Capel, Manuel I.2021-08-262021-08-262021Capel, M.I. ML models for real-time hybrid systems. En XLII Jornadas de Automática: libro de actas. Castelló, 1-3 de septiembre de 2021 (pp. 752-759). DOI capítulo: https://doi.org/10.17979/spudc.9788497498043.752 DOI libro: https://doi.org/10.17979/spudc.9788497498043978-84-9749-804-3http://hdl.handle.net/2183/28376[Abstract] A correct system design can be systematically obtained from a specification model of a real-time system that integrates hybrid measurements In a realistic industrial environment, this has been carried out through complete Matlab / Simulink / Stateflow models. However, there is a widespread interest in carrying out that modeling resorting to Machine Learning models, which can be understood as Automated Machine Learning for Real-time systems that present some degree of hybridation. An AC motor controller which must be able to maintain a constant air flow through a filter is one of these systems. The article also discusses a practical application of the method for implementing a closed loop control system to show how the proposed procedure can be applied to derive complete hybrid system designs with ANN.engAtribución-NoComercial-CompartirIgual 4.0 Internacional https://creativecommons.org/licenses/by-nc-sa/4.0/deed.eshttp://creativecommons.org/licenses/by-nc-sa/3.0/es/Automated machine learningRealtime embedded control systemsCyber-physical systemsTime series forecastingNeural networksEnergy efficiencyconference outputopen accesshttps://doi.org/10.17979/spudc.9788497498043.752