Hot water temperature prediction using a dynamic neural network for absorption chiller application in Indonesia

Nasruddin, Sholahudin, M. Idrus Alhamid, Kiyoshi Saito

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    Weather condition particularly for solar radiation and dry bulb temperature has important role in absorption chiller performance. In this paper hot water temperature prediction in generator inlet of absorption chiller has been conducted under various weather conditions. Dry bulb temperature and global horizontal radiation are selected as predictors. Three artificial neural network (ANN) types including feed forward back-propagation, cascade forward back-propagation, and Elman back propagation models have been investigated for prediction. Moreover, numbers of neuron and time delay effects were analyzed to achieve an accurate prediction. The results show that hot water temperature in generator inlet can be predicted precisely using a feed forward back propagation neural network with the configuration of a three hour delayed input on radiation, current dry bulb temperature, seven neurons, tan-sigmoid transfer function and Bayesian regularization algorithm. The prediction results perform a good agreement between predicted and experimental values. The error resulting from training and validation is 3.1 °C and 2.6 °C with a coefficient of variation at 4.4% and 3.5% respectively.

    Original languageEnglish
    Pages (from-to)114-120
    Number of pages7
    JournalSustainable Energy Technologies and Assessments
    Volume30
    DOIs
    Publication statusPublished - 2018 Dec 1

    Fingerprint

    Backpropagation
    Neural networks
    Water
    Neurons
    Temperature
    Radiation
    Solar radiation
    Transfer functions
    Time delay

    Keywords

    • Absorption chiller
    • Hot water
    • Neural network
    • Solar radiation

    ASJC Scopus subject areas

    • Renewable Energy, Sustainability and the Environment
    • Energy Engineering and Power Technology

    Cite this

    Hot water temperature prediction using a dynamic neural network for absorption chiller application in Indonesia. / Nasruddin; Sholahudin; Idrus Alhamid, M.; Saito, Kiyoshi.

    In: Sustainable Energy Technologies and Assessments, Vol. 30, 01.12.2018, p. 114-120.

    Research output: Contribution to journalArticle

    @article{793cfd81c6a648748d388dfa15d2415c,
    title = "Hot water temperature prediction using a dynamic neural network for absorption chiller application in Indonesia",
    abstract = "Weather condition particularly for solar radiation and dry bulb temperature has important role in absorption chiller performance. In this paper hot water temperature prediction in generator inlet of absorption chiller has been conducted under various weather conditions. Dry bulb temperature and global horizontal radiation are selected as predictors. Three artificial neural network (ANN) types including feed forward back-propagation, cascade forward back-propagation, and Elman back propagation models have been investigated for prediction. Moreover, numbers of neuron and time delay effects were analyzed to achieve an accurate prediction. The results show that hot water temperature in generator inlet can be predicted precisely using a feed forward back propagation neural network with the configuration of a three hour delayed input on radiation, current dry bulb temperature, seven neurons, tan-sigmoid transfer function and Bayesian regularization algorithm. The prediction results perform a good agreement between predicted and experimental values. The error resulting from training and validation is 3.1 °C and 2.6 °C with a coefficient of variation at 4.4{\%} and 3.5{\%} respectively.",
    keywords = "Absorption chiller, Hot water, Neural network, Solar radiation",
    author = "Nasruddin and Sholahudin and {Idrus Alhamid}, M. and Kiyoshi Saito",
    year = "2018",
    month = "12",
    day = "1",
    doi = "10.1016/j.seta.2018.09.006",
    language = "English",
    volume = "30",
    pages = "114--120",
    journal = "Sustainable Energy Technologies and Assessments",
    issn = "2213-1388",
    publisher = "Elsevier Limited",

    }

    TY - JOUR

    T1 - Hot water temperature prediction using a dynamic neural network for absorption chiller application in Indonesia

    AU - Nasruddin,

    AU - Sholahudin,

    AU - Idrus Alhamid, M.

    AU - Saito, Kiyoshi

    PY - 2018/12/1

    Y1 - 2018/12/1

    N2 - Weather condition particularly for solar radiation and dry bulb temperature has important role in absorption chiller performance. In this paper hot water temperature prediction in generator inlet of absorption chiller has been conducted under various weather conditions. Dry bulb temperature and global horizontal radiation are selected as predictors. Three artificial neural network (ANN) types including feed forward back-propagation, cascade forward back-propagation, and Elman back propagation models have been investigated for prediction. Moreover, numbers of neuron and time delay effects were analyzed to achieve an accurate prediction. The results show that hot water temperature in generator inlet can be predicted precisely using a feed forward back propagation neural network with the configuration of a three hour delayed input on radiation, current dry bulb temperature, seven neurons, tan-sigmoid transfer function and Bayesian regularization algorithm. The prediction results perform a good agreement between predicted and experimental values. The error resulting from training and validation is 3.1 °C and 2.6 °C with a coefficient of variation at 4.4% and 3.5% respectively.

    AB - Weather condition particularly for solar radiation and dry bulb temperature has important role in absorption chiller performance. In this paper hot water temperature prediction in generator inlet of absorption chiller has been conducted under various weather conditions. Dry bulb temperature and global horizontal radiation are selected as predictors. Three artificial neural network (ANN) types including feed forward back-propagation, cascade forward back-propagation, and Elman back propagation models have been investigated for prediction. Moreover, numbers of neuron and time delay effects were analyzed to achieve an accurate prediction. The results show that hot water temperature in generator inlet can be predicted precisely using a feed forward back propagation neural network with the configuration of a three hour delayed input on radiation, current dry bulb temperature, seven neurons, tan-sigmoid transfer function and Bayesian regularization algorithm. The prediction results perform a good agreement between predicted and experimental values. The error resulting from training and validation is 3.1 °C and 2.6 °C with a coefficient of variation at 4.4% and 3.5% respectively.

    KW - Absorption chiller

    KW - Hot water

    KW - Neural network

    KW - Solar radiation

    UR - http://www.scopus.com/inward/record.url?scp=85054167682&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85054167682&partnerID=8YFLogxK

    U2 - 10.1016/j.seta.2018.09.006

    DO - 10.1016/j.seta.2018.09.006

    M3 - Article

    AN - SCOPUS:85054167682

    VL - 30

    SP - 114

    EP - 120

    JO - Sustainable Energy Technologies and Assessments

    JF - Sustainable Energy Technologies and Assessments

    SN - 2213-1388

    ER -