de-Prado-Gil Jesús, Palencia Covadonga, Jagadesh P, Martínez-García Rebeca
Department of Applied Physics, Campus de Vegazana s/n, University of León, 24071 León, Spain.
Department of Civil Engineering, Coimbatore Institute of Technology, Coimbatore 638056, Tamil Nadu, India.
Materials (Basel). 2022 Jul 28;15(15):5232. doi: 10.3390/ma15155232.
A considerable amount of discarded building materials are produced each year worldwide, resulting in ecosystem degradation. Self-compacting concrete (SCC) has 60-70% coarse and fine particles in its composition, so replacing this material with another waste material, such as recycled aggregate (RA), reduces the cost of SCC. This study compares novel Artificial Neural Network algorithm techniques-Levenberg-Marquardt (LM), Bayesian regularization (BR), and Scaled Conjugate Gradient Backpropagation (SCGB)-to estimate the 28-day compressive strength (f'c) of SCC with RA. A total of 515 samples were collected from various published papers, randomly splitting into training, validation, and testing with percentages of 70, 10 and 20. Two statistical indicators, correlation coefficient (R) and mean squared error (MSE), were used to assess the models; the greater the R and lower the MSE, the more accurate the algorithm. The findings demonstrate the higher accuracy of the three models. The best result is achieved by BR (R = 0.91 and MSE = 43.755), while the accuracy of LM is nearly the same (R = 0.90 and MSE = 48.14). LM processes the network in a much shorter time than BR. As a result, LM and BR are the best models in forecasting the 28 days f'c of SCC having RA. The sensitivity analysis showed that cement (28.39%) and water (23.47%) are the most critical variables for predicting the 28-day compressive strength of SCC with RA, while coarse aggregate contributes the least (9.23%).
全球每年都会产生大量废弃建筑材料，导致生态系统退化。自密实混凝土（SCC）的成分中60%-70%是粗、细颗粒，因此用另一种废料（如再生骨料（RA））替代这种材料可降低SCC的成本。本研究比较了新型人工神经网络算法技术——列文伯格-马夸尔特算法（LM）、贝叶斯正则化算法（BR）和缩放共轭梯度反向传播算法（SCGB），以估算含RA的SCC的28天抗压强度（f'c）。从各种已发表的论文中总共收集了515个样本，随机分为训练集、验证集和测试集，比例分别为70%、10%和20%。使用两个统计指标，即相关系数（R）和均方误差（MSE）来评估模型；R越大且MSE越小，算法越准确。研究结果表明这三种模型具有更高的准确性。BR取得了最佳结果（R = 0.91，MSE = 43.755），而LM的准确性几乎相同（R = 0.90，MSE = 48.14）。LM处理网络的时间比BR短得多。因此，LM和BR是预测含RA的SCC的28天f'c的最佳模型。敏感性分析表明，水泥（28.39%）和水（23.47%）是预测含RA的SCC的28天抗压强度的最关键变量，而粗骨料的贡献最小（9.23%）。
