应用GRNN网络预测高强混凝土强度

为了更好地解决混凝土强度的预测问题,提出了应用GRNN(广义回归网络)预测混凝土28d强度的方法。该网络是建立在数理统计基础之上的一种新型的神经网络,能够综合考虑影响混凝土强度的各种因素,具有良好的函数逼近效果。利用试验所得数据,建立了GRNN网络模型和BP网络模型,并对两种网络进行了比较。     

高强混凝土强度预测的支持向量机模型及应用

高强混凝土的强度受多种因素的影响,其强度的预测是一个动态性的系统工程。采用支持向量机理论,建立了高强混凝土的强度预测的支持向量机预测模型。并将该模型计算结果与实测混凝土28 d抗压强度、BP网络计算的强度、RBF径向基函数神经网络计算的强度、线性回归模型计算的强度、非线性回归模型计算的强度进行比较。研究表明:预测结果与实测结果吻合较好,较线性回归和神经网络预测精度高,为高强混凝土的强度预测提供了一条新途径。     

高强混凝土强度预测的未确知聚类预测优化模型

高强混凝土的强度受多种因素的影响,其强度的预测是一个动态性的系统工程。建立了高强混凝土强度预测的未确知聚类的预测优化模型。并将未确知聚类预测优化模型计算的强度结果与实测混凝土28 d抗压强度进行比较。研究表明,预测结果与实测结果吻合一致,说明该预测模型具有较高的预测精度,为以后高强混凝土强度预测提出一种新方法和一条新途径。     

高强混凝土强度预测人工智能方法及应用

高强混凝土的强度预测是一个动态性可变复杂问题,受各种因素的影响。采用多种智能方法,建立了高强混凝土的强度预测的遗传算法与神经网络的集成模型。并将该模型计算结果与实测混凝土28 d抗压强度,RBF径向基函数神经网络计算的强度,非线性回归模型计算的强度进行比较。研究表明:预测结果与实测结果吻合较好,较线性回归和神经网络预测精度高,为高强混凝土的强度预测提供了一条新方法。     

机器学习LGBM回归算法预测混凝土强度

混凝土强度关乎土木结构安全,影响混凝土强度的因素诸多,文章采用机器学习LGBM回归算法分析台湾重华大学信息管理系叶怡成教授的混凝土强度试验相关数据,通过数据分析验证影响混凝土强度各因素的重要性,并回归预测混凝土强度.该分析方法可用在其他室内试验或监测检测领域,为决策提供依据.     

高强混凝土钻芯强度的测定

<正> 近年来,高强混凝土已得到广泛应用,因而很有必要弄清混凝土现场养护强度、标养圆柱体强度与实地混凝土强度之间的关系,以便真实地评价任何龄期混凝土构件性能。从建筑观点来看,测定现场混凝土强度是很重要的。芯样是用于测定现场硬化     

高强混凝土的试件强度及检验

本文分析了影响高强度混凝土试件强度检测结果的主要因素,试件强度与构件混凝土强度的相关性;提出了构件混凝土强度检验中存在的问题和措施。     

高强混凝土配合比设计及其龄期强度规律研究

通过对高强混凝土的配合比及其龄期强度的试验研究,分析了高强混凝土配合比设计方法,探讨了高强混凝土龄期强度的发展规律,得到相应的拟合公式,可为高强混凝土的配合比设计及强度预测提供参考.     

基于高斯过程机器学习的岩爆等级识别方法

针对岩爆发生等级与其影响因素之间存在着复杂的非线性关系,如何根据影响因素有效识别岩爆等级是一类复杂的模式识别问题。提出了一种基于高斯过程二元分类模型的岩爆等级识别方法,该方法通过对少量学习样本的学习,就可以建立岩爆等级与其影响因素之间的复杂非线性映射关系。将方法应用于锦屏二级水电站长探洞和引水隧洞岩爆等级实例,研究结果表明,该方法具有模型参数自适应确定、容易实现且识别精度高等优点,具有良好的工程应用前景。     

混凝土强度预测的两种非线性模型比较研究

混凝土的强度的预测是一个复杂的问题,受多种因素的影响.采用两种先进的非线性算法支持向量机与小波支持向量机,建立 了混凝土强度预测的两种非线性预测方法.研究结果表明:两种方法的预测结果与实测结果吻合较好,小波支持向量机的预测精度较支持向量机精度高,在混凝土的强度预测中具有较好的适应性.     

基于非线性优化理论的混凝土材料配合比研究

建立了高强混凝土的强度预测的非线性优化模型。并将该模型计算结果与实测混凝土28 d抗压强度进行比较。改用十进制遗传算法在训练过程中搜索最优超参数,形成遗传-组合核函数高斯过程回归算法,并编制了相应的计算程序,研究结果表明:与单一核函数高斯过程回归算法和支持向量回归(SVR)算法相比,提出的遗传-组合核函数高斯过程回归算法显著提高了预测精度,预测结果与实测结果吻合较好,具有较高的预测精度,为高强混凝土的强度预测提供了一条新途径。     

Strength properties and durability aspects of high strength concrete using Korean metakaolin

Metakaolin is a cementitious material used as admixture to produce high strength concrete. In Korea, the utilization of this material remained mainly limited to fireproof walls but began recently to find applications as a replacement for silica fume in the manufacture of high performance concrete.In order to evaluate and compare the mechanical properties and durability of concrete using metakaolin, the following tests were conducted on concrete specimens using various replacements of silica fume and metakaolin; mechanical tests such as compressive, tensile and flexural strength tests, durability tests like rapid chloride permeability test, immersion test in acid solution, repeated freezing and thawing test and accelerated carbonation test.Strength tests revealed that the most appropriate strength was obtained for a substitution rate of metakaolin to binder ranging between 10% and 15%. It was observed that the resistance to chloride ion penetration reduced significantly as the proportion of silica fume and metakaolin binders increased. The filler effect resulting from the fine powder of both binders was seen to ameliorate substantially the resistance to chemical attacks in comparison with ordinary concrete. Durability tests also verified that concrete using metakaolin bore most of the mechanical and durability characteristics exhibited by concrete using silica fume. The tests implemented in this study confirmed that metakaolin constitutes a promising material as a substitute for the cost prohibitive silica fume.     

Strength of slender concrete filled high strength steel box columns

The use of thin walled steel sections coupled with concrete infill has been used on various building projects with great advantage. The currently available international standards for composite structures are limited to the design of concrete filled steel columns with compact sections. However, there is limited research work in the literature available which is concerned with slender concrete filled thin-walled steel columns. This paper presents a comprehensive experimental study of thin walled steel sections utilising high strength steel of a thin walled nature and filled with normal strength concrete. A numerical model is developed herein in order to study the behaviour of slender concrete filled high strength steel columns incorporating material and geometric non-linearities. For this analysis, the equilibrium of the member is investigated in the deformed state, using the idealised stress–strain relationships for both the steel and concrete materials, considering the elastic and plastic ranges. This paper presents both an experimental and theoretical treatment of coupled local and global buckling of concrete filled high strength steel columns sometimes termed interaction buckling. The experimental results of columns with high strength steel casings conducted herein by the authors are used for comparison. The effect of the confined concrete core is also addressed and the method shows good agreement with the experimental results of concrete filled steel columns with compact sections. The behaviour of concrete filled steel slender columns affected by elastic or inelastic local buckling is also investigated and compared with relevant experimental results. The paper then concludes with a design recommendation for the strength evaluation of slender composite columns using high strength steel plates with thin-walled steel sections, paying particular attention to existing codes of practice so as not to deviate from current design methodologies.     

A hybrid machine learning model to estimate self-compacting concrete compressive strength

This study examined the feasibility of using the grey wolf optimizer (GWO) and artificial neural network (ANN) to predict the compressive strength (CS) of self-compacting concrete (SCC). The ANN-GWO model was created using 115 samples from different sources, taking into account nine key SCC factors. The validation of the proposed model was evaluated via six indices, including correlation coefficient (R), mean squared error, mean absolute error (MAE), IA, Slope, and mean absolute percentage error. In addition, the importance of the parameters affecting the CS of SCC was investigated utilizing partial dependence plots. The results proved that the proposed ANN-GWO algorithm is a reliable predictor for SCC’s CS. Following that, an examination of the parameters impacting the CS of SCC was provided.     

采用微波加热养护法的混凝土强度早期预测

采用微波加热的方法对混凝土试件进行养护,促进混凝土的凝结硬化在短时间内即可形成一定的强度,并建立了以此方式测定的混凝土早期强度与标准养护条件下混凝土后期强度的关系,实现了在混凝土浇筑后6 h内测定混凝土强度,为混凝土强度的快速测量提供了一种有效手段。     

Evaluation and prediction of slope stability using machine learning approaches

In this paper, the machine learning (ML) model is built for slope stability evaluation and meets the high precision and rapidity requirements in slope engineering. Different ML methods for the factor of safety (FOS) prediction are studied and compared hoping to make the best use of the large variety of existing statistical and ML regression methods collected. The data set of this study includes six characteristics, namely unit weight, cohesion, internal friction angle, slope angle, slope height, and pore water pressure ratio. The whole ML model is primarily divided into data preprocessing, outlier processing, and model evaluation. In the data preprocessing, the duplicated data are first removed, then the outliers are filtered by the LocalOutlierFactor method and finally, the data are standardized. 11 ML methods are evaluated for their ability to learn the FOS based on different input parameter combinations. By analyzing the evaluation indicators R ², MAE, and MSE of these methods, SVM, GBR, and Bagging are considered to be the best regression methods. The performance and reliability of the nonlinear regression method are slightly better than that of the linear regression method. Also, the SVM-poly method is used to analyze the susceptibility of slope parameters.