Abstract In this study, we investigated the mechanical properties and chloride ion permeation resistance of geopolymer mortars based on fly ash modified with nano-SiO2 (NS) and polyvinyl alcohol (PVA) fiber and metakaolin (MK) at dose levels of 0–1.2% for PVA fiber and 0–2.5% for NS. The Levenberg–Marquardt (L–M) back propagation (BP) neural network, as well as the radial-based function (RBF) neural network, was used to predict the compressive strength and chloride ion permeation resistance of the geopolymer mortar with different admixtures of nanoparticles and PVA fiber, wherein the electric flux value was used as the index for chloride ion permeation performance. The RBF–BP composite neural network was constructed to study the compressive strength and chloride ion permeation resistance of nanoparticle-doped and PVA fiber ground geopolymer mortars. According to the experimental results of the RBF–BP composite neural network model, the mean square error (MSE) was observed to be 0.00071943, root mean square error (RMSE) was 0.026822, and mean absolute error (MAE) was 0.026822, thereby showing higher prediction accuracy, faster convergence, and better fitting effect compared with the single BP neural network and RBF neural network models. In this study, we combined the RBF–BP composite artificial neural network, providing a new method for the future assessment of the compressive strength and chloride ion penetration resistance of geopolymer mortar merging PVA fibers and NS in experiments and engineering studies.

中文翻译：

---

基于 RBF-BP 复合神经网络的 PVA 纤维与纳米 SiO2 融合的地质聚合物砂浆抗压强度和抗氯离子渗透评估

摘要 在这项研究中，我们研究了基于粉煤灰的地质聚合物砂浆的力学性能和抗氯离子渗透性，粉煤灰在 0-1.2% 的剂量水平下用纳米 SiO2 (NS) 和聚乙烯醇 (PVA) 纤维和偏高岭土 (MK) 改性。 PVA 纤维和 NS 的 0-2.5%。Levenberg-Marquardt (L-M) 反向传播 (BP) 神经网络以及基于径向的函数 (RBF) 神经网络，用于预测具有不同外加剂的地质聚合物砂浆的抗压强度和氯离子渗透阻力纳米粒子和PVA纤维的研究，其中以电通量值作为氯离子渗透性能的指标。构建RBF-BP复合神经网络，研究纳米颗粒掺杂和PVA纤维地面地质聚合物砂浆的抗压强度和抗氯离子渗透性。根据RBF-BP复合神经网络模型的实验结果，观察到均方误差（MSE）为0.00071943，均方根误差（RMSE）为0.026822，平均绝对误差（MAE）为0.026822，从而表明与单一的BP神经网络和RBF神经网络模型相比，预测精度更高、收敛速度更快、拟合效果更好。在这项研究中，我们结合了 RBF-BP 复合人工神经网络，