边坡随机场数字图像特征CNN深度学习及可靠度分析

考虑土体强度空间变异性,提出了数字图像化随机场特征深度学习模型并进行边坡稳定可靠度分析。通过Karhunen-Loeve展开法离散边坡土体随机场并将离散结果转化为数字图像,建立起随机场图像与边坡功能函数值之间隐式关系的卷积神经网络（CNN）代理模型,进而计算随机场数字图像表征后边坡的失效概率。在建立CNN代理模型时,采用拉丁超立方抽样、贝叶斯优化和五折交叉验证以提高精度。最后以单层不排水饱和黏土边坡和双层黏性土边坡为例说明了该方法的有效性。结果表明：在随机场高维表征图像化和边坡小概率失稳情况下,所提CNN深度学习模型能够比较精确地逼近真实边坡稳定性计算结果,进而显著提高考虑随机场模拟的边坡可靠度分析计算效率。     

Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine

Plastic concrete is an engineering material, which is commonly used for construction of cut-off walls to prevent water seepage under the dam. This paper aims to explore two machine learning algorithms including artificial neural network (ANN) and support vector machine (SVM) to predict the compressive strength of bentonite/sepiolite plastic concretes. For this purpose, two unique sets of 72 data for compressive strength of bentonite and sepiolite plastic concrete samples (totally 144 data) were prepared by conducting an experimental study. The results confirm the ability of ANN and SVM models in prediction processes. Also, Sensitivity analysis of the best obtained model indicated that cement and silty clay have the maximum and minimum influences on the compressive strength, respectively. In addition, investigation of the effect of measurement error of input variables showed that change in the sand content (amount) and curing time will have the maximum and minimum effects on the output mean absolute percent error (MAPE) of model, respectively. Finally, the influence of different variables on the plastic concrete compressive strength values was evaluated by conducting parametric studies.     

Assessment of different machine learning techniques in predicting the compressive strength of self-compacting concrete

The compressive strength of self-compacting concrete (SCC) needs to be determined during the construction design process. This paper shows that the compressive strength of SCC (CS of SCC) can be successfully predicted from mix design and curing age by a machine learning (ML) technique named the Extreme Gradient Boosting (XGB) algorithm, including non-hybrid and hybrid models. Nine ML techniques, such as Linear regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees (DTR), Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Network using two training algorithms LBFGS and SGD (denoted as ANN_LBFGS and ANN_SGD), are also compared with the XGB model. Moreover, the hybrid models of eight ML techniques and Particle Swarm Optimization (PSO) are constructed to highlight the reliability and accuracy of SCC compressive strength prediction by the XGB_PSO hybrid model. The highest number of SCC samples available in the literature is collected for building the ML techniques. Compared with previously published works’ performance, the proposed XGB method, both hybrid and non-hybrid models, is the most reliable and robust of the examined techniques, and is more accurate than existing ML methods (R² = 0.9644, RMSE = 4.7801, and MAE = 3.4832). Therefore, the XGB model can be used as a practical tool for engineers in predicting the CS of SCC.     

Optimization of machine learning models for predicting the compressive strength of fiber-reinforced self-compacting concrete

Fiber-reinforced self-compacting concrete (FRSCC) is a typical construction material, and its compressive strength (CS) is a critical mechanical property that must be adequately determined. In the machine learning (ML) approach to estimating the CS of FRSCC, the current research gaps include the limitations of samples in databases, the applicability constraints of models owing to limited mixture components, and the possibility of applying recently proposed models. This study developed different ML models for predicting the CS of FRSCC to address these limitations. Artificial neural network, random forest, and categorical gradient boosting (CatBoost) models were optimized to derive the best predictive model with the aid of a 10-fold cross-validation technique. A database of 381 samples was created, representing the most significant FRSCC dataset compared with previous studies, and it was used for model development. The findings indicated that CatBoost outperformed the other two models with excellent predictive abilities (root mean square error of 2.639 MPa, mean absolute error of 1.669 MPa, and coefficient of determination of 0.986 for the test dataset). Finally, a sensitivity analysis using a partial dependence plot was conducted to obtain a thorough understanding of the effect of each input variable on the predicted CS of FRSCC. The results showed that the cement content, testing age, and superplasticizer content are the most critical factors affecting the CS.     

Forecasting electricity consumption of OECD countries: A global machine learning modeling approach

Electricity is a critical utility for social growth. Accurate estimation of its consumption plays a vital role in economic development. A database that included past electricity consumption data from all OECD countries was prepared. Since national trends may be transferable from one country to another, the entire database was modeled and simulated via machine learning techniques to forecast the energy consumption of each country. Understanding similarities among the profiles of different countries could increase predictive accuracy and improve associated public policies.     

基于机器学习的区域火灾分布特征分析方法

为定量分析区域的经济发展水平、人口密度、建筑密集度、消防站分布等因素与火灾发生的关系,引入多种机器学习分类算法进行研究。利用ArcGIS 10.2对非数值型数据进行处理,并根据渔网点内火灾核密度的高低进行等级划分,使变量转化成对应的数值型数据;在确保精度的条件下,利用多次随机森林算法进行特征筛选,并对筛选后的剩余特征进行深度学习训练,同时采用支持向量机算法对所有特征进行训练,并分别构建预测模型;最终将3种算法进行加权平均融合,并通过对比4种模型ROC曲线及分类的准确度进行相应分析。以重庆市火灾警情系统中统计的真实火灾数据为例进行分析的结果显示,4种模型的准确率均高于90%;3种算法耦合后模型准确度和Kappa值分别为0.980 7和0.843 6,其结果与3种单一模型相比较为稳定准确。     

Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines

This study aims to improve the unconfined compressive strength of soils using additives as well as by predicting the strength behavior of stabilized soils using two artificial-intelligence-based models. The soils used in this study are stabilized using various combinations of cement, lime, and rice husk ash. To predict the results of unconfined compressive strength tests conducted on soils, a comprehensive laboratory dataset comprising 137 soil specimens treated with different combinations of cement, lime, and rice husk ash is used. Two artificial-intelligence-based models including artificial neural networks and support vector machines are used comparatively to predict the strength characteristics of soils treated with cement, lime, and rice husk ash under different conditions. The suggested models predicted the unconfined compressive strength of soils accurately and can be introduced as reliable predictive models in geotechnical engineering. This study demonstrates the better performance of support vector machines in predicting the strength of the investigated soils compared with artificial neural networks. The type of kernel function used in support vector machine models contributed positively to the performance of the proposed models. Moreover, based on sensitivity analysis results, it is discovered that cement and lime contents impose more prominent effects on the unconfined compressive strength values of the investigated soils compared with the other parameters.     

Punching shear capacity estimation of FRP-reinforced concrete slabs using a hybrid machine learning approach

Fibre-reinforced polymer (FRP) provides an alternative reinforcement for concrete flat slabs. This research proposes a hybrid machine learning model for predicting the ultimate punching shear capacity of FRP-reinforced slabs. The model employs the least squares support vector machine (LS-SVM) to discover the mapping between the influencing factors and the slab punching capacity. Furthermore, the firefly algorithm (FA), a population-based metaheuristic, is utilised to facilitate the LS-SVM training. A data-set which contains actual tests of FRP-reinforced concrete slabs is utilised to construct and verify the proposed approach. The contribution of this research is to establish a hybrid machine method, based on the LS-SVM and FA algorithms, for meliorating the prediction accuracy of FRP-reinforced slabs’ ultimate punching shear capacity. Experimental results demonstrate that the new model has achieved roughly 55 and 15% reductions in terms of Root Mean Squared Error compared with the formula-based and Artificial Neural Network methods, respectively.     

基于聚类分析和支持向量机的滑坡易发性评价

在将支持向量机(support vector machine,SVM)等机器学习模型用于区域滑坡易发性评价时,大都随机或主观地选取非滑坡栅格单元,不能保证所选的非滑坡栅格单元是真正的"非滑坡"。为解决此问题,提出基于聚类分析和SVM的滑坡易发性评价模型。该模型首先用自组织映射(self-organizing mapping,SOM)神经网络对滑坡易发性进行聚类分析;然后从极低易发区中选择非滑坡栅格单元,确保所选非滑坡栅格单元是高概率的"非滑坡";最后采用SVM模型基于已知滑坡、所选非滑坡和环境因子对滑坡易发性进行评价。将提出的SOM-SVM模型用于三峡库区万州区滑坡易发性评价,并将得到的易发性结果与随机选取非滑坡的单独SVM模型结果做对比。结果显示SOM-SVM模型具有比单独SVM模型更高的成功率和预测率,表明SOM神经网络能更准确地选取非滑坡栅格单元。     

基于机器语言的建筑混凝土设计

建筑混凝土的强度受多种因素的影响,其强度的预测是一个多指标综合复杂问题。基于机器算法支持向量机建立了建筑混凝土的强度设计与预测的支持向量机模型,其中模型参数通过粒子群算法进行选择和优化。将建立的模型计算结果与实测混凝土28 d抗压强度进行比较,讨论了各因素与强度值之间的关系。研究表明:预测结果与实测结果一致,可见该模型可以很好的为混凝土设计提供依据。     

四类常见边坡岩石类别识别和边界范围确定的方法

岩质边坡岩石的分类与边界范围的确定对于边坡稳定性的分析至关重要,目前人工方法效率低且受主观因素影响,所以基于Tensorflow建立了岩质边坡图像集分析的卷积神经网络模型,通过卷积操作和池化操作分别对80000张岩质边坡图像进行特征信息的提取和压缩,然后对网络模型进行训练从而实现了岩质边坡岩石的自动识别与分类;采用训练集和测试集中的岩质边坡图像对模型进行检验分析,训练集准确率达到了98%,测试集准确率达到了90%,显示了训练之后的网络模型具有良好的鲁棒性,达到了理想的训练效果。接下来以边坡不同岩石的颜色为主要区分依据,利用深度学习回归操作对岩质边坡不同种类岩石的范围进行确定,为验证算法效果,选取标准彩色岩质边坡图像进行仿真试验,边界检测效果准确。最终采用深度学习建立的网络模型,实现了岩质边坡岩石识别与边界范围划分的快速化、自动化,为后续将图像识别获取的岩质边坡信息导入团队自主研发的GeoSMA-3D软件中,作为对岩质边坡等级判定的重要参数。     

边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究

介绍了人工智能领域最新的基于结构风险最小化原理的数据挖掘算法---支持向量机算法,运用Matlab语言编写了程序,采用不同的核函数对具体的边坡工程实例作了计算,并将人工神经元网络计算结果与之对比,可见无论是在学习或预测精度方面,支持向量机算法较基于经验风险最小化原理的人工神经元网络算法都有很大的优越性,可以运用于实际工程。     

双掺粉煤灰和矿渣混凝土强度的BP网络预测模型

双掺粉煤灰和矿渣混凝土的强度发展机理复杂,不能用传统的水灰比线性函数来预测,利用BP神经网络模型来预测其3、28和56d的抗压强度.结果表明:BP神经网络具有较强的非线性映射能力,预测结果比较理想,可以指导实际工程;早龄期的混凝土强度预测值与实测值之间的误差较大,随着粉煤灰和矿渣的二次水化反应逐渐充分,强度发展趋于规律化,预测误差相应变小.     

全景绿视率自动识别和计算研究

绿视率是用于绿色空间感知的直观评价标准，传统研究的绿视率多基于平面影像进行计算，不能完全反映三维空间中人对绿量的主观感受。基于全景影像，提出全景绿视率的概念，通过全景相机获取球面全景照片，将等距圆柱投影转换为等积圆柱投影，利用基于语义分割的卷积神经网络模型，自动识别植被区域面积以实现全景绿视率自动化识别和计量。通过比较5项卷积神经网络模型对绿视率的识别效果，显示出Dilated ResNet-105神经网络模型具有最高的识别准确度。以武汉市武昌区紫阳公园为例，对各级园路和广场的全景绿视率进行计算和分析。将卷积神经网络的识别结果同人工判别结果进行对比研究，结果显示：使用Dilated ResNet-105卷积神经网络对绿植范围识别的平均交并比（mIoU）为62.53%，与人工识别的平均差异为9.17%。全景绿视率自动识别和计算可以为相关研究提供新的思路，实现客观准确、快速便捷的绿视率测量评估。     

结构表面裂缝数字图像法识别研究综述与前景展望

裂缝反映结构受力状态与安全性、耐久性,是结构现场安全性检测监测以及结构模型试验研究的重要指标之一。现有的人工裂缝识别技术难以满足工程现场与实验室需求,操作中存在测不准、高空多、效率低、记不全等缺点。相比之下,采用数字图像法进行结构表面裂缝识别,具有便捷、自动、定量、准确等优势。文章对结构表面裂缝数字图像法识别研究进行系统综述,对裂缝识别中图像预处理、裂缝识别与提取、裂缝参数计算等重要环节的常见算法进行讨论,阐述采用多视角几何三维重建方法实现裂缝成像修正与拼接、裂缝表达输出的原理与流程,结合实桥案例报道了基于无人机平台的裂缝识别研究与应用,讨论国内首部数字图像法检测规程《工程结构数字图像法检测技术规程》征求意见稿中裂缝检测的相关规定。最后,对结构表面裂缝数字图像法识别研究进行前景展望。     

煤岩微观相态FCN智能识别与分形重构

数字岩芯可提供无差别化仿真计算模型,是研究岩石物理力学性质的理想模型,精准高效建模一直制约着数字岩芯重构技术的推广。传统方法处理CT切片扫描数据费时费力,主要受限于2个方面,一是扫描层数有限;二是孔裂隙识别依赖于传统阈值分割算法。以煤岩为例,引入人工智能识别实现4种微观相态:孔隙、裂隙、高密度矿物和基质的智能识别,并开展分形重构。基于微米CT扫描建立4种微观相态数据集并进行了数据增强,开发了专用标注软件可实现跨尺度孔裂隙的准确标注。算法上优化了全卷级神经网络智能识别架构,建立Crack-FCN网络结构,网络层次少且错误率低。同时引入矢量化算法实现了裂隙面积、长度和宽度的定量计算;进而引入中心线细化算法实现了复杂裂隙拓扑结构的有效提取。最后开发局部自相似分形重构算法,并基于优化策略解决了快速插值问题,解决了相邻CT层扫描信息缺失的问题。结果表明分形插值与直线插值和三阶样条插值相比局部粗糙特性明显,且保证了裂隙断面的粗糙性和连续性。工作引入全卷级神经网络智能识别技术用于构造数字岩芯,为高效精准建立数字岩芯提供了新的技术支撑。     

基于深度学习的水体生境图像分类与质量评价——以长三角一体化先行启动区为例

【目的】面对长三角一体化地区生态高质量修复与智能化监测的更高诉求,开展基于深度学习的水体生境质量评价,旨在探索风景园林数字技术的前沿领域,为长三角一体化地区的水体生态修复与生态绿色发展提供信息化与智能化的技术支撑。【方法】采用基于深度学习的图像分类方法,通过卷积神经网络（convolutional neural networks, CNN）训练,实现大范围、大批量的水体生境卫星图像智能识别、分类与评价。【结果】构建了长三角一体化先行启动区水体生境卫星图像数据集,训练了水体生境质量评价深度学习模型,对研究范围内全域的水体生境进行了高精度、自动化的生境质量评价。【结论】深度学习模型能够长时序、大范围地对水体生境进行质量评价,为水体生境的修复实践提供技术支撑,未来可实现对长三角一体化示范区水体生境质量的跟踪监测。