کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
4913265 1428763 2017 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Experimental observations and SVM-based prediction of properties of polypropylene fibres reinforced self-compacting composites incorporating nano-CuO
موضوعات مرتبط
مهندسی و علوم پایه سایر رشته های مهندسی مهندسی عمران و سازه
پیش نمایش صفحه اول مقاله
Experimental observations and SVM-based prediction of properties of polypropylene fibres reinforced self-compacting composites incorporating nano-CuO
چکیده انگلیسی
This paper presents an experimental study to examine the hardened and fresh properties of self-compacting concrete (SCC) containing nano-CuO (NC) and polypropylene (PP) fibres. Slump-flow, T50 and V-funnel tests were carried out on fresh SCCs. The hardened properties of SCCs included compressive strength, flexural strength, tensile strength, water absorption and electrical resistivity were studied. Moreover, Scanning Electron Microscope (SEM) was employed in order to investigate the microstructure of the cement matrix. Results revealed that NC had a significant influence on compressive strength, water absorption and electrical resistivity of SCCs. The replacement of cement with a combination of 3% NC and 0.3% PP fibre gave better mechanical and durability performances than the other samples. However, the compressive strength reduced slightly when PP fibres were added to the concrete. SEM images illustrated that NC refined the pores of cement matrix and thus resulting in low permeability. Also, it is evident from the SEM images that PP fibres would improve the properties of SCCs by bridging across the cracks. Apparently, the inclusion of 3% NC and 0.3% PP can be considered as an appropriate combination regarding the fresh and hardened properties of concrete. Furthermore, three support vector machine (SVM) approaches were used to predict the compressive strength based on the mix proportions. The results demonstrated that the Wavelet Weighted Least Square SVM (WWLSSVM) and Least Square SVM (LSSVM) models gave more accurate prediction than standard Support Vector Machine (SVM).
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Construction and Building Materials - Volume 143, 15 July 2017, Pages 589-598
نویسندگان
, , , , , ,