基于聚类-二叉树支持向量机的砂土液化预测模型

建立在统计学习理论基础之上的支持向量机（SVM）,是一种基于结构风险最小的小样本机器学习方法。经典的支持向量机主要针对二分类问题,而工程实践中遇到的往往是多分类问题。根据影响砂土液化的主要因素,采用聚类分析中的类距离思想,建立了基于聚类-二叉树的多类支持向量机的砂土液化判别模型。该模型可以通过有限样本的学习,建立砂土液化与各影响因素之间的非线性关系。研究结果表明,基于聚类-二叉树支持向量机的层次结构合理,分类精度高,泛化性好,可对砂土液化等级进行较准确判别     

砂土地震液化预测的GA_SVM_Adaboost模型

为快速准确地对砂土液化情况作出预测,选取地震烈度、地下水位、覆盖厚度、标贯击数、平均粒径、地貌单元、土质及不均匀系数为主要影响因素,运用相关性分析和因子分析模型对其进行分析和属性约减,采用遗传算法（GA）对支持向量机（SVM）的参数寻优,结合Adaboost迭代算法,建立预测砂土地震液化的GA_SVM_Adaboost模型。选用唐山地震砂土液化现场勘察资料中的329组数据对模型进行训练,利用该模型对剩余68组砂土液化数据进行预测。最后,将预测结果与GA_SVM和SVM模型预测结果进行比较。结果表明,3个模型的平均预测准确率分别为100%、98.04%、89.71%,基于因子分析的GA_SVM_Adaboost模型的预测准确性优于GA_SVM模型和SVM模型,是一种解决砂土地震液化预测问题的有效方法,具有一定的应用参考价值。      

支持向量机方法在膨胀土分类中的应用

将支持向量机方法应用于膨胀土分类问题中,建立了膨胀土分类的支持向量机模型。以膨胀土实测数据为学习样本,经过训练,得到膨胀土的分类区间。应用该模型对剩余的膨胀土数据进行预测,预测结果表明支持向量机分类模型性能良好、预测精度高、简便易行,是膨胀土判别的一种有效方法,具有广阔的应用前景。     

基于ICA-SVM的超长大直径钢管桩承载力预测

基于支持向量机（SVM）和独立分量分析（ICA）建立了超长大直径钢管桩极限承载力的预测模型。先采用独立分量分析FastICA算法从实际工程的超长大直径钢管桩试桩的实测数据样本中抽取相互独立的分量,这些分量不仅去除了相关性,还保持统计独立,并服从非高斯分布,能更好地表现数据间的本质结构;然后,确定支持向量机作为分类器,以抽取的独立分量作为支持向量机模型的输入参数,建立超长大直径钢管桩的承载力预测模型ICASVM_Q;最后,采用某大桥的工程数据对预测模型进行测试。结果表明,ICASVM_Q的预测效果明显优于以原始数据作为支持向量机模型输入的SVM_Q模型的预测效果。可见,采用将独立分量分析与支持向量机相结合的方法建模预测超长大直径钢管桩的承载力是可行的,ICASVM_Q模型的预测结果可用于超长大直径钢管桩承载力的设计参考,具有一定的工程应用价值。这种方法还可以用于其他领域的智能预测研究中。     

岩爆分类的支持向量机方法

针对岩爆分类问题,提出了基于支持向量机的分类方法。通过对影响岩爆因素的分析,运用支持向量机理论建立岩爆类别的支持向量机模型。结果表明,基于支持向量机的岩爆分类方法具有较高的准确率,该方法是科学可行的,具有广泛的应用前景。     

基于网格搜索法优化支持向量机的围岩稳定性分类模型

为科学评价围岩稳定性,本次研究借助支持向量机(SVM)处理小样本、非线性问题能力强的特性,对围岩的稳定性进行了分类。选取16组围岩数据作为学习样本,以岩石质量指标、岩石单轴饱和抗压强度、完整性系数、结构面强度系数和地下水渗水量5个指标作为模型输入,围岩稳定程度为模型输出,建立了基于支持向量机的围岩稳定性分类模型。为增强模型的推广性能,提高其预测准确率,运用改进的网格搜索方法(GSM)寻找最优的支持向量机参数,并对8组围岩数据进行预测,并同BP神经网络模型的预测结果进行对比。结果表明,建立的GSM-SVM模型对预测样本的评判结果与实际结果一致,其预测精度较BP神经网络有很大的提升。     

基于AGA的SVM需水预测模型研究

需水预测是一个由城市人口、工业水平、社会经济水平共同作用的多因素、多层次的复杂非线性系统.其结果将直接影响受区域水资源承载力约束的产业结构、布局形态等决策.作为一种集中参数预报方法,支持向量机方法具有对未来样本的较好的泛化性能,对于这类资料缺乏、系统结构尚欠清晰的问题可以取得较好的模拟和预测结果.基于此,本文将支持向量机方法引入需水预测领域,建立了需水预测支持向量机模型.同时,本文将加速遗传算法和支持向量机方法耦合起来,构造了支持向量机模型参数的自适应优化算法.模型在珠海市的应用实例表明:与简单遗传算法比较,AGA的模型参数寻优效率更高;与BP神经网络模型相比,SVM模型较好地解决了小样本、经验性等问题,并取得了较高的预测精度.     

基于PCA-DDA原理的砂土液化预测模型及应用

影响砂土液化的因素有很多,建立多指标的液化预测模型非常有必要。目前所有的多指标砂土液化预测模型,均默认选取的判别因子之间相互独立,不存在相关性,可能导致各判别因子之间存在信息叠加而发生误判。以唐山地震砂土液化的25个案例为样本,选取8个影响因素作为砂土液化预测的初始判别指标,首先采用主成分分析（PCA）对各判别指标进行分析,对存在相关性比较高的指标进行了降维处理。基于降维后的4个主成分换算得到新的样本数据,以18个案例为学习样本,建立主成分分析与距离判别分析（DDA）相结合的砂土液化预测模型。利用建立的预测模型对18个案例进行回判,结果全部正确。对其他7个案例的液化情况进行了预测,并与规范法、Seed方法、BP法、DDA法的判别结果进行分析比较,结果表明基于主成分分析与距离判别方法的砂土液化判别模型预测准确率为100%。将模型应用于工程实例,判别结果也与实际情况一致,表明该模型具有良好的预测功能,可在实际工程中应用。     

基于邻域粗糙集和支持向量机的固结系数预测

采用邻域粗糙集和支持向量机建立滹沱河某地区软土固结系数的预测模型。基于自行改装的渗透固结仪,利用公式法确定不同压力下的固结系数。通过室内试验确定土体的指标参数,采用邻域粗糙集对该指标参数进行属性约简,将约简后的指标参数作为影响因素,分别建立支持向量机和神经网络的固结系数预测模型,预测未知样本的固结系数,并与实测值进行对比。结果表明:公式法可以准确客观地确定固结系数;支持向量机和BP神经网络建立的该地区软土固结系数预测模型均可以预测区域内未知点的固结系数,且支持向量机方法的预测精度比神经网络方法的预测精度提高了约10%。本文提出的方法直接从实验数据出发,通过易获取的影响因素建立特定地区固结系数预测模型,并可预测该区域其余未知点的固结系数。     

基于支持向量机分类算法的湖泊水质评价研究

支持向量机（SVM）是由Vapnik等人提出的建立在统计学习理论基础上的一种小样本机器学习方法,最初用于解决二分类问题。由于使用结构风险最小化原则代替经验风险最小化原则,使它较好地解决了小样本情况下的学习问题。又由于采用了核函数思想,使它将非线性问题转化为线性问题来解决,降低了算法的复杂度。利用支持向量机多类分类算法,构建湖泊水环境评价模型。实验结果表明,该方法能够正确地对湖泊水环境质量进行分类评价。     

Analysis of soil erosion characteristics in small watersheds with particle swarm optimization, support vector machine, and artificial neuronal networks

Sand production by soil erosion in small watershed is a complex physical process. There are few physical models suitable to describe the characteristics of the intense erosion in domestic loess plateau. Introducing support vector machine (SVM) oriented to small sample data and possessing good extension property can be an effective approach to predict soil erosion because SVM has been applied in hydrological prediction to some extent. But there are no effective methods to select the rational parameters for SVM, which seriously limited the practical application of SVM. This paper explored the application of intelligence-based particle swarm optimization (PSO) algorithm in automatic selection of parameters for SVM, and proposed a prediction model by linking PSO and SVM for small sample data analysis. This method utilized the high efficiency optimization property and swarm paralleling property of PSO algorithm and the relatively strong learning and extending capacity of SVM. For an example of Huangfuchuan small watershed, its intensive fragmentation and intense erosion earn itself the name of “worst erosion in the world”. Using four characteristics selection algorithms of correlation feature selection, the primary affecting factors for soil erosion in this small watershed were determined to be the channel density, ravine area, sand rock proportion, and the total vegetation coverage. Based on the proposed PSO–SVM algorithm, the soil erosion modulus in the small watershed was predicted. The accuracy of the simulation and prediction was good, and the average error was 3.85%. The SVM predicting model was based on the monitoring data of sand production. The construction of the SVM erosion modulus prediction model for the small watershed comprehensively reflected the complex mechanism of soil erosion and sand production. It had certain advantage and relatively high practical value in small sample prediction in the discipline of soil erosion.     

Application of Artificial Intelligence to Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilized Soil

This paper describes two artificial intelligence techniques for prediction of maximum dry density (MDD) and unconfined compressive strength (UCS) of cement stabilized soil. The first technique uses various artificial neural network (ANN) models such as Bayesian regularization method (BRNN), Levenberg- Marquardt algorithm (LMNN) and differential evolution algorithm (DENN). The second technique uses the support vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses regression technique by introducing ε-insensitive loss function has been adopted. The inputs of both models are liquid limit (LL), plasticity index (PI), clay fraction (CF)%, sand (S)%, gravel Gr (%), moisture content (MC) and cement content (Ce). The sensitivity analyses of the input parameters have been also done for both models. Based on different statistical criteria the SVM models are found to be better than ANN models for the prediction of MDD and UCS of cement stabilized soil.     

Application of Relevance Vector Machine for Prediction of Ultimate Capacity of Driven Piles in Cohesionless Soils

This paper examines the potential of relevance vector machine (RVM) in prediction of ultimate capacity of driven piles in cohesionless soils. RVM is a Bayesian framework for regression and classification with analogous sparsity properties to the support vector machine (SVM). In this study, RVM has been used as a regression tool. It can be seen as a probabilistic version of SVM. In this study, RVM model outperforms the artificial neural network (ANN) model based on root-mean-square-error (RMSE) and mean-absolute-error (MAE) performance criteria. It also estimates the prediction variance. An equation has been developed for the prediction of ultimate capacity of driven piles in cohesionless soils based on the RVM model. The results show that the RVM model has the potential to be a practical tool for the prediction of ultimate capacity of driven piles in cohesionless soils.     

公路软基沉降预测的支持向量机模型

提出了基于支持向量机（SVM）模型对公路软基沉降进行预测的一种新方法,工程实例预测结果表明,在同样的训练均方误差下,SVM模型预测能力要优于BP神经网络模型,同时该模型能够综合利用分级加载过程中的沉降观测数据作为训练样本集,比仅依靠预压期内部分实测沉降数据的双曲线法更能反映地基土的变形趋势。因此,将建立的SVM模型应用于公路软基沉降预测能够更准确地反映实际沉降过程     

煤体瓦斯渗透率的PSO-LSSVM预测模型

结合有关煤体渗透率的众多研究成果,总结出影响煤体渗透率的3个主要因素为有效应力、温度和瓦斯压力。采用粒子群优化算法(PSO)对最小二乘支持向量机(LSSVM)的参数进行优化选择,并以上述3个因素和抗压强度为输入值,以渗透率为目标输出值,建立煤体瓦斯渗透率的PSO-LSSVM预测模型。利用25组数据进行PSO-LSSVM模型与BP神经网络及支持向量机的比较实验,PSO-LSSVM预测结果与实际值拟合程度优于其他两个模型,且具有更小的误差。实验结果表明,采用PSO-LSSVM模型可由有效应力、温度和瓦斯压力对渗透率进行较高精度的预测。      

Least square support vector machine and relevance vector machine for evaluating seismic liquefaction potential using SPT

The determination of liquefaction potential of soil is an imperative task in earthquake geotechnical engineering. The current research aims at proposing least square support vector machine (LSSVM) and relevance vector machine (RVM) as novel classification techniques for the determination of liquefaction potential of soil from actual standard penetration test (SPT) data. The LSSVM is a statistical learning method that has a self-contained basis of statistical learning theory and excellent learning performance. RVM is based on a Bayesian formulation. It can generalize well and provide inferences at low computational cost. Both models give probabilistic output. A comparative study has been also done between developed two models and artificial neural network model. The study shows that RVM is the best model for the prediction of liquefaction potential of soil is based on SPT data.