在这项研究中，研究了不同百分比的飞灰 (FA)、硅灰 (SF) 和飞灰 + 硅灰对硬化水泥浆 (CS–H ve CH) 和混凝土的力学和微观结构性能的影响。波特兰水泥被粉煤灰、硅粉和粉煤灰+硅粉替代，水泥的量分别为 5%、10%、15% 和 20%（以重量计）。采用X射线衍射(XRD)和扫描电子显微镜(SEM)技术研究了样品的力学性能、抗压强度和微观结构。结果表明，粉煤灰在 7 天后对混凝土的抗压强度产生不利影响，而在 28 天和 90 天龄时提高了抗压强度。在使用硅灰的混凝土中，与所有年龄的对照样品相比，获得了更高的抗压强度。在含有硅粉的样品中，使用 15% 的硅粉，在含有粉煤灰的样品中使用 10% 的粉煤灰，以及在硅粉和粉煤灰一起使用 15% 的情况下，获得了最高的抗压强度。在 XRD 分析中，由于水化作用形成的 CH 的速率随着使用的飞灰、硅灰和飞灰 + 硅灰的比例而降低。SEM 分析表明，飞灰和硅灰的使用减少了空隙并增加了 CS-H 比。研究发现，由于硅粉和飞灰比例的增加，CS-H 比的增加与 CH 浓度之间的反比关系之间存在线性关系。这是由于 Ca(OH) 10% 的粉煤灰在含有粉煤灰的样品中，15% 在硅粉和粉煤灰一起的情况下。在 XRD 分析中，由于水化作用形成的 CH 的速率随着使用的飞灰、硅灰和飞灰 + 硅灰的比例而降低。SEM 分析表明，飞灰和硅灰的使用减少了空隙并增加了 CS-H 比。研究发现，由于硅粉和飞灰比例的增加，CS-H 比的增加与 CH 浓度之间的反比关系之间存在线性关系。这是由于 Ca(OH) 10% 的粉煤灰在含有粉煤灰的样品中，15% 在硅粉和粉煤灰一起的情况下。在 XRD 分析中，由于水化作用形成的 CH 的速率随着使用的飞灰、硅灰和飞灰 + 硅灰的比例而降低。SEM 分析表明，飞灰和硅灰的使用减少了空隙并增加了 CS-H 比。研究发现，由于硅粉和飞灰比例的增加，CS-H 比的增加与 CH 浓度之间的反比关系之间存在线性关系。这是由于 Ca(OH) 使用硅粉和粉煤灰+硅粉。SEM 分析表明，飞灰和硅灰的使用减少了空隙并增加了 CS-H 比。研究发现，由于硅粉和飞灰比例的增加，CS-H 比的增加与 CH 浓度之间的反比关系之间存在线性关系。这是由于 Ca(OH) 使用硅粉和粉煤灰+硅粉。SEM 分析表明，飞灰和硅灰的使用减少了空隙并增加了 CS-H 比。研究发现，由于硅粉和飞灰比例的增加，CS-H 比的增加与 CH 浓度之间的反比关系之间存在线性关系。这是由于 Ca(OH)2由于粉煤灰和硅灰和氢氧化钙 (Ca(OH) 2 ) 之间的反应并填充间隙。生成的硅酸盐将水泥水合物与生成的 C 3 S 和 C 2的飞灰结合S 形成 CS-H。此外，在这项研究中，开发了一个模型来估计混凝土在从 SEM 和 XRD 分析获得的数据方向上的抗压强度。从人工神经网络 (ANN) 上获得的模拟 SEM 和 XRD 数据获得的 CH 和 CS-H 密度、硅灰比、飞灰和湿参数作为输入并获得抗压强度。将模型得到的结果与实验得到的结果进行比较，得到了96.76%的正确结果。用这种方法可以看出，混凝土的压力密度可以从一个小的混凝土样品的 SEM 和 XRD 分析的结果中计算出来，而不会破坏现有的结构。根据 SEM 和 XRD 结果，
"点击查看英文标题和摘要"
ANN Modeling of Concrete Containing Silica Fume and Flay Ash with SEM and XRD
In this study, the effects of different percentages of fly ash (FA), silica fume (SF) and fly ash + silica fume had on the mechanical and microstructural properties of hardened cement paste (C-S–H ve CH) and concrete were investigated. Portland cement was replaced with fly ash, silica fume and fly ash + silica fume in quantities of 5%, 10%, 15%, and 20% (in terms of weight) of cement. The mechanical properties, compressive strength and microstructures of the samples were investigated by using X-ray diffraction (XRD) and scanning electron microscopy (SEM) techniques. According to the results, fly ash adversely affects the compressive strength of concrete in 7 days, while it increased compressive strength in 28 and 90 days of age. In concrete using silica fume, a higher compressive strength was obtained compared the control sample at all ages. In samples containing silica fume, the highest compressive strength was obtained by using 15% silica fume, 10% fly ash in the samples containing fly ash, and 15% in the case of silica fume and fly ash together. In the XRD analysis, the rate of CH formed as a result of hydration decreased with age and the ratio of fly ash, silica fume and fly ash + silica fume used. SEM analysis showed that the use of fly ash and silica fume decreased the voids and increased the C-S–H ratio. It was found that there was a linear relationship between the increase in C-S–H ratio due to the increase in silica fume and fly ash ratios used, and an inversely proportional relation between the CH concentrations. This is caused by the reduction of the amount of Ca(OH)2 due to the reaction between fly ash and silica fume and calcium hydroxide (Ca(OH)2) and filling the gaps. The resulting portlandites combine the cement hydrate with the resulting fly ash of the resulting C3S and C2S to form C-S–H. Additionally, in the study, a model was developed to estimate the compressive strength of concrete in the direction of the data obtained from SEM and XRD analyses. The CH and C-S–H densities, silica fume ratio, fly ash and wet parameters obtained from modeled SEM and XRD data obtained on artificial neural networks (ANN) were taken as inputs and compressive strength were obtained. The results obtained from the model were compared with the results obtained from the experiments and 96.76% correct results were obtained. With this method, it is seen that the concrete pressure density can be calculated from the results obtained by SEM and XRD analysis of a small concrete sample without destroying the existing structure. According to the SEM and XRD results, a method has been proposed for estimating the compressive strength of concrete by non-destructive methods with the model developed using artificial neural networks.
京公网安备 11010802027423号