摘   要：为了揭示透水混凝土力学与透水性能的协同变化规律，并实现对其性能的精准预测与协同设计，本文研究了矿物掺合料总掺量（等质量取代0、20%、25%的水泥）、粉煤灰掺量（0、5%、10%、15%、20%、25%）、硅灰掺量（0、5%、10%、15%、20%、25%）、设计孔隙率（10%、20%）对透水混凝土抗压强度、透水系数的影响，并基于SSA-BP神经网络模型对透水混凝土性能进行了预测。结果表明：掺入矿物掺合料可以有效提高透水混凝土的抗压强度；当矿物掺合料总掺量为25%、硅灰掺量为10%、粉煤灰掺量为15%、设计孔隙率为10%时，透水混凝土的抗压强度最优；当矿物掺合料总掺量相同时，随着硅灰掺量的增加，透水混凝土的透水系数降低；其他条件相同情况下，设计孔隙率增加，透水混凝土的透水系数增加；SSA-BP神经网络模型在透水混凝土性能预测方面精度较高。研究成果可为透水混凝土的研发及应用提供参考。Abstract: In order to reveal the synergistic variation patterns between the mechanical properties and water pervious properties of pervious concrete and to achieve accurate performance prediction and coordinated design, the effects of total mineral admixture content (0, 20%, and 25% replacement of cement by equal mass), fly ash content (0, 5%, 10%, 15%, 20%, 25%), silica fume content (0, 5%, 10%, 15%, 20%, 25%), and design porosity (10%, 20%) on the compressive strength and permeability coefficient of pervious concrete were investigated in this article. Additionally, the performance of pervious concrete was predicted using the SSA-BP neural network model. The results indicate that incorporating mineral admixtures can effectively enhance the compressive strength of pervious concrete. When the total mineral admixture content is 25%, the content of silica fume is 10%, the content of fly ash is 15%, and the design porosity is 10%, the compressive strength of pervious concrete is optimal. At the same total mineral admixture content, the permeability coefficient of pervious concrete decreases as the silica fume content increases. Under identical conditions, an increase in design porosity leads to a higher permeability coefficient. The SSA-BP neural network model demonstrates high accuracy in predicting the performance of pervious concrete. The research results can provide reference for the development and application of pervious concrete.

王卫,陈小华,王冠潮,等.粉煤灰与硅灰对透水混凝土性能的影响及SSA-BP神经网络预测模型研究[J].混凝土与水泥制品,2026,53(5):83-87. WANG W,CHEN X H,WANG G C,et al.Study on the influence of fly ash and silica fume on the properties of pervious concrete and the SSA-BP neural network prediction model[J].China Concrete and Cement Products,2026,53(5):83-87 (in Chinese).

摘   要：在纤维增强聚合物（Fiber reinforced polymer，FRP）与混凝土黏结体系中，黏结力是决定FRP与混凝土加固性能的关键因素，故建立准确的黏结力预测模型具有非常重要的意义。鉴于此，为对FRP-混凝土界面的黏结力进行预测，本文提出了一种基于鲸鱼优化算法（Whale optimization algorithm，WOA）的极限梯度提升（Extreme gradient boosting，XGBoost）模型（即WOA-XGBoost模型），并与XGBoost模型及10种黏结力模型进行了对比。最后，基于SHAP（Shapley additive explanations）方法进行了特征重要性分析。结果表明：所提出的WOA-XGBoost模型预测结果较好，预测精度明显优于其他模型；FRP的胶结宽度对FRP-混凝土界面的黏结力影响最大。研究结果可为FRP-混凝土界面黏结力的预测提供参考。Abstract: In the bond system between fiber reinforced polymer (FRP) and concrete, bond stress is the key factor determining the reinforcement performance of FRP and concrete. Therefore, establishing an accurate bond stress prediction model is great significance. In view of this, to predict the bond stress of FRP-concrete interfaces, this paper proposed an extreme gradient boosting (XGBoost) model based on the whale optimization algorithm (WOA), namely the WOA-XGBoost model. A comparison was conducted between the proposed model, the standalone XGBoost model, and 10 other bond stress models. Finally, feature importance analysis was carried out using the SHAP (Shapley additive explanations) method. The results show that the proposed WOA-XGBoost model has good prediction results and significantly better prediction accuracy than other models. The bond width of FRP has the greatest impact on the bond stress of the FRP concrete interface. The research results can provide theoretical references for predicting the interfacial bond stress of FRP concrete.

戴庆斌,陶莉,薛新华.基于WOA-XGBoost模型的FRP-混凝土界面黏结力预测[J].混凝土与水泥制品,2026,53(5):75-82. DAI Q B,TAO L,XUE X H.Prediction of interfacial bond stress of FRP-concrete based on WOA-XGBoost model[J].China Concrete and Cement Products,2026,53(5):75-82 (in Chinese).

摘   要：为了揭示纳米C-S-H对水泥砂浆早期性能的增强机理并优化配合比设计，本文采用响应面法，研究了水灰比、胶砂比、纳米C-S-H掺量对砂浆力学性能的影响，分析了单因素及多因素交互影响，采用SEM对砂浆进行了微观分析，并结合渴求函数对砂浆配合比进行了多目标优化。结果表明：纳米C-S-H对砂浆20 h、3 d力学性能的影响显著；经验证，所建立的模型可靠，拟合精度高；纳米C-S-H主要通过提供成核位点促进水泥早期水化，提高砂浆的早期强度，且对后期强度无明显影响；低水灰比和高水泥用量体系可增强纳米C-S-H的早强效果；优化后的最佳水灰比为0.4、胶砂比为0.5、纳米C-S-H掺量为5.4%；优化后的试验值与模型预测值相对误差的绝对值均小于5%。研究成果可为掺纳米C-S-H水泥基材料的多目标优化提供参考。Abstract: To reveal the enhancement mechanism of nano-C-S-H in improving the early performance of cement mortar and optimize the mix design, this article used response surface methodology to study the effects of water-cement ratio, cement-sand ratio, and nano-C-S-H content on the mechanical properties of mortar. The interaction effects of single and multiple factors were analyzed, and SEM was used for microscopic analysis of the mortar. Combined with the desirability function, multi-objective optimization of the mortar mix proportion was carried out. The results indicate that nano-C-S-H has a significant effect on the mechanical properties of mortar at 20 h and 3-day. The established model is verified to be reliable with high fitting accuracy. Nano-C-S-H mainly promotes early hydration of cement by providing nucleation sites, improves the early strength of mortar, and has no significant effect on the later strength. Low water-cement ratio and high cement content can enhance the early strength effect of nano-C-S-H. The optimized optimal water-cement ratio is 0.4, the cement-sand ratio is 0.5, and the nano-C-S-H content is 5.4%. The absolute relative errors between the optimized experimental values and the model predicted values are less than 5%. The research results can provide a reference for multi-objective optimization of cement-based materials doped with nano-C-S-H.

杜建峰,韩跃伟,颜功兴,等.基于响应面法的掺纳米C-S-H砂浆早期力学性能研究[J].混凝土与水泥制品,2026,53(5):66-74. DU J F,HAN Y W,YAN G X,et al.Study on early mechanical properties of mortar with nano-C-S-H based on response Surface methodology[J].China Concrete and Cement Products,2026,53(5):66-74 (in Chinese).

摘   要：为有效抑制水泥水化热引发的混凝土开裂问题，充分发挥内养护材料与纳米材料的协同作用，本文研究了高吸水性树脂（Super absorbent polymer，SAP）与纳米SiO2（Nano-SiO2，NS）复掺（SAP掺量0.08%、0.16%、0.24%，NS掺量0.5%、1.0%、1.5%）对水泥净浆水化放热量的影响，并建立了BP神经网络模型对其水化热进行预测。结果表明：单掺NS时，水泥净浆的累计水化放热量呈先快速后略微平缓再快速最后慢速的增加趋势，随着NS掺量的增加，水泥净浆的累计水化放热量增加，NS可显著促进水泥的水化反应进程，进而促进体系累计水化放热量的增加；当SAP掺量为0.24%、NS掺量为1.5%时，水泥净浆的累计水化放热量最多；BP神经网络模型的预测值与实测值接近，预测精度较高。研究结果可为混凝土的抗裂相关研究以及工程实践提供理论支撑。Abstract: In order to effectively suppress the cracking problem of concrete caused by cement hydration heat and fully utilize the synergistic effect of internal curing materials and nanomaterials, the effect of the combination of super absorbent polymer (SAP) and nano-SiO2 (NS) (with SAP contents of 0.08%, 0.16%, and 0.24%, and NS contents of 0.5%, 1.0%, and 1.5%) on the hydration heat release of cement paste was studied in this article, and a BP neural network prediction model was established to predict its hydration heat. The results show that when NS is added alone, the cumulative hydration heat release of cement paste increases rapidly at first, slows down slightly, then increases rapidly again, and finally increases slowly. With the increase of NS content, the cumulative hydration heat release of cement paste increases, and NS can significantly promote the process of cement hydration reaction, thereby promoting the increase of cumulative hydration heat release of the system. When the SAP content is 0.24% and the NS content is 1.5%, the cumulative hydration heat release of cement paste is the highest. The BP neural network model demonstrates close agreement between predicted and measured values, with high prediction accuracy. The research results can provide theoretical support for the study of crack resistance in concrete and engineering practice.

徐帅,王豪杰,王琦,等.纳米SiO2与SAP复掺对水泥水化热的影响及BP神经网络预测研究[J].混凝土与水泥制品,2026(5):61-65. XU S,WANG H J,WANG Q,et al.Study on the effect of nano-SiO2 and SAP composite on cement hydration heat and BP neural network prediction[J].China Concrete and Cement Products,2026(5):61-65 (in Chinese).

摘   要：公路桥梁隧道混凝土结构常因地下水、雨水等因素处于不同含水率状态，易引发结构损伤并削弱其承载能力，威胁工程运营安全。为了明确不同含水率下混凝土的力学特性，建立适配的单轴压缩本构模型，本文以饱和度表征混凝土含水状态，设置了0、0.3、0.5、0.7、1.0 共5种工况，开展了单轴压缩试验，分析了饱和度对混凝土应力-应变曲线、力学参数及破坏形态的影响，拟合了各力学参数与饱和度的关系，构建了分段式本构模型并进行了验证。结果表明：不同饱和度混凝土峰前应力-应变曲线均含压密、弹性、裂纹扩展三个阶段，饱和度升高使曲线趋缓、峰值强度降低、塑性增强，破坏模式由剪切为主转为张拉为主；各力学参数与饱和度拟合相关性良好；所建模型（以弹性起始点为分界）计算值与实测值一致性良好，可有效描述不同饱和度混凝土单轴压缩力学行为。研究成果可为公路桥梁隧道工程中不同含水率混凝土承重构件的施工建设、结构设计及运营维护提供参考，也可为后续不同含水率混凝土压缩本构模型的建立提供理论依据。Abstract: Concrete structures of highway bridges and tunnels are often subjected to different moisture content conditions due to groundwater, rainwater and other factors, which can easily cause structural damage, weaken their  load-bearing capacity and threaten the operational safety of engineering projects. To clarify the mechanical properties of concrete under different moisture contents and establish a suitable uniaxial compression constitutive model, this study employed the saturation degree to characterize the moisture state of concrete. Five saturation  degrees (0, 0.3, 0.5, 0.7, and 1.0) were designed, and a series of uniaxial compression tests were conducted. The effects of saturation degree on the stress-strain curves, mechanical parameters and failure modes of concrete were analyzed. The relationships between the mechanical parameters and the saturation degree were fitted, and a piecewise constitutive model was established and verified. The results show that the pre-peak stress-strain curves of concrete with different saturation degrees all exhibit three stages, namely compaction, elasticity and crack propagation. With the increase of saturation degree, the curve becomes flatter, the peak strength decreases, and the plasticity is enhanced, while the failure mode transforms from shear-dominated to tension-dominated. The mechanical parameters show good fitting correlation with saturation degree. The calculated values of the established model (taking the initial elastic point as the boundary) agree well with the measured ones, indicating that it can effectively describe the uniaxial compressive mechanical behavior of concrete with different saturation degrees. The research findings can provide references for the construction, structural design, operation and maintenance of load-bearing concrete Abstract: Concrete structures of highway bridges and tunnels are often subjected to different moisture content conditions due to groundwater, rainwater and other factors, which can easily cause structural damage, weaken their  load-bearing capacity and threaten the operational safety of engineering projects. To clarify the mechanical properties of concrete under different moisture contents and establish a suitable uniaxial compression constitutive model, this study employed the saturation degree to characterize the moisture state of concrete. Five saturation  degrees (0, 0.3, 0.5, 0.7, and 1.0) were designed, and a series of uniaxial compression tests were conducted. The effects of saturation degree on the stress-strain curves, mechanical parameters and failure modes of concrete were analyzed. The relationships between the mechanical parameters and the saturation degree were fitted, and a piecewise constitutive model was established and verified. The results show that the pre-peak stress-strain curves of concrete with different saturation degrees all exhibit three stages, namely compaction, elasticity and crack propagation. With the increase of saturation degree, the curve becomes flatter, the peak strength decreases, and the plasticity is enhanced, while the failure mode transforms from shear-dominated to tension-dominated. The mechanical parameters show good fitting correlation with saturation degree. The calculated values of the established model (taking the initial elastic point as the boundary) agree well with the measured ones, indicating that it can effectively describe the uniaxial compressive mechanical behavior of concrete with different saturation degrees. The research findings can provide references for the construction, structural design, operation and maintenance of load-bearing concrete

陈兆志,郭春志.单轴压缩下不同含水率混凝土力学特性及本构模型研究[J].混凝土与水泥制品,2026,53(5):54-60. CHEN Z Z,GUO C Z.Study on the mechanical properties and constitutive model of concrete with varying moisture contents under uniaxial compression[J].China Concrete and Cement Products,2026,53(5):54-60 (in Chinese).

摘   要：为解决机制砂生产中因原料云母含量波动大、工艺参数调控依赖经验造成其云母含量超标问题，本文提出了一种基于双层贝叶斯优化支持向量机回归（BO-SVR-BO）的云母去除工艺参数优化方法。在第一层优化中，采用贝叶斯优化（Bayesian optimization，BO）对支持向量机回归（Support vector regression，SVR）的超参数进行全局寻优，构建针对云母含量、细度模数和产品率的高精度预测模型，并与反向传播（Backpropagationk，BP）神经网络、长短期记忆网络（Long short-term memory，LSTM）、门控循环单元（Gated recurrent unit，GRU）和多层感知机(Multilayer perceptron，MLP）模型进行对比；在第二层优化中，以训练好的BO-SVR为代理模型，结合BO实现风选风速与磁场强度的多目标全局优化。结果表明：在同一测试集下，BO-SVR模型在云母含量、细度模数和产品率的预测中表现出更高的精度与稳定性；在工艺参数优化方面，BO-SVR-BO能够在确保选别后机制砂云母含量≤2%、细度模数符合相关标准要求的前提下，显著提升产品率。研究成果可为机制砂除云母工艺的智能调控和质量优化提供技术参考。Abstract: To address the problems of excessive mica content in finished manufactured sand caused by large fluctuations in the content of mica in raw material and experience-dependent regulation of process parameters during manufactured sand production, this paper proposes a process parameter optimization method for mica removal based on double-layer Bayesian optimization-support vector regression (BO-SVR-BO). In the first layer optimization, Bayesian optimization (BO) is used to globally optimize the hyperparameters of support vector regression (SVR) and construct a high-precision prediction model for mica content, fineness modulus, and product yield. The prediction performance is compared with that of backpropagation (BP) neural network, long short-term memory (LSTM), gated recurrent unit (GRU), and multilayer perceptron (MLP) model. In the second layer optimization, the trained BO-SVR is used as the surrogate model, and is combined with BO to achieve multi-objective global optimization of classification wind speed and magnetic field strength. The results show that on the same test set, the BO-SVR model exhibits higher prediction accuracy and stability in predicting mica content, fineness modulus, and product yield. In terms of process parameter optimization, the BO-SVR-BO method can significantly improve product yield while ensuring that the mica content of the manufactured sand after mica removal is ≤2% and that the fineness modulus meets the requirements of relevant standards. The findings can provide a technical reference for the intelligent regulation and quality optimization of the mica removal process in manufactured sand production.

胡嘉靖,张明,杨大兵.基于BO-SVR-BO的机制砂除云母工艺参数优化方法[J].混凝土与水泥制品,2026,53(5):47-53. HU J J,ZHANG M,YANG D B.Research on process parameter optimization of mica removal from manufactured sand based on BO-SVR-BO[J].China Concrete and Cement Products,2026,53(5):47-53 (in Chinese).