Neural Network approach to assess the thermal affected zone around the injection well in a groundwater heat pump system

Tipo di pubblicazione: Articolo in atti di convegno
Tipologia MIUR: Contributo in Atti di Convegno (Proceeding) > Abstract in atti di convegno
Titolo: Neural Network approach to assess the thermal affected zone around the injection well in a groundwater heat pump system
Autori: Stefano Lo Russo; Glenda Taddia; Vittorio Verda
Autori di ateneo:
Editore: EGU General Assembly
Volume: 16
Titolo del convegno: European Geosciences Union General Assembly 2014
Luogo dell'evento: Vienna
Data dell'evento: 27 April - 2 May 2014
Rilevanza dell'evento: Internazionale
Luogo di pubblicazione: Vienna
Abstract: The common use of well doublets for groundwater-sourced heating or cooling results in a thermal plume of colder or warmer re-injected groundwater known as the Thermal Affected Zone(TAZ). The plumes may be regarded either as a potential anthropogenic geothermal resource or as pollution, depending on downstream aquifer usage. A fundamental aspect in groundwater heat pump (GWHP) plant design is the correct evaluation of the thermally affected zone that develops around the injection well. Temperature anomalies are detected through numerical methods. Crucial elements in the process of thermal impact assessment are the sizes of installations, their position, the heating/cooling load of the building, and the temperature drop/increase imposed on the re-injected water flow. For multiple-well schemes, heterogeneous aquifers, or variable heating and cooling loads, numerical models that simulate groundwater and heat transport are needed. These tools should consider numerous scenarios obtained considering different heating/cooling loads, positions, and operating modes. Computational fluid dynamic (CFD) models are widely used in this field because they offer the opportunity to calculate the time evolution of the thermal plume produced by a heat pump, depending on the characteristics of the subsurface and the heat pump. Nevertheless, these models require large computational efforts, and therefore their use may be limited to a reasonable number of scenarios. Neural networks could represent an alternative to CFD for assessing the TAZ under different scenarios referring to a specific site. The use of neural networks is proposed to determine the time evolution of the groundwater temperature downstream of an installation as a function of the possible utilization profiles of the heat pump. The main advantage of neural network modeling is the possibility of evaluating a large number of scenarios in a very short time, which is very useful for the preliminary analysis of future multiple installations. The neural network is trained using the results from a CFD model (FEFLOW) applied to the installation at Politecnico di Torino (Italy) under several operating conditions
Data: 2014
Status: Pubblicato
Lingua della pubblicazione: Inglese
Parole chiave: groundwater heat pumps, feflow, neural networks, italy
Dipartimenti (originale): DENERG - Dipartimento Energia
DIATI - Dipartimento di Ingegneria dell'Ambiente, del Territorio e delle Infrastrutture
DIST - Dipartimento Interateneo di Scienze, Progetto e Politiche del Territorio
Dipartimenti: DIATI - Dipartimento di Ingegneria dell'Ambiente, del Territorio e delle Infrastrutture
DENERG - Dipartimento Energia
URL correlate:
    Area disciplinare: Area 09 - Ingegneria industriale e dell'informazione > FISICA TECNICA INDUSTRIALE
    Area 04 - Scienze della terra > GEOLOGIA APPLICATA
    Data di deposito: 15 Nov 2016 13:26
    Data ultima modifica (IRIS): 15 Nov 2016 12:26:51
    Data inserimento (PORTO): 18 Nov 2016 05:55
    Permalink: http://porto.polito.it/id/eprint/2566743
    Link resolver URL: Link resolver link

    Allegati

    [img]
    Preview
    PDF (2014_ID_2566743_EGU_Neural_Network_VIENNA.pdf) - Presentazione/Abstract
    Accesso al documento: Visibile (Ad accesso aperto)
    Licenza: Pubblico - Tutti i diritti riservati.

    Download (37Kb (38504 bytes)) | Preview

    Azioni (richiesto il login)

    Visualizza il documento (riservato amministratori) Visualizza il documento (riservato amministratori)

    Statistiche sul Download degli allegati

    Altre statistiche su questa pubblicazione...