基于混合核函数HS-RVM的边坡稳定性分析

doi:10.13722/j.cnki.jrme.2016.0306

Abstract
Figure/Table
References (17)
Related Citation (15)

Download: PDF (830 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

The nonlinear characteristic of the slope stability problem is difficult to be accurately described by the traditional calculation methods，so a slope stability analysis method based on the harmony search(HS) and the relevance vector machine(RVM) is proposed. Considering the characteristics of small sample，nonlinear，high dimension of the slope safety factor prediction，the RVM is employed to quickly calculate the higher accuracy prediction and the posterior probability distribution，and then the confidence interval is established. Since the prediction effect of the RVM depends on the kernel function and its parameters，the mixed kernel function whose generalization and interpolation ability are strong is introduced；the latin hypercube sampling(LHS) is used to initialize the harmony memory；the parameters of mixed kernel function are optimized by the HS. The slope stability analysis method based on the HS-RVM is established with Matlab program，and minimizing mean absolute error(MAE) is used as an optimization target. The application examples show that the HS-RVM gives fully play to the computing power of the HS and the RVM；the HS-RVM is easy to use and has the advantages of high accuracy，high speed；it has good application in the practical engineering calculation.

Key words： slope engineering slope stability analysis relevance vector machine harmony search mixed kernel latin hypercube sampling

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	MA Chunhui1
	2
	YANG Jie1
	2
	CHENG Lin1
	2
	LI Ting1
	2
	WANG Lu1
	2

Cite this article:

MA Chunhui1,2,YANG Jie1, et al. Slope stability analysis based on HS-RVM with mixed kernel[J]. , 2017, 36(S1): 3409-3415.

URL:

https://rockmech.whrsm.ac.cn/EN/10.13722/j.cnki.jrme.2016.0306 OR https://rockmech.whrsm.ac.cn/EN/Y2017/V36/IS1/3409

[1]	余志雄，周创兵，李俊平，等. 基于v-SVR算法的边坡稳定性预测[J]. 岩石力学与工程学报，2005，24(14)：2 468-2 475.(YU Zhixiong，ZHOU Chuangbing，LI Junping，et al. Predicting slope stability base on v-SVR algorithm[J]. Chinese Journal of Rock Mechanics and Engineering，2005，24(14)：2 468-2 475.(in Chinese))
[2]	冯夏庭. 智能岩石力学导论[M]. 北京：科学出版社，2000. (FENG Xiating. Introduction to intelligent rock mechanics[M]. Beijing：Science Press，2000.(in Chinese))
[3]	林鲁生，冯夏庭，白世伟，等. 人工神经网络在边坡滑移预测中的应用[J]. 岩土力学，2002，23(4)：508-510.(LIN Lusheng，FENG Xiating，BAI Shiwei，et al. Application of artificial neural work to prediction of sliding slope[J]. Rock and Soil Mechanics，2002，23(4)：508-510.(in Chinese))
[4]	赵洪波，冯夏庭. 支持向量机函数拟合在边坡稳定性估计中的应用[J]. 岩石力学与工程学报，2003，22(2)：241-245.(ZHAO Hongbo，FENG Xiating. Application of support vector machines function fitting in slope stability evaluation[J]. Chinese Journal of Rock Mechanics and Engineering，2003，22(2)：241-245.(in Chinese))
[5]	苏国韶. 圆弧破坏型岩质边坡安全系数快速估计的高斯过程模型[J]. 应用基础与工程科学学报，2010，18(6)：959-966.(SU Guoshao. Fast estimation of safety factor for circular failure rock slope using gaussian process model[J]. Journal of Basic Science and Engneering，2010，18(6)：959-966.(in Chinese))
[6]	ZHAO H B，YIN S D，RU Z L. Relevance vector machine applied to slop stability analysis[J]. International Journal for Numerical and Analytical Methods in Geomechanics，2012，36：643-652.
[7]	罗亦泳，张豪，张立亭. 基于进化相关向量机的边坡安全系数估算[J]. 人民黄河，2016，38(2)：103-107.(LUO Yiyong，ZHANG Hao，ZHANG Liting. Estimation of slope safety factor based on evolutionary relevance vector machine[J]. Yellow River，2016，38(2)：103-107.(inChinese))
[8]	GEEM Z W，KIM J H，LOGANATHAN G V. A new heuristic optimization algorithm：harmony search[J]. Simulation，2001，76(2)：60-68.
[9]	ZOU D X，GAO L Q，LI S，et al. An effective global harmony search algorithm for reliability problems[J]. Expert Systems with Applications，2011，38(4)：4 642-4 648.
[10]	TIPPING M E. Sparse bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research，2001，1(3)：211-244.
[11]	DAI X S，YUAN X F，ZHANG Z J. A self-adaptive multi-objective harmony search algorithm based on harmony memory variance[J]. Applied Soft Computing，2015，35：541-557.
[12]	LIU D T，ZHOU J B，PAN D W，et al. Lithium-ion battery remaining useful life estimation with an optimized relevance vector machine algorithm with incremental learning[J]. Measurement，2015，63：143-151.
[13]	TIPPING M E，FAUL A C. Fast marginal likelihood maximisation for sparse bayesian models[C]// Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics. Florida：Key West，2006：1-13.
[14]	SHIELDS M D，ZHANG J X. The generalization of latin hypercube sampling[J]. Reliability Engineering and System Safety，2016，148：96-108.
[15]	舒苏荀，龚文惠. 边坡稳定分析的神经网络改进模糊点估计法[J]. 岩土力学，2015，36(7)：2 111-2 116.(SHU Suxun，GONG Wenhui. An improved fuzzy point estimate method for slope stability analysis based on neural network[J]. Rock and Soil Mechanics，2015，36(7)：2 111-2 116.(in Chinese))
[16]	ZHENG D J，CHENG L，BAO T F，et al. Integrated parameter inversion analysis method of a CFRD based on multi-output support vector machines and the clonal selection algorithm[J]. Computers and Geotechnic，2013，47：68-77.
[17]	郑志成，徐卫亚，徐飞，等. 基于混合核函数PSO-LSSVM的边坡变形预测[J]. 岩土力学，2012，33(5)：1 421-1 426.(ZHENG Zhicheng，XU Weiya，XU Fei，et al. Forecasting of slope displacement based on PSO-LSSVM with mixed kernel[J]. Rock and Soil Mechanics，2012，33(5)：1 421-1 426.(in Chinese))