基于灰色支持向量机残差修正模型的地面沉降量预测

沉降现象在各地区普遍发生,地面沉降量预测越来越受到重视。本文通过结合灰色(GM(1,1))预测模型和支持向量机(SVM)模型各自的优点,建立灰色支持向量机(GM(1,1)-SVM)残差修正模型,在突出时间序列发展趋势影响的同时降低序列中异常值的消极作用。以某高层建筑的18次地面沉降量数据为实例,检验GM(1,1)-SVM模型的预测效果。结果表明:相对单一的GM(1,1)沉降量预测模型,GM(1,1)-SVM模型相对误差小,预测精度高,对地面沉降量预测有一定指导意义。     

高路堤沉降变形预测模型研究

以某高等级公路高69 m路堤的沉降资料为研究样本,采用经修正了的非匀速填土和非等步长沉降观测时间的 GM（1,1）灰色理论预测模型进行高路堤工后最终沉降量预测,与等比级数曲线模型预测结果对比,认为这两种预测模型都能很好地预测高路堤工后最终沉降量,且灰色预测模型较等比级数曲线预测模型能更好地反映高路堤不均匀沉降趋势。同时认为考虑了沉降观测时间非等步长性和路堤填土速度不均匀性的灰色预测模型,其预测结果更符合高路堤沉降变形趋势,可进一步的研究、推广和应用。     

建筑物沉降量预测和最终沉降量早期确定的灰色Verhulst模型

根据建筑物沉降特性,首次引用灰色Verhulst模型方法建立起建筑物沉降量预测模型.能运用较少的沉降观测数据建立起可靠性很好的预测模型,并可用以早期确定建筑物的最终沉降量.这不仅可以减少沉降长期观测的浪费,同时也可较早地获知建筑物最终沉降量大小,为早期采用工程防治措施挽回时间,具有理论和实际意义.     

灰色GM(1,1)模型和Verhulst模型在喀斯特地区耕地预测中的应用——以毕节生态试验区为例

毕节生态试验区是典型的喀斯特地区,人口密度大,生态环境脆弱,水土流失严重,耕地保护尤为重要。本文以毕节地区1998—2006年常用耕地面积统计数据为基础,分别利用灰色GM(1,1)模型和Verhulst模型对该喀斯特地区常用耕地面积变化进行预测。预测结果表明,GM(1,1)模型和Verhulst模型都揭示了毕节地区常用耕地面积在未来几年呈逐年递减的趋势。但是通过模拟精度验证,研究区耕地面积原始数据变化曲线呈S型,就灰色GM(1,1)模型与Verhulst模型模拟预测结果相比较,对于原始数据的模拟,GM(1,1)模型预测精度较高,而Verhulst模型更适合研究区未来几年耕地面积变化的预测。该研究结果可为区域合理利用土地资源、编制土地利用规划和耕地保护提供依据。      

BP神经网络-灰色系统联合模型预测软基沉降量

目前软基沉降预测多采用指数曲线和双曲线延伸法,其结果不够理想,神经网络在此方面的运用也存在一定的局限,虽然GM(1,1)模型在软基沉降预测领域已得到运用,但在已有的案例中所使用的等时距模型都没有明确说明所采用的插值方法。以深圳湾西部通道填海软基沉降预测分析为例,建立BP神经网络-灰色系统联合模型来探讨解决这一问题的方法。采用BP神经网络逼近非线性插值方法构建等时距时间序列数据,在此基础上建立沉降变形时间序列的GM模型,并建立相应的时间响应函数,预测沉降量。计算实例表明,该模型短期沉降预测结果比较准确,其最终沉降预测结果具有一定的工程参考价值。     

爆炸挤淤筑堤沉降的Verhulst预测

沉降观测是爆炸挤淤筑堤质量检测的一个重要手段,目前其监测方法较多还是按传统的观测法,需要较长的观测时间,耗时耗力。通过分析灰色Verhulst模型的特点,根据实际观测资料运用灰色Verhulst模型预测了堤身各时刻的沉降量,与实际观测具有较好的符合性,并预测了堤身的最终沉降量和所需时间。结合实例预测表明,这一模型具有较好的适用性,可以在类似工程中推广应用。     

灰色线性回归组合模型在北京地面沉降分层预测中的应用

灰色系统理论GM(1,1)模型,应用于地面沉降模拟和预测中只能分析数据的指数变化规律。对于地面沉降发展过程中,存在的线性关系不能有效地反映。本文利用灰色组合模型中的第一类灰色组合模型即GM(1,1)与线性回归模型相融合。选取北京东部某地面沉降监测站2004～2012年的分层监测数据建立模型,计算出各监测层位沉降的数学模型,并以此预测各监测层位地面沉降量。结果表明：利用灰色线性回归组合模型在对地面沉降进行分层模拟和预测是可行的。在已有数据的基础上,利用数学模型进行沉降模拟时,两种模型的精度均很高,但通过模型预测未来一年沉降量时,灰色线性回归组合模型的精度,要远高于普通均值GM(1,1)模型。     

改进灰色模型对路基沉降预测的应用研究

讨论了灰色系统理论在路基沉降预测中的应用,并对等间隔的灰色模型GM（1,1）进行了改进,建立了任意间隔的非时序改进灰色模型。通过具体工程实践,给出了两种模型对路基沉降量预测结果与实测结果的比较,结果表明改进灰色模型的预测沉降量与实际沉降量更接近,精度更高,更能满足工程需要。     

改进灰色模型对路基沉降预测的应用研究

讨论了灰色系统理论在路基沉降预测中的应用 ,并对等间隔的灰色模型GM(1,1)进行了改进 ,建立了任意间隔的非时序改进灰色模型。通过具体工程实践 ,给出了两种模型对路基沉降量预测结果与实测结果的比较 ,表明改进灰色模型的预测沉降量与实际沉降量更接近 ,精度更高 ,更能满足工程需要     

地面沉降模拟计算的灰色离散GM（1，1）模型

地面沉降的模拟计算属于灰色问题,建立一个有效的灰色预测模型是十分重要的,在分析灰色线性回归组合模型模拟序列特点的基础上,建立了以原始数据直接建模的离散GM（1,1）模型（称为ODGM（1,1）模型）,将某沉降实例数据建立ODGM（1,1）模型,并与灰色线性回归组合预测模型进行比较,结果证明离散GM（1,1）模型优于灰色线性回归组合预测模型。     

苏家里新村地面及建筑物裂缝成因分析

以苏家里新村地面及建筑物裂缝调查结果和沉降监测资料为基础,应用工程地质类比法对非采矿因素引起的裂缝进行综合的定性分析,并应用FLAC3D程序对受煤矿采空区影响的建筑物进行数值模拟分析,同时归纳分析了对由于采矿因素和非采矿因素导致的地面及建筑物裂缝的成因、位置和规律。分析结果表明:苏家里新村地面及建筑物裂缝是开采沉陷引起的地表变形、填土地基不均匀沉降、河流冲蚀边坡坡脚等因素共同作用的结果。研究结果为该矿区地面建筑物的修复加固提供依据。      

Finite-difference model of land subsidence caused by cluster loads in Zhengzhou,China

Groundwater exploitation has been regarded as the main reason for land subsidence in China and thus receives considerable attention from the government and the academic community.Recently,building loads have been identified as another important factor of land subsidence,but researches in this sector have lagged.The effect of a single building load on land subsidence was neglected in many cases owing to the narrow scope and the limited depth of the additional stress in stratum.However,due to the superposition of stresses between buildings,the additional stress of cluster loads is greater than that of a single building load under the same condition,so that the land subsidence caused by cluster loads cannot be neglected.Taking Shamen village in the north of Zhengzhou,China,as an example,a finite-difference model based on the Biot consolidation theory to calculate the land subsidence caused by cluster loads was established in this paper.Cluster loads present the characteristics of large-area loads,and the land subsidence caused by cluster loads can have multiple primary consolidation processes due to the stress superposition of different buildings was shown by the simulation results.Pore water migration distances are longer when the cluster loads with high plot ratio are imposed,so that consolidation takes longer time.The higher the plot ratio is,the deeper the effective deformation is,and thus the greater the land subsidence is.A higher plot ratio also increases the contribution that the deeper stratigraphic layers make to land subsidence.Contrary to the calculated results of land subsidence caused by cluster loads and groundwater recession,the percentage of settlement caused by cluster loads in the total settlement was 49.43%and 55.06%at two simulated monitoring points,respectively.These data suggest that the cluster loads can be one of the main causes of land subsidence.     

基于三维激光扫描的空间地物建模

利用地面三维激光扫描仪获取的空间数据,进行了三维空间地物建模研究。以建筑物建模为例,首先从原始数据中分离提取建筑物,然后对得到的建筑物数据进行去噪处理,再通过整体匹配纠正并对原始测量数据进行重新采样和拼接配准,建立了由三角网构成的三维表面模型。结果表明,所构建的三维表面模型较好地表达了建筑物的几何特征,户外实验也验证了上述过程可以实现对建筑物快速三维建模。     

建筑物对浅埋隧道开挖地表沉降的影响

采用解析法研究穿越地表建筑物浅埋隧道开挖引起的地表沉降。由无建筑物时岩土体开挖引起的地表沉降公式及半无限平面在均布荷载下的相对沉陷,推导出了穿越地表建筑物浅埋隧道施工引起的地表沉降公式,并通过实例验证了此方法的可行性。采用上述方法研究了地表建筑物的重量及其与浅埋隧道位置关系对地表沉降的影响,研究结果表明：浅埋隧道开挖引起的地表沉降随建筑物重量的增大而增大;建筑物中心到隧道轴线的水平距离是对地表沉降的一个重要影响因素,超过一定范围时建筑物的存在对地表沉降的影响可以忽略不计。研究结果可为类似隧道工程提供一定参考。     

Centrifuge modeling of land subsidence caused by the high-rise building group in the soft soil area

With the increase of the high-rise buildings, land subsidence induced by human activities becomes a major problem. Land subsidence occurs slowly, but the accumulation results in the cracks in the road, the damage to the pipelines and in the tilting or the cracking of the buildings. With the withdrawal of groundwater controlled reasonably, the engineering-environmental effect of the dense high-rise building group comes to be the main cause of land subsidence. Based on the high-rise building group in the soft soil area in Shanghai, the mechanism of land subsidence is studied in this paper by the centrifuge model tests. The central area of the building group has larger subsidence and the subsidence superimposition effect is obvious. It can exceed the allowance and cause land subsidence hazard. The land subsidence affected by the different building distances is also studied. For smaller building distances, the subsidence superimposition effect is more obvious. The larger excess pore water pressure in the pile-base supporting layer of the central area shows that the stress superimposition effect is larger. The earth pressure under the buildings fluctuates by the disturbance of the pile tips.     

工程环境效应引起上海地面沉降预测

地面沉降是目前常见的地质灾害之一,其长期的积累给城市带来巨大的经济损失,成为制约城市发展的主要因素。进入20世纪90年代以来,工程环境效应诱发的沉降已经成为上海地面沉降的新趋势,对于外荷载引起的地面沉降过程而言,影响因素较多,既无法用明确的数学关系式表达,又非黑箱那样内部结构、参数和特征一无所知,因此可将灰色预测理论应用于地面沉降的预测。针对监测和观测时间的非等时性,本文应用非等时距灰色理论模型对上海陆家嘴地区某高层建筑的沉降进行预测,并和实际监测沉降量进行了比较;对室内模型试验进行沉降预测,并和实验观测数据以及自适应神经网络系统(ANFIS)预测结果进行了比较。研究发现,对于工程环境效应引起的地面沉降,应用非等时距灰色理论模型进行沉降预测是可行、精确的。     

Study on land subsidence under different plot ratios through centrifuge model test in soft-soil territory

Since the mid-1990s, multi-storied buildings, high-rise buildings and skyscrapers have been emerging due to the new round of great-scale development on the soft-soil littoral. Land subsidence in soft-soil areas caused by engineering environmental effect, especially by construction of high-dense building groups, attracts more and more attention. The plot ratio may be one of the most important factors on engineering-induced land subsidence. Thus, three geotechnical centrifugal model tests were conducted under three conditions of different plot ratios to study the ground settlement mechanism of high-dense building groups in soft-soil territory. It is concluded that the subsidence superimposition effect is obvious in the central area of high-dense building groups; the settlement increases with the growth of plot ratio. The urban planning department should take this subsidence situation into account when determining the construction plot ratio to utilize the earth more aptly and safely.     

坑式钢管静压桩在地基加固中的应用

坑式钢管静压桩是解决既有建筑物因软弱土层地基产生沉降变形的一种技术方法。针对山西北化关铝化工有限公司质检楼地基沉降变形及工程地质条件,提出了采用坑式钢管静压桩进行加固处理的设计方案,介绍了坑式钢管静压桩施工方案和施工流程及注意事项;总结了施工过程中遇到的问题,并对施工后的监测数据进行了分析。结果表明,坑式钢管静压桩施工对软弱地基加固效果良好,可成功地解决软弱土层产生的地基沉降开裂问题。     

卡尔曼滤波在建筑沉降监测数据处理中的应用

卡尔曼滤波作为一种动态数据处理方法已广泛应用于变形监测数据处理中。本文结合合肥市某小区6号楼沉降监测数据,建立相应的卡尔曼滤波模型,通过MATLAB编程实现,成果显示该模型较好的模拟了建筑物沉降的变化规律。     

Classification and regression tree theory application for assessment of building damage caused by surface deformation

A framework of applying the classification and regression tree theory (CART) for assessing the concrete building damage, caused by surface deformation, is proposed. The prognosis methods used for approximated building hazard estimation caused by continuous deformation are unsatisfactory. Variable local soil condition, changing intensity of the continuous deformation and variable resistance of the concrete buildings require the prognosis method adapted to the local condition. Terrains intensely induced by surface deformation are build-up with hundreds of building, so the method of their hazard estimation needs to be approximated and relatively fast. Therefore, promising might be addressing problems of reliable building damage risk assessment by application of classification and regression tree. The presented method based on the classification and regression tree theory enables to establish the most significant risk factors causing the building damage. Chosen risk factors underlie foundation for the concrete building damage prognosis method, which was caused by the surface continuous deformation. The established method enabled to assess the severity of building damage and was adapted to the local condition. High accuracy of shown approach is validated based on the independent data set of the buildings from the similar region. The research presented introduces the CART to determination of the risk of building damage with the emphasis on the grade of the building damage. Since presented method bases on the observations of the damages from the previous subsidence, the method might be applied to any local condition, where the previous subsidence is known.