ $$aeng
000150666 100__ $$aFañanás-Anaya, Javier$$uUniversidad de Zaragoza
000150666 245__ $$aDynamical system simulation with attention and recurrent neural networks
000150666 260__ $$c2025
000150666 5060_ $$aAccess copy available to the general public$$fUnrestricted
000150666 5203_ $$aAccurate and efficient real-time simulation of nonlinear dynamic systems remains an important challenge in fields such as robotics, control systems and industrial processes, requiring innovative solutions for predictive modeling. In this work, we introduce a novel recurrent neural networks (RNN) architecture designed to simulate complex nonlinear dynamical systems. Our approach aims to predict system behavior at any time step and over any prediction horizon, using only the system’s initial state and external inputs. The proposed architecture combines RNN with multilayer perceptron and incorporates an attention mechanism to process both previous state estimates and external inputs. By training without teacher forcing, our model can iteratively estimate the system’s state over long prediction horizons. Experimental results on three public benchmarks show that our method outperforms other state-of-the-art solutions. We highlight the potential of our proposal for modeling and simulating nonlinear systems in real-world applications.
000150666 536__ $$9info:eu-repo/grantAgreement/EUR/AEI/CPP2021-008938$$9info:eu-repo/grantAgreement/EUR/AEI/TED2021-130224B-I00$$9info:eu-repo/grantAgreement/ES/DGA/T45-23R$$9info:eu-repo/grantAgreement/ES/MICINN-AEI-FEDER/PID2021-124137OB-I00
000150666 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000150666 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000150666 700__ $$0(orcid)0000-0001-9347-5969$$aLópez-Nicolás, Gonzalo$$uUniversidad de Zaragoza
000150666 700__ $$0(orcid)0000-0002-3032-954X$$aSagüés, Carlos$$uUniversidad de Zaragoza
000150666 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000150666 773__ $$g37 (2025), 2711-2731$$pNeural comput. appl.$$tNeural Computing and Applications$$x0941-0643
000150666 8564_ $$s596109$$uhttps://zaguan.unizar.es/record/150666/files/texto_completo.pdf$$yPostprint
000150666 8564_ $$s3494818$$uhttps://zaguan.unizar.es/record/150666/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000150666 909CO $$ooai:zaguan.unizar.es:150666$$particulos$$pdriver
000150666 951__ $$a2025-10-17-14:30:49
000150666 980__ $$aARTICLE