Modeling the performance of a sorption thermal energy storage reactor using artificial neural networks

Luca Scapino (Corresponding author), Herbert A. Zondag, Jan Diriken, Camilo C.M. Rindt, Johan van Bael, Adriano Sciacovelli

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Uittreksel

Sorption technology has the potential to provide high energy density thermal storage units with negligible losses. However, major experimental and computational advancements are necessary to unlock the full potential of such storage technology, and to efficiently model its performance at system scale. This work addresses for the first time, the development, use and capabilities of neural networks models to predict the performance of a sorption thermal energy storage system. This type of models has the potential to have a lower computational cost compared to traditional physics-based models and an easier integrability into broader energy system models. Two neural network architectures are proposed to predict dynamically the state of charge, outlet temperature and therefore thermal power output of a sorption storage reactor. Every neural network architecture has been investigated in 32 different configurations for the two operating modes (hydration and dehydration), and a systematic training procedure identified the best configuration for each architecture and each operating mode. A campaign of test cases was thoroughly investigated to assess the performance of the proposed neural network architectures. The results show that the proposed model is capable to accurately replicate and predict the dynamic behavior of the storage system, with mean squared error estimators below 2 · 10−3 and 50 °C2 for the state of charge and the outlet temperature outputs, respectively. Our findings, therefore, highlight the potential of an artificial neural networks based modelling technique for sorption heat storage, which is accurate, computationally efficient, and with the potential to be driven by real time data.
TaalEngels
Artikelnummer113525
Aantal pagina's15
TijdschriftApplied Energy
Volume253
DOI's
StatusGepubliceerd - 1 nov 2019

Vingerafdruk

Thermal energy
artificial neural network
Energy storage
Sorption
sorption
Neural networks
Network architecture
modeling
Heat storage
thermal power
Dehydration
hydration
dehydration
Hydration
energy
energy storage
reactor
physics
Physics
temperature

Trefwoorden

    Citeer dit

    @article{5e4039c7e12346ca981d8c883ce0de32,
    title = "Modeling the performance of a sorption thermal energy storage reactor using artificial neural networks",
    abstract = "Sorption technology has the potential to provide high energy density thermal storage units with negligible losses. However, major experimental and computational advancements are necessary to unlock the full potential of such storage technology, and to efficiently model its performance at system scale. This work addresses for the first time, the development, use and capabilities of neural networks models to predict the performance of a sorption thermal energy storage system. This type of models has the potential to have a lower computational cost compared to traditional physics-based models and an easier integrability into broader energy system models. Two neural network architectures are proposed to predict dynamically the state of charge, outlet temperature and therefore thermal power output of a sorption storage reactor. Every neural network architecture has been investigated in 32 different configurations for the two operating modes (hydration and dehydration), and a systematic training procedure identified the best configuration for each architecture and each operating mode. A campaign of test cases was thoroughly investigated to assess the performance of the proposed neural network architectures. The results show that the proposed model is capable to accurately replicate and predict the dynamic behavior of the storage system, with mean squared error estimators below 2 · 10−3 and 50 °C2 for the state of charge and the outlet temperature outputs, respectively. Our findings, therefore, highlight the potential of an artificial neural networks based modelling technique for sorption heat storage, which is accurate, computationally efficient, and with the potential to be driven by real time data.",
    keywords = "Artificial neural networks, Sorption heat storage, Energy efficiency, Thermal energy storage",
    author = "Luca Scapino and Zondag, {Herbert A.} and Jan Diriken and Rindt, {Camilo C.M.} and {van Bael}, Johan and Adriano Sciacovelli",
    year = "2019",
    month = "11",
    day = "1",
    doi = "10.1016/j.apenergy.2019.113525",
    language = "English",
    volume = "253",
    journal = "Applied Energy",
    issn = "0306-2619",
    publisher = "Elsevier",

    }

    Modeling the performance of a sorption thermal energy storage reactor using artificial neural networks. / Scapino, Luca (Corresponding author); Zondag, Herbert A.; Diriken, Jan; Rindt, Camilo C.M.; van Bael, Johan; Sciacovelli, Adriano.

    In: Applied Energy, Vol. 253, 113525, 01.11.2019.

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    TY - JOUR

    T1 - Modeling the performance of a sorption thermal energy storage reactor using artificial neural networks

    AU - Scapino,Luca

    AU - Zondag,Herbert A.

    AU - Diriken,Jan

    AU - Rindt,Camilo C.M.

    AU - van Bael,Johan

    AU - Sciacovelli,Adriano

    PY - 2019/11/1

    Y1 - 2019/11/1

    N2 - Sorption technology has the potential to provide high energy density thermal storage units with negligible losses. However, major experimental and computational advancements are necessary to unlock the full potential of such storage technology, and to efficiently model its performance at system scale. This work addresses for the first time, the development, use and capabilities of neural networks models to predict the performance of a sorption thermal energy storage system. This type of models has the potential to have a lower computational cost compared to traditional physics-based models and an easier integrability into broader energy system models. Two neural network architectures are proposed to predict dynamically the state of charge, outlet temperature and therefore thermal power output of a sorption storage reactor. Every neural network architecture has been investigated in 32 different configurations for the two operating modes (hydration and dehydration), and a systematic training procedure identified the best configuration for each architecture and each operating mode. A campaign of test cases was thoroughly investigated to assess the performance of the proposed neural network architectures. The results show that the proposed model is capable to accurately replicate and predict the dynamic behavior of the storage system, with mean squared error estimators below 2 · 10−3 and 50 °C2 for the state of charge and the outlet temperature outputs, respectively. Our findings, therefore, highlight the potential of an artificial neural networks based modelling technique for sorption heat storage, which is accurate, computationally efficient, and with the potential to be driven by real time data.

    AB - Sorption technology has the potential to provide high energy density thermal storage units with negligible losses. However, major experimental and computational advancements are necessary to unlock the full potential of such storage technology, and to efficiently model its performance at system scale. This work addresses for the first time, the development, use and capabilities of neural networks models to predict the performance of a sorption thermal energy storage system. This type of models has the potential to have a lower computational cost compared to traditional physics-based models and an easier integrability into broader energy system models. Two neural network architectures are proposed to predict dynamically the state of charge, outlet temperature and therefore thermal power output of a sorption storage reactor. Every neural network architecture has been investigated in 32 different configurations for the two operating modes (hydration and dehydration), and a systematic training procedure identified the best configuration for each architecture and each operating mode. A campaign of test cases was thoroughly investigated to assess the performance of the proposed neural network architectures. The results show that the proposed model is capable to accurately replicate and predict the dynamic behavior of the storage system, with mean squared error estimators below 2 · 10−3 and 50 °C2 for the state of charge and the outlet temperature outputs, respectively. Our findings, therefore, highlight the potential of an artificial neural networks based modelling technique for sorption heat storage, which is accurate, computationally efficient, and with the potential to be driven by real time data.

    KW - Artificial neural networks

    KW - Sorption heat storage

    KW - Energy efficiency

    KW - Thermal energy storage

    U2 - 10.1016/j.apenergy.2019.113525

    DO - 10.1016/j.apenergy.2019.113525

    M3 - Article

    VL - 253

    JO - Applied Energy

    T2 - Applied Energy

    JF - Applied Energy

    SN - 0306-2619

    M1 - 113525

    ER -