基于SVR的高层办公建筑全生命周期碳排放预测模型——以天津地区为例

Prediction Model for Carbon Emissions of Life Cycle Assessment of High-rise Office Buildings Based on SVR:Take Tianjin as an Example

高层办公建筑体量大、能耗高、碳排放基量大,已成为公共建筑节能减排的重点。根据建筑全生命周期碳排放评价体系,将高层办公建筑全生命周期划分为4个阶段:建材生产、建筑施工、运行维护和拆解回收;梳理了各阶段的碳排放因子,将"年单位建筑面积碳排放量kgCO_(2)/(m^(2)·a)"作为碳排放计量参数,以消除使用年限、建筑规模不同的影响,便于开展计算结果的平行比较;进一步创建了高层办公建筑全生命周期碳排放计算模型。基于模型计算了天津市29栋高层办公建筑全生命周期的碳排放量,结果在48.3~66.1 kgCO_(2)/(m^(2)·a)之间,其中"运行维护"阶段碳排放占比最大,达到89.3%,其次是"建材生产"阶段,占比10.4%,"建筑施工"阶段碳排放与"拆解回收"阶段减碳量可相互抵消而忽略不计。运用SVR(支持向量回归机)模型,对碳排放计算结果与影响变量进行拟合分析,构建出高层办公建筑全生命周期碳排放预测模型,预测模型得出的训练样本(22栋)、测试样本(7栋)碳排放值与实际值相关系数分别为0.85和0.95,模型预测性能良好。该预测模型通过输入4个影响变量数据,即可得碳排放量预测值,能够极大地降低运算时间和工作量,实现了设计师在高层办公建筑设计初期阶段方便快捷的预测碳排放。

High-rise office buildings become the focus of energy conservation due to large volume,high energy consumption and large carbon emissions.Based on the theory of life cycle assessment of the building,the life cycle was divided into four stages:production,construction,operation and maintenance,demolition and processing.Carbon emission factors were sorted out."Annual carbon emissions per unit area,kgCO_(2)/(m^(2)·a)"was used as a measurement parameter to eliminate the effects of different service years and building scales and to facilitate the parallel comparison of calculation results.Furthermore,the calculation model was summarized.Based on model,carbon emissions of 29 high-rise office buildings in Tianjin were calculated and the results were between 48.3~66.1 kgCO_(2)/(m^(2)·a).Carbon emissions accounted for 89.3%and 10.4%in operation and maintenance stage and production stage respectively.Carbon emissions in construction stage and carbon reductions during demolition and processing stage can be offset.Using the SVR(Support Vector Regression)model,the calculation results and the impact variables were analyzed and constructed a prediction model for high-rise office buildings.The correlation coefficients of predicted values and actual values of the training samples(22 buildings)and the test samples(7 buildings)were 0.85 and 0.95 respectively.The model has good prediction performance.Prediction model can obtain the predicted value by inputting the data of 4 impact variables,which can greatly reduce the calculation time and workload.Designers can easily and quickly predict the carbon emissions of high-rise office buildings during the design stage.