共查询到16条相似文献，搜索用时 245 毫秒
1.
2.
为了建立高精度的边坡位移预测模型,文章采用基于粒子群优化(PSO)的双稀疏相关向量机(DSRVM)建立边坡稳定性和影响因素之间的非线性关系。双稀疏相关向量机是在变分和相关向量机(RVM)框架下提出的一种多核组合优化的方法,相比于RVM和其他多核学习方法,DSRVM不仅有更少的训练时间,并且能够得到更高的预测精度。由于DSRVM的核参数对预测效果的影响较大,文章采用粒子群算法实现多个核参数的优化选取并应用于边坡位移预测。最后将本文提出的基于粒子群优化的双稀疏相关向量机(PSO-DSRVM)预测结果与极限学习机(ELM)和小波神经网络(WNN)预测结果进行对比,通过均方根误差(RMSE)、复相关系数(R2)和平均相对预测误差(ARPE)进行评价,验证了PSO-DSRVM模型在边坡变形预测上的可行性。 相似文献
3.
提出一种基于支持向量机的岩质边坡稳定性预测方法。该方法地很好的表达了岩质边坡稳定性与其影响因素之间的非线性映射关系,并应用该方法建立了相应的模型。预测结果表明,利用该方法进行岩质边坡稳定性预测是可行的、有效的。 相似文献
4.
基于灰色最小二乘支持向量机的边坡位移预测 总被引：1，自引：0，他引：1
利用边坡实测位移序列预测边坡未来时间的位移,可以有效地判断边坡的稳定性。在分析了灰色预测方法和最小二乘支持向量机各自的优缺点的基础上,提出了将二者相结合的一种新的预测模型--灰色最小二乘支持向量机预测模型。新模型既发挥了灰色预测方法中“累加生成”的优点,弱化了原始序列中随机扰动因素的影响,增强了数据的规律性,又充分利用了最小二乘支持向量机求解速度快、易于描述非线性关系的优良特性,避免了灰色预测方法及模型存在的理论缺陷。同时,采用遗传算法进行了模型的参数优化,通过2个工程实例说明灰色最小二乘支持向量机模型预测边坡位移的有效性,具有较高的精度。 相似文献
5.
6.
基于混合核函数PSO-LSSVM的边坡变形预测 总被引：2，自引：0，他引：2
支持向量机（SVM）的核函数类型和超参数对边坡位移时序预测的精度有重要影响。鉴于局部核函数学习能力强、泛化性能弱,而全局核函数泛化性能强、学习能力弱的矛盾,通过综合两类核函数各自优点构造了基于全局多项式核和高斯核的混合核函数,并引入粒子群算法（PSO）对最小二乘支持向量机（LSSVM）超参数进行全局寻优,提出了边坡位移时序预测的混合核函数PSO-LSSVM模型。将模型应用于锦屏一级水电站左岸岩石高边坡变形预测分析,并与传统核函数支持向量机预测结果进行对比分析。结果表明,该模型较传统方法在预测精度上有了明显提高,预测结果科学可靠,在边坡位移时序预测中具有良好的实际应用价值。 相似文献
7.
8.
应用3D-? 软件对西南某大型水电站左岸边坡开挖过程进行三维数值模拟,模拟结果表明：开挖坡面产生不同程度的张拉应力区域;缆机平台和拱肩槽槽坡底部产生一些竖直方向的回弹变形和水平向坡外的变形;5#梁山脊在拱肩槽开挖后将产生进一步的卸荷松弛,表层岩体稳定性将可能恶化,f42-9断层以上的大块岩体将是一个潜在的威胁;根据以上分析对开挖边坡制定了分层开挖、分层加固的方案,支护方案采用预应力锚索及排水系统的组合形式进行加固,支护后的稳定性计算表明,采用的支护措施是有效的,达到了工程设计的要求。 相似文献
9.
10.
金沙江溪洛渡水电站拱肩槽工程边坡块体稳定性评价 总被引：1，自引：0，他引：1
采用层次性分析原理，研究了金沙江溪洛渡水电站拱肩槽工程边坡各类结构面和临空面组合而成的块体特征，将边坡块体分为确定性块体、半确定性块体和随机块体三个层次；采用块体理论计算评价了不同层次的块体在天然、地震、爆破、地下水状况下的稳定性，并对影响块体稳定性各种内外因素做了敏感性分析，建立了一套非规则边坡块体稳定性分析评价的技术思路和方法体系。研究表明，拱肩槽边坡出现确定性块体的可能性较小，边坡中的不稳定块体大部分为半确定性块体，且规模较小，影响深度有限，切割边界不完善。 相似文献
11.
采用数值模拟方法研究和论证我国西南某水电站拱肩槽高边坡的稳定性。重点对左岸拱肩槽边坡在自然状态下和施工开挖过程中以及开挖后的应力、应变场特征和演化规律进行了二维有限元分析，并据此对边坡的稳定性进行分析与评价，为设计和施工提供了科学依据。 相似文献
12.
Slope reliability analysis by updated support vector machine and Monte Carlo simulation 总被引：1，自引：0，他引：1
This paper presents a new methodology for slope reliability analysis by integrating the technologies of updated support vector machine (SVM) and Monte Carlo simulation (MCS). MCS is a powerful tool that may be used to solve a broad range of reliability problems and has therefore become widely used in slope reliability analysis. However, MCS often involves a great number of slope stability analysis computations, a process that requires excessive time consumption. The updated SVM is introduced in order to build the relationship between factor of safety and random variables of slope, contributing to reducing a large number of normal computing tasks and enlarging the problem scale and sample size of MCS. In the algorithm of the updated SVM, the particle swarm optimization method is adopted in order to seek the optimal SVM parameters, enhancing the performance of SVM for solving complex problems in slope stability analysis. Finally, the integrating method is applied to a classic slope for addressing the problem of reliability analysis. The results of this study indicate that the new methodology is capable of obtaining positive results that are consistent with the results of classic solutions; therefore, the methodology is proven to be a powerful and effective tool in slope reliability analysis. 相似文献
13.
Slope reliability analysis using a support vector machine 总被引：6，自引：0，他引：6
The first-order second-moment method (FOSM) reliability analysis is commonly used for slope stability analysis. It requires the values and partial derivatives of the performance function with respect to the random variables for the design. Such calculations can be cumbersome when the performance functions are implicit. Implicit performance functions are normally encountered when the slope is geologically complicated and the limit equilibrium method (LEM) is used for the stability analysis.
To address this issue, this paper presents a support vector machine (SVM)-based reliability analysis method which combines the SVM with the FOSM. This method employs the SVM method to approximate the implicit performance functions, thus arriving at SVM-based explicit performance functions. The SVM method uses a small set of the actual values of the performance functions obtained via the LEM for complicated slope engineering. Using the SVM model, a large number of values and partial derivatives of the performance functions can be obtained for conventional reliability analysis using the FOSM. Examples are given to illustrate the proposed SVM-based slope reliability analysis. The results show that the proposed approach is applicable to slope reliability analysis which involves implicit performance functions. 相似文献
14.
针对某核电取水隧洞工程,采用非线性的动力分析方法,用Flac3D建立大型三维有限差分模型,模拟隧洞洞口段在场址时程地震波作用下的地震响应规律,同时通过建立隧洞洞口处回填高边坡的二维有限元模型,进行洞口边坡在地震动作用下的稳定性分析,得出其边坡滑动面位置和动力安全系数时程曲线。通过场址地震波的输入,探讨隧洞洞口及边坡的结构响应特点,得出隧洞洞口衬砌内力随地震波作用的时程变化曲线,绘制隧洞衬砌内力图,同时给出隧洞洞口段高边坡安全系数。分析结果表明,隧洞洞口抗震的薄弱部位位于隧洞拱肩及边墙位置。分析方法及结论对于隧洞的抗震设计具有一定的参考价值。 相似文献
15.
The Dynamic Evaluation of Rock Slope Stability Considering the Effects of Microseismic Damage 总被引：1，自引：1，他引：0
N. W. Xu F. Dai Z. Z. Liang Z. Zhou C. Sha C. A. Tang 《Rock Mechanics and Rock Engineering》2014,47(2):621-642
A state-of-the-art microseismic monitoring system has been implemented at the left bank slope of the Jinping first stage hydropower station since June 2009. The main objectives are to ensure slope safety under continuous excavation at the left slope, and, very recently, the safety of the concrete arch dam. The safety of the excavated slope is investigated through the development of fast and accurate real-time event location techniques aimed at assessing the evolution and migration of the seismic activity, as well as through the development of prediction capabilities for rock slope instability. Myriads of seismic events at the slope have been recorded by the microseismic monitoring system. Regions of damaged rock mass have been identified and delineated on the basis of the tempo-spatial distribution analysis of microseismic activity during the periods of excavation and consolidation grouting. However, how to effectively utilize the abundant microseismic data in order to quantify the stability of the slope remains a challenge. In this paper, a rock mass damage evolutional model based on microseismic data is proposed, combined with a 3D finite element method (FEM) model for feedback analysis of the left bank slope stability. The model elements with microseismic damage are interrogated and the deteriorated mechanical parameters determined accordingly. The relationship between microseismic activities induced by rock mass damage during slope instability, strength degradation, and dynamic instability of the slope are explored, and the slope stability is quantitatively evaluated. The results indicate that a constitutive relation considering microseismic damage is concordant with the simulation results and the influence of rock mass damage can be allowed for its feedback analysis of 3D slope stability. In addition, the safety coefficient of the rock slope considering microseismic damage is reduced by a value of 0.11, in comparison to the virgin rock slope model. Our results demonstrate that microseismic activity induced by construction disturbance only slightly affects the stability of the slope. The proposed feedback analysis technique provides a novel method for dynamically assessing rock slope stability and can be used to assess the slope stability of other similar rock slopes. 相似文献
16.
基于三维非线性有限元的边坡稳定分析方法 总被引：3，自引：0，他引：3
刚体极限平衡法不能反映岩体中实际的应力分布,而基于有限元的强度折减系数法在判断收敛性方面存在一些问题。为了解决这些问题,采用多重网格法,分别建立用于有限元计算的结构网格和用于计算滑面稳定安全系数的滑面网格,可以方便地获得任意滑面或滑块的稳定安全系数,从而将非线性有限元和极限平衡分析结合起来。为了提高计算规模和计算精度,采用有限元并行计算程序TFINE.Pfem进行计算,分析了网格密度对计算结果精度的影响,并应用于锦屏高边坡的稳定分析中。与刚体极限平衡法结果的对比分析表明,由于考虑了计算过程中的非线性应力调整,该方法的计算结果比刚体极限平衡法偏大,而且更符合实际情况。 相似文献