Liu Jing, Mohammadi Masoud, Zhan Yubao, Zheng Pengqiang, Rashidi Maria, Mehrabi Peyman
Collage of Resources, Shandong University of Science and Technology, Taian 271019, China.
Centre for Infrastructure Engineering, Western Sydney University, Penrith, NSW 2751, Australia.
Materials (Basel). 2021 Nov 11;14(22):6792. doi: 10.3390/ma14226792.
Self-consolidating concrete (SCC) is a well-known type of concrete, which has been employed in different structural applications due to providing desirable properties. Different studies have been performed to obtain a sustainable mix design and enhance the fresh properties of SCC. In this study, an adaptive neuro-fuzzy inference system (ANFIS) algorithm is developed to predict the superplasticizer (SP) demand and select the most significant parameter of the fresh properties of optimum mix design. For this purpose, a comprehensive database consisting of verified test results of SCC incorporating cement replacement powders including pumice, slag, and fly ash (FA) has been employed. In this regard, at first, fresh properties tests including the J-ring, V-funnel, U-box, and different time interval slump values were considered to collect the datasets. At the second stage, five models of ANFIS were adjusted and the most precise method for predicting the SP demand was identified. The correlation coefficient (R), Pearson's correlation coefficient (r), Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE), mean absolute error (MAE), and Wilmot's index of agreement (WI) were used as the measures of precision. Later, the most effective parameters on the prediction of SP demand were evaluated by the developed ANFIS. Based on the analytical results, the employed algorithm was successfully able to predict the SP demand of SCC with high accuracy. Finally, it was deduced that the V-funnel test is the most reliable method for estimating the SP demand value and a significant parameter for SCC mix design as it led to the lowest training root mean square error (RMSE) compared to other non-destructive testing methods.
自密实混凝土（SCC）是一种知名的混凝土类型，因其具有理想性能而被应用于不同的结构工程中。人们开展了不同的研究以获得可持续的配合比设计并改善SCC的新拌性能。在本研究中，开发了一种自适应神经模糊推理系统（ANFIS）算法，用于预测减水剂（SP）用量并选择最优配合比设计新拌性能的最显著参数。为此，采用了一个综合数据库，该数据库包含了掺入包括浮石、矿渣和粉煤灰（FA）在内的水泥替代粉末的SCC的经核实的试验结果。在这方面，首先，考虑进行包括J环、V型漏斗、U型箱以及不同时间间隔坍落度值在内的新拌性能试验来收集数据集。在第二阶段，调整了五个ANFIS模型，并确定了预测SP用量的最精确方法。相关系数（R）、皮尔逊相关系数（r）、纳什-萨特克利夫效率（NSE）、均方根误差（RMSE）、平均绝对误差（MAE）和威尔莫特一致性指数（WI）被用作精度度量指标。随后，通过所开发的ANFIS评估了对SP用量预测最有效的参数。基于分析结果，所采用的算法成功地能够高精度预测SCC的SP用量。最后得出结论，V型漏斗试验是估计SP用量值的最可靠方法，也是SCC配合比设计的一个重要参数，因为与其他无损检测方法相比，它导致的训练均方根误差（RMSE）最低。
