Scribd Logo
Upload

Welcome to Scribd!

  • 1 views

    A Machine Learning-Based Prediction Model of LCCO2 For Building Envelope Renovation in Taiwan

    Uploaded by

    yu.kulthana

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    A Machine Learning-Based Prediction Model of LCCO2 For Building Envelope Renovation in Taiwan

    Uploaded by

    yu.kulthana
    1 views3 pages

    Original Title

    A Machine Learning-Based Prediction Model of LCCO2 for Building Envelope Renovation in Taiwan

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    1 views3 pages

    A Machine Learning-Based Prediction Model of LCCO2 For Building Envelope Renovation in Taiwan

    Uploaded by

    yu.kulthana

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 3

    A Machine Learning-Based Prediction Model of LCCO2 for Building Envelope Renovation

    in Taiwan
    2021 NCKU
    Objective: create the model for LCCO2 and annual energy consumption prediction
    Data: Building envelope renovation project 744 cases in Tainan
    - Original design: Typical row house in Taiwan
    - Construction methods: 11 of roofs, 6 of exterior walls, 15 of glass materials
    o U-value (sum of heat transmitted from warm space to cold space, lower is better
    insulated)
    o Solar heat gain coefficient of glass, SHGC: set as 0 – 1 (lower is better blocking
    heat)
    o Visible transmittance of glass, VT (sensitivity of human eyes to light, higher VT
    transmits more visible light)
    o Under the premise that the original design of the building remains unchanged, we replaced the
    building materials, with the exception of the main structure, according to the common structure of
    Taiwan’s existing row houses as mentioned in Section 2.1. Among them, the short side of the
    exterior wall is the street-facing facade, and the simulation was set to be affected by airflow and
    sunlight. Meanwhile, the wall connected to the neighboring house (the long side of the exterior
    wall) was set as an insulating wall during simulation. Indoor floors, doors, and walls were not
    affected by airflow and sunlight.

    - Locations: Taipei, Taichung, Kaohsiung


    o Different locationsclimate zone temperature, humidity, wind speed
    o All data from Typical Meteorological Years (TMY3) #data adopted by Taiwan
    using Sandia Method from US
    - Orientations: North, South, East, West (each side of houses will face to every direction)
    - Indoor temperature: less or higher than outdoor for < 26 degree Celsius
    - Ventilation methods: close or open the window, turn on the air conditioners
    o Coefficient of Performance (COP) was set at 4.5 (higher COP, higher efficiency,
    lower energy consumption)
    o Discharge coefficient for the opening factor: 0.6 for opening window, 0.0001 for
    closing window
    Calculation tools:
    1. EnergyPlus (energy consumption)
    2. SimaPro
    3. Local database: LCBA
    Calculation:
    1. Data collection
    a. waste disposal >> LCCO2
    b. materials >> LCCO2
    c. construction >> LCCO2
    d. air conditioning
    i. The calculation of the carbon emissions of air conditioning during the use phase converts
    the results of energy consumption according to the carbon emission coefficient
    announced by the Ministry of Economic Affairs [39].

    ii. The annual energy consumption is given by the simulation result of air conditioning
    energy consumption with EnergyPlus and is then converted into the carbon emissions of
    the use phase over 20 years (life cycle of a renovation building project). The simulation
    settings of EnergyPlus are explained in Section 2.2.2.

    iii. Life cycle for renovation building: 20 years


    2. Spearman’s rank correlation
    a. Annual energy consumption & LCCO2: high
    b. Annual energy consumption & location
    i. Temperature: high
    ii. Humidity and wind: some
    3. Check the accuracy
    a. Two model; second model deleted U-value of roof and exterior wall as they
    have low correlation #main heat go through the window
    i. But second model did not work well
    ii. Tuning the hyperparameters
    Model training and testing:

    You might also like