摘要
随着“无废城市”建设的不断推进,装修垃圾治理需求与日俱增,但目前办公楼装修垃圾发生量预测与资源化研究尚不足。利用BP神经网络对全国31个省市(除港澳台外)办公楼装修垃圾发生源特征及趋势进行研究。经检验,训练后的BP神经网络拟合优度R=0.93693>0.9,模型精度为优秀。根据BP模型预测结果,到2030年全国办公楼装修垃圾发生总量将达到785.6万t,相较2020年增长率为36.8%。利用ArcGIS手段对我国办公楼装修垃圾排放进行时空分布表征,发现全国发生量高区域以东南沿海和川渝地区为主,中南地区为辅,其余地区发生量整体偏低。由于废弃物中废纸面石膏板占比最大,高达58.9%,因此对其进行了资源化处理处置研究。通过与脱硫石膏对比实验证明,其力学性能表现较好,在高掺量情况下性能优于脱硫石膏。通过不同工艺对比,确定了废纸面石膏板作为缓凝剂时的最佳掺入量以及水泥样品最佳力学性能。当掺入5%废石膏板时,水泥性能最优。原材料混磨制成的水泥样品最佳抗折强度为8.9 MPa,抗压强度为46.5 MPa。
With the continuous promotion of the construction of Zero-Waste City,the demand for decoration waste treatment is increasing day by day.However,there are still shortcomings in the prediction of the amount of decoration waste in relevant office buildings and the research on resource utilization.In this study,the BP neural network was used to study the characteristics and trends of the source of office building decoration waste in 31 provinces and cities(except for Hong Kong,Macao and Taiwan).After the test,the goodness-of-fit of the trained BP neural network was R=0.93693>0.9,and the model accuracy was excellent.According to the prediction results of the BP model,the total amount of office building renovation waste occurring in China will reach 7.856 million tons by 2030,with a growth rate of 36.8%compared with 2020.Using ArcGIS means to characterize the spatial and temporal distribution of office renovation waste emissions in China,the study shows that the national occurrence is mainly in the southeast coastal and Sichuan-Chongqing regions,supplemented by the central and southern regions,and the overall low occurrence in the rest of the regions.Since the waste paper-faced gypsum board accounts for the largest proportion of the waste,up to 58.9%,a study on its resource treatment and disposal was conducted.Through comparison experiments with desulfurization gypsum,it was proved that its mechanical properties was better than that of desulfurization gypsum under high dosing.The optimal amount of gypsum as a retarder and the best mechanical properties of cement samples were determined by comparing different processes.The cement performance was optimal when a 5%waste gypsum board was added.The best flexural strength of the cement samples made by mixing raw materials was 8.9 MPa and the compressive strength was 46.5 MPa.
作者
刘国涛
任福民
胡舒馨
贾谨铭
LIU Guotao;REN Fumin;HU Shuxin;JIA Jinming(School of Environment,Beijing Jiaotong University,Beijing 100044,China;Beijing Zhongzi Huake Traffic Construction Technology Co.,Ltd.,Beijing 100039,China)
出处
《环境工程》
CAS
CSCD
2024年第6期119-126,共8页
Environmental Engineering
基金
国家重点研发计划(2018YFC0706000)。
关键词
办公楼装修垃圾
发生量预测
BP神经网络
时空分布特征
水泥缓凝剂
office building decoration waste
occurrence prediction
BP neural network
spatial and temporal distribution characteristics
cement retarder
